slay images
— style bible

Monet

Французский импрессионизм. Никаких контуров — край там, где встречаются два цвета. Разбитые мазки чистого пигмента. Цветные тени. Свет — главный герой.

Стабильный Живопись

←→

Длинный~3492 Короткий~1590 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> CLAUDE MONET STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Claude Monet (1840–1926), French Impressionism. Monet's radical premise: the subject of the painting is not the thing depicted, but the light falling on it at a specific moment. A haystack, a cathedral, a woman in a garden — all are pretexts for capturing the quality of light at a particular hour and season. Forms dissolve. Edges disappear. What remains is colour, vibration, atmosphere. THE CORE TECHNIQUE: BROKEN COLOUR No mixed paint producing smooth transitions. Instead, small separate strokes of pure or near-pure pigment placed adjacent on the canvas. At viewing distance the eye blends them optically — this creates a luminous vibration impossible with mixed paint. Stroke types: - Comma dabs: short curved marks, for foliage, water sparkle, atmospheric shimmer - Horizontal strokes: for water surfaces, reflections, open sky - Vertical strokes: for upright elements, figures, tree trunks — but broken, not continuous - Mosaic dabs: for densely packed surfaces (flower beds, lily pads) Stroke direction always follows the form or the light — not arbitrary. NO HARD OUTLINES — EVER. This is the rule that makes or breaks the style. Forms are defined entirely by colour difference between adjacent areas. Where a warm lit area meets a cool shadowed area, the 'edge' is simply that boundary. No line drawn over it. COLOUR AND SHADOW SYSTEM Monet understood that shadows are not grey or black — they are coloured. WARM LIGHT → COOL SHADOWS: - Golden hour light: warm amber-yellow on lit surfaces - Shadows: blue-violet, cool mauve, green-blue - This warm/cool opposition makes the painting vibrate COOL LIGHT → WARM SHADOWS: - Overcast or blue sky light: cool blue-white - Shadows: warm violet, pink, soft sienna - Less dramatic but luminous PURE PALETTE — Monet's colours: - Cadmium yellow / lemon yellow (sunlight, warm highlights) - Rose madder / vermillion (flowers, warm skin, sunset) - Cerulean blue / cobalt blue (sky, shadows, water) - Viridian / emerald (foliage in full light) - Cobalt violet / blue-violet (deep shadows) - White (mixed into every highlight, used pure for sparkle) - No black. Shadow is always a dark value of a colour, never grey or black. ATMOSPHERE — THE INVISIBLE SUBJECT Every Monet painting has an atmosphere that changes what the colours mean: MORNING MIST: cool grey-blue dominates, forms half-dissolved, highlights pearl-white, shapes emerging from haze. Garden or water scene. Stillness, potential. GOLDEN SUMMER HOUR: warm amber-rose light raking across the scene, long violet shadows, everything touched with gold. High saturation. Maximum life. MIDDAY SUMMER: high overhead light, bleached brights, dense saturated colour in shadows. Figures cast short dark shadows. OVERCAST: flat even pearl light, no cast shadows, colours appear true without warm boost. Contemplative. AUTUMN: orange-gold foliage, warm amber light, ochre and sienna in the ground, early blue shadows. Melancholy warmth. WATER SUBJECTS: Monet's signature. Reflective surface broken into horizontal strokes. Sky colour + reflection + own colour of water = three colour layers. Lily pads as flat green strokes floating on reflected colour. No line where water 'edge' is. SETTINGS (Monet's world): - Garden at Giverny: flower beds, lily pond, Japanese bridge, weeping willows - River scene: poplar trees, still water, reflections - Coastal: cliffs, sea in multiple blues, beach, boats - Grain stacks or haystacks in open field - Cathedral facade (abstract, colour study) - Interior with window: light pouring in, figure at the light source HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. In Monet style: clothing is colour and light, not fabric. Describe dominant colour only. 'White dress catching warm light', 'dark coat dissolving into shadow'. The brushwork handles the rest. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Use Monet-appropriate settings: garden, lily pond, river, coastal, field, cathedral, interior with window. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Choose atmosphere type: morning mist / golden summer hour / midday summer / overcast / autumn. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Claude Monet French Impressionism oil painting style. No hard outlines anywhere — all edges are colour meeting colour. Short broken comma-dab brushstrokes of pure unmixed pigment placed side by side for optical blending. Coloured shadows in violet, blue-violet, and green — never grey or black. Light is the true subject. Forms dissolve into atmosphere at edges. Pure luminous palette: cadmium yellow, rose madder, cerulean, viridian, cobalt violet, white. No black used. Single oil painting scene, no text, no panels, no outlines.' 8. NEGATIVE (append verbatim): 'Avoid: hard outlines, black lines anywhere, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, flat digital illustration, dark gloomy palette, grey or black shadows, smooth blended gradients, sharp crisp edges, western comic style' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"impressionist_painting","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"4:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:4/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> CLAUDE MONET STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Claude Monet French Impressionism. The subject is light itself — the scene is a pretext for capturing how light falls, scatters, and changes. No hard outlines — edges are where two colours meet. Colour laid in loose, broken strokes of pure pigment placed side by side, vibrating optically. The painting is arrested at the moment of impression. No black outlines ever. Broken colour: short comma-shaped dabs of varied hue side by side. Shadows always coloured — cool violet, blue, or green against warm light. Palette: pure colours loosely mixed — cadmium yellow, rose madder, cerulean blue, viridian, cobalt violet. Never muddy. Highlights near-white with warm or cool tint. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings) — suggested, not detailed. Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. In Monet style, describe colour only — paint dissolves fabric into light and atmosphere. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Claude Monet French Impressionism painting style. No hard outlines — all edges are colour meeting colour. Broken comma-dab brushstrokes of pure pigment placed side by side for optical colour mixing. Coloured shadows in violet, blue, or green. Light is the true subject. Loose dissolution of form into atmosphere. Vibrant pure palette, never muddy. Single oil painting scene, no text, no panels.' NEGATIVE (append verbatim): 'Avoid: hard outlines, black lines, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, blurry in an unintentional way, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, flat digital illustration, dark gloomy palette, western comic style, sharp crisp edges' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"impressionist_painting","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"4:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:4/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Claude Monet French Impressionism oil painting style. No hard outlines anywhere — all edges are colour meeting colour. Short broken comma-dab brushstrokes of pure unmixed pigment placed side by side for optical blending. Coloured shadows in violet, blue-violet, and green — never grey or black. Light is the true subject. Forms dissolve into atmosphere at edges. Pure luminous palette: cadmium yellow, rose madder, cerulean, viridian, cobalt violet, white. No black used. Single oil painting scene, no text, no panels, no outlines. Avoid: hard outlines, black lines anywhere, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, flat digital illustration, dark gloomy palette, grey or black shadows, smooth blended gradients, sharp crisp edges, western comic style

Копировать [Image generation hint, STYLE: French Impressionist oil painting, no outlines, broken comma-dab brushstrokes of pure pigment, coloured shadows in violet and blue, vibrant pure palette, luminous natural light as the main subject]

Manet

Реализм / прото-импрессионизм. Плоские пятна цвета, смелые чёрные, прямой конфронтационный взгляд. Видимый мазок как высказывание.

Экспериментальный Живопись

←→

Длинный~3420 Короткий~1604 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> ÉDOUARD MANET STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Édouard Manet (1832–1883). The hinge between academic painting and Impressionism. Not quite one, not quite the other — he refused both. Where academic painters laboured over smooth blended surfaces and correct chiaroscuro, Manet painted in bold flat patches of colour with confident abrupt transitions. Where Monet dissolved form into light, Manet kept form — solid, direct, present. His subjects look back at you. They are not idealized or romanticized. They are there, in the room, being observed and observing in return. CORE TECHNIQUE: THE 'TACHE' Manet's fundamental unit is the 'tache' — a patch of flat tone that represents a plane of colour as it appears to the eye in a single glance. Not blended. Not gradated. A single confident application of colour: this fabric is this colour in this light. Done. Move on. This creates: - Strong, readable forms - Abrupt transitions between light and shadow (less mid-tone than academic painting) - A surface that looks painted — intentionally, honestly - Speed and confidence as visual qualities TONAL STRUCTURE Manet uses fewer tonal steps than his contemporaries. Where an academic painter might have five values from light to dark, Manet often uses three: light, mid, dark. Sometimes just two. The abruptness is the point. BLACKS: Manet loved black and used it freely as a positive colour element — not as shadow darkness, but as a colour in its own right. Dark clothing, dark backgrounds, dark accents. His blacks are warm or cool depending on context. This distinguishes him from Impressionists who avoided black entirely. LIGHT SYSTEM Manet's light is not theatrical. It is direct, even, clear — the light of a studio with good windows, or a café, or an outdoor scene in soft daylight. Not the raking amber light of golden hour. Not the deep chiaroscuro shadow drama of Rembrandt. The light exists to reveal the subject, not to create atmosphere. Types: STUDIO / INDOOR: soft diffused light from one side. Even illumination. Shadows present but not dramatic. OUTDOOR: flat bright daylight or soft overcast. No strong cast shadows. CAFÉ / SOCIAL: warm interior ambient light. Tables, glasses catching light. PALETTE Manet's specific colours: - Black: used directly, warm (mars black) or cool (ivory black) - White: bright, clean, used for shirt fronts, tablecloths, highlights - Warm ochre/sienna: skin undertones, warm backgrounds - Deep navy / Prussian blue: clothing, shadows - Crimson / rose: lips, flowers, accent colour - Green-grey / olive: backgrounds, foliage - Cream / ivory: skin in light, light surfaces SUBJECTS AND SETTINGS Manet painted modern Parisian life — cafés, gardens, studios, racecourses, bars. His figures are contemporary, dressed in current fashion. For our purposes, translate any scene into Manet-appropriate settings: - Café or restaurant interior: warm light, marble table, glass in hand - Garden or terrace: outdoor light, modern clothing - Interior room: window light, contemporary furnishings - Bar scene: bottles, mirror behind, people at bar - Any social encounter: two people talking, someone reading, a moment of waiting DIRECT GAZE: Manet's subjects frequently make eye contact with the viewer. This is a deliberate choice — use it for moments of psychological intensity or confrontation. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. Manet renders clothing as flat confident colour patches. Describe: garment + dominant colour. 'Black coat', 'pale grey dress', 'white shirt, dark trousers'. The tache handles the rest. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' Gaze direction: at viewer / away / at other character — choose deliberately. 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Use Manet-appropriate settings: café, garden, studio, interior, bar, social encounter. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Choose light type: studio/indoor / outdoor flat / warm interior / café social. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Édouard Manet French Realist oil painting style. Bold flat colour patches — taches — with abrupt strong tonal transitions and minimal gradation. Confident economical brushwork, visible paint surface. Deep rich blacks used as positive colour elements alongside warm cream, ochre, navy, and crimson. Figures solid and direct with clear psychological presence and contemporary immediacy. Loosely suggested or flat background. Clear even studio or outdoor light, no theatrical chiaroscuro. Single painting scene, no text, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: Impressionist soft blur and dissolution, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, smooth airbrush gradient blending, dark theatrical Rembrandt lighting, western comic style, academic over-blended surfaces' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"manet_realist_painting","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> EDOUARD MANET STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Edouard Manet, French Realism/Proto-Impressionism. Where Monet dissolves form into light, Manet asserts it. Bold flat areas of colour. Strong value contrasts. Figures rendered with directness and psychological presence — they look back at you. Sketchy loose background, precise face. The painting acknowledges it is a painting. Broad flat colour areas with minimal gradation — 'taches' (patches of flat tone). Strong tonal jumps: light abruptly next to dark. Loose, confident, economical brushwork. Figures solid and present; backgrounds suggested or flat. Visible paint surface. Palette: rich deep blacks used confidently, warm ivory, cream, strong red accents, deep navy, warm ochre. Light flat or diffused — drama from subject matter, not theatrical lighting. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. Describe colour + type — Manet renders fabric as flat confident colour patches. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Edouard Manet French Realist oil painting style. Bold flat colour patches with strong tonal contrast and minimal gradation. Confident economical brushwork, visible paint surface. Deep blacks used as positive colour elements. Figures solid and direct with psychological presence. Loose suggested background. Clear even or softly directional light, no dramatic chiaroscuro. Single painting scene, no text, no panels.' NEGATIVE (append verbatim): 'Avoid: Monet impressionist blur, photorealistic, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, flat digital vector illustration, dark theatrical lighting, western comic style, smooth airbrush blending' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"manet_realist_painting","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Édouard Manet French Realist oil painting style. Bold flat colour patches — taches — with abrupt strong tonal transitions and minimal gradation. Confident economical brushwork, visible paint surface. Deep rich blacks used as positive colour elements alongside warm cream, ochre, navy, and crimson. Figures solid and direct with clear psychological presence and contemporary immediacy. Loosely suggested or flat background. Clear even studio or outdoor light, no theatrical chiaroscuro. Single painting scene, no text, no panels. Avoid: Impressionist soft blur and dissolution, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, smooth airbrush gradient blending, dark theatrical Rembrandt lighting, western comic style, academic over-blended surfaces

Копировать [Image generation hint, STYLE: realist proto-impressionist painting, flat taches of bold colour, dramatic blacks, direct confrontational gaze, visible brushwork, modern life rendered with unflinching directness]

Van Gogh

Пост-импрессионизм. Густое импасто, закрученные направленные мазки. Мазок И ЕСТЬ эмоция. Насыщенные цвета, усиленные ради эмоциональной правды.

Стабильный Живопись

←→

Длинный~3683 Короткий~1611 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> VINCENT VAN GOGH STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Vincent van Gogh (1853–1890). Post-Impressionism taken to its emotional extreme. Van Gogh looked at the world and painted not what was there but what it felt like to be there. His technique — thick impasto, swirling directional brushstrokes, intense colour — is the direct physical record of an emotional response. The paint has weight and direction. Every stroke is a decision. The surface of a Van Gogh painting is a map of feeling. IMPASTO AND BRUSHSTROKE SYSTEM Impasto: paint applied thickly, sometimes directly from the tube, sometimes with palette knife. The texture is physical — ridges and peaks of paint catch light. The surface is three-dimensional. STROKE DIRECTIONS — each element has its own stroke logic: SKY: long swirling arcs that flow and spiral. Night sky: concentric spiral swirls around stars and moon, flowing bands of movement. Day sky: sweeping curved horizontal-to-arc strokes. Storm sky: turbulent crossing strokes. CYPRESS TREES: twisting upward flame strokes. The tree doesn't have a single straight line in it. Every stroke curves and reaches upward. Dark blue-green. WHEAT FIELDS: strong parallel diagonal or horizontal strokes following the slope of the land. Yellow-gold with green and ochre shadows. Wind-effect: strokes tilting in one direction. WATER: horizontal flowing strokes with colour reflections. River or sea: sweeping parallel marks. BUILDINGS / VILLAGE: shorter geometric strokes following wall planes. Windows as dark rectangular marks. Roofs in warm sienna or ochre. FACES AND FIGURES: strokes follow the contours of the face (cheekbone strokes arc outward, forehead strokes horizontal, jaw strokes following the jawline). Figures simplified but expressive. Less detail than a portrait painter but more psychological intensity. GROUND AND EARTH: strokes following the terrain direction. Contour lines of the landscape visible in the stroke direction. COLOUR SYSTEM Van Gogh's colours are based on complementary contrast — opposite colours on the colour wheel placed adjacent to maximize vibrancy. PRIMARY CONTRASTS: - Yellow / violet-purple (sunflower yellow against purple shadow) - Blue / orange (cobalt blue sky against warm ochre earth) - Green / red (viridian green against touches of red in flowers or roofs) SPECIFIC COLOURS Van Gogh used: - Chrome yellow / cadmium yellow: sunflowers, wheat, lamplight, sunlight - Cobalt blue / ultramarine: sky, shadow, night - Viridian / emerald green: foliage, grass - Burnt sienna / raw umber: earth, warm shadow, skin undertone - White: mixed into all colours for daytime brightness - Black: used for outlines and deepest shadows Night palette (Starry Night register): - Deep cobalt and ultramarine for sky - Chrome yellow halos around stars and moon - Swirling blue-white for stars - Dark green-black cypress - Warm amber-ochre for lit windows Day palette (Arles summer register): - Hot chrome yellow sun and wheat - Viridian and emerald fields - Cobalt blue sky - White buildings - Sienna and ochre earth EMOTIONAL REGISTER → PAINTING STYLE Van Gogh's technique shifts with emotional intensity: ECSTATIC / ALIVE: maximum swirl, maximum saturation. Sky whirling. Everything vibrating. Use when scene is overwhelming with feeling. TENDER / STILL: strokes more controlled but still directional. Lower contrast. Warm lamp-lit interior. Quiet. ANGUISHED / TURBULENT: crossing strokes, dissonant colours. Dark blue-greens, harsh yellows, distorted perspective. MELANCHOLIC: cooler palette, slower strokes, more space in the composition. Blues dominate. SUBJECTS AND SETTINGS Night sky: the absolute Van Gogh signature. Deep blue swirling sky, star halos, crescent moon, dark landscape below. Wheat fields: high summer, hot yellow, green-blue sky, often with crows. Bedroom / interior: lamp light, warm ochre walls, simple furniture, night window. Café at night: terrace with gaslight, cobalt blue night, warm yellow interior glow. Portrait: figure against coloured flat background, swirling strokes on clothing and hair. Garden or garden wall: flowers, foliage, path, wall. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. Describe colour + type. Van Gogh renders fabric as bold colour with directional strokes following the garment's form. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Use Van Gogh settings: night sky, wheat fields, bedroom/interior, café at night, garden, portrait background. Choose emotional register: ecstatic / tender / anguished / melancholic. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Sky type: night swirl / day blue / storm / golden hour. Dominant palette: 3-4 specific Van Gogh colours. Stroke note for dominant element. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Vincent van Gogh Post-Impressionist oil painting style. Thick heavy impasto paint with bold directional brushstrokes as defining visual element — sky in swirling arcs and spirals, cypress trees in twisting flame-strokes upward, fields in parallel terrain-following strokes, figures in contour-following curved marks. Strong dark contour outlines around major forms. Intensely saturated complementary colour contrasts: cobalt blue against ochre, chrome yellow against violet, viridian against sienna. Everything pulsing with inner energy and emotional intensity. No smooth blending — every stroke remains distinct. Single painting scene, no text, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: smooth blended gradients, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, flat digital illustration, muted desaturated palette, western comic style, impressionist soft dissolution, uniform unstroke texture' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"van_gogh_painting","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> VINCENT VAN GOGH STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Vincent van Gogh, Post-Impressionism. Thick impasto paint in bold swirling directional strokes. The brushwork itself IS the emotion — swirling sky, churning fields, twisting cypress trees. Intense saturated colour, exaggerated for emotional truth rather than observed reality. Everything pulses with inner life. Thick impasto with visible physical texture. Directional strokes: sky spirals and flows, ground follows contour, trees twist upward. Bold dark contour outlines around major forms. Colour intensity saturated and vivid. Everything in motion — even still objects vibrate. Palette: cadmium yellow, chrome yellow, cobalt blue, ultramarine, viridian, burnt sienna, ochre. Complementary contrasts: yellow-violet, blue-orange, green-red placed adjacent. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. Describe colour — Van Gogh renders clothing in bold expressive strokes. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Vincent van Gogh Post-Impressionist oil painting style. Thick impasto paint with bold swirling directional brushstrokes visible as physical texture. Strong dark contour outlines around major forms. Intensely saturated colours exaggerated for emotional expression. Sky in swirling arcs, trees in twisting flame-strokes, ground following terrain direction. Everything vibrating with inner energy. Complementary colour contrasts. Single painting, no text, no panels.' NEGATIVE (append verbatim): 'Avoid: smooth blended surfaces, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, flat illustration, muted desaturated palette, western comic style, Monet soft dissolution' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"van_gogh_painting","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Vincent van Gogh Post-Impressionist oil painting style. Thick heavy impasto paint with bold directional brushstrokes as defining visual element — sky in swirling arcs and spirals, cypress trees in twisting flame-strokes upward, fields in parallel terrain-following strokes, figures in contour-following curved marks. Strong dark contour outlines around major forms. Intensely saturated complementary colour contrasts: cobalt blue against ochre, chrome yellow against violet, viridian against sienna. Everything pulsing with inner energy and emotional intensity. No smooth blending — every stroke remains distinct. Single painting scene, no text, no panels. Avoid: smooth blended gradients, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, flat digital illustration, muted desaturated palette, western comic style, impressionist soft dissolution, uniform unstroke texture

Копировать [Image generation hint, STYLE: Post-Impressionist oil painting, thick impasto, swirling directional brushstrokes, intense saturated exaggerated colour, complementary contrasts, emotional vibrating surface, every stroke visible]

Serov

Русский импрессионистический портрет. Свежий свет из окна, психологическое присутствие. Валентин Серов — светящаяся кожа, сдержанная палитра.

Экспериментальный Живопись

←→

Длинный~3768 Короткий~1607 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> VALENTIN SEROV STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Valentin Alexandrovich Serov (1865–1911). Russia's greatest portrait painter and one of the finest in European art. Student of Repin, friend of the Impressionists — Serov took the structural solidity of the Russian realist tradition and infused it with the freshness and spontaneity of Impressionism. His paintings feel caught at a specific moment, as if the sitter just sat down and the painter worked quickly before the light changed. His most famous work, Girl with Peaches (1887), painted when he was 22, defines the style: a young woman at a sunlit table, soft dappled light through windows, loose fresh paint, total psychological presence. It looks effortless. It is not. BRUSHWORK AND SURFACE Serov's brushwork is loose and confident but underpinned by superb draughtsmanship. He knew exactly where everything was before he painted it loosely over the top. Key surface qualities: - Fresh, spontaneous strokes — the painting appears to have been completed quickly, in one inspired session - No overworking or laborious blending — each stroke placed and left - Direction: brushwork loosely follows form without the rigidity of academic painting - Texture: visible but not as prominent as Van Gogh; the surface is alive but not thick LIGHT SYSTEM Serov's light is almost always NATURAL WINDOW LIGHT. This is his defining atmospheric choice. SOFT DIFFUSED WINDOW LIGHT (most common): Comes from one or more windows off to the side or in front of the figure. Light is even, generous, and slightly warm or cool depending on time of day. No hard cast shadows. Everything is visible and clear. The room feels inhabited and real. Morning light: cool blue-white, crisp, fresh, slightly silver Afternoon: warm ivory-gold, soft, the most beautiful and gentle Overcast: flat even grey-white, colours appear true and clear The shadow areas in Serov are not dark — they are simply the absence of the window light. Warm shadows in cool light, cool shadows in warm light. GARDEN / EXTERIOR: Softer, more Impressionist. Dappled light through foliage. Slightly more dissolved than the precise interior light. Warm summer afternoon. PALETTE SYSTEM Serov's palette is quiet, refined, and true. Not dramatic, not decorative. SKIN: warm ivory to soft peach in light. Cool grey-mauve in shadow. Never dark. The face glows from within. BACKGROUNDS: loosely painted. Light grey walls, cream, muted olive-green, warm tan. Suggested rather than described. A window frame, a table edge, a chair back — enough to locate the figure, not enough to compete. CLOTHING: reproduced accurately in colour but painted with economy. White or cream: rich and luminous. Dark colours: simplified, focusing on form not fabric detail. Occasional colour accent (red bow, blue scarf) placed carefully. SPECIFIC PALETTE: - Warm ivory + soft peach: skin in afternoon light - Dusty rose / muted rose: lips, warm accents - Soft grey-blue: cool shadows, window reflections - Warm ochre: table surfaces, wooden furniture - Muted green-grey: garden or wall background - Deep muted burgundy or navy: clothing anchoring the composition PSYCHOLOGICAL PRESENCE This is the quality that makes Serov different from photographic portraiture or idealised academic painting. His subjects are thinking something. They are not posed — they are present. Describe faces in terms of inner state, not just surface expression: - 'Slightly distracted, looking toward the window, something on her mind' - 'Quiet, settled, the particular stillness of someone at home in themselves' - 'Mid-thought, about to say something, lips not quite closed' - 'Looking directly at the painter with calm appraisal' - 'Slightly guarded warmth — open but not performing' The hands in Serov are also expressive. Often resting on a table, in lap, or loosely in front — not gestural, just present and specific. COMPOSITIONS TABLE WITH FIGURE: Serov's signature composition. Figure at or near a table. Objects on the table (bowl of fruit, cup, letter, flowers). Window light from the left or right. Figure slightly off-centre. PURE PORTRAIT: figure fills two-thirds of the frame. Loose background. Maximum focus on face and expression. GARDEN SCENE: figure in soft outdoor light. More Impressionist dissolution. Flowers or foliage in background. INTERIOR WITH MULTIPLE ELEMENTS: room with furniture, objects, window, figure as part of the environment rather than dominating it. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. Serov renders any clothing with painterly economy. Describe colour + type. The paint handles the fabric quality. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' Inner psychological state: specific, not generic. What are they thinking, not just how they look. 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Composition type: table scene / pure portrait / garden / interior environment. 1-2 grounding objects (bowl of fruit, cup, letter, flowers). 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Light type: morning / afternoon / overcast + window direction. Dominant tones: skin, background, clothing palette. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Valentin Serov Russian Impressionist portrait oil painting style. Loose, fresh, confident, spontaneous brushwork — alive and unhurried, not overworked or blended smooth. Soft diffused natural window light filling the scene from one side. Psychologically present and specific face as the emotional centre. Impressionistic background and setting with loosely indicated furniture and space. Warm ivory skin tones with cool-grey shadow. Refined quiet palette: dusty rose, soft grey-blue, warm ochre, muted green-grey, cream. Single oil painting scene, no text, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: theatrical chiaroscuro, dramatic rim lighting, dark backgrounds, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, flat digital illustration, harsh shadows, western comic style, overblended smooth surfaces, bright saturated palette' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"serov_portrait_painting","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> VALENTIN SEROV STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Valentin Serov (1865-1911), Russian Impressionist portrait painter. Loose, fresh, spontaneous brushwork with underlying structural solidity. Where Monet dissolves everything into light, Serov keeps the person. Portraits feel caught in a real moment — the sitter is thinking something, about to move, present. Light fills the room from a window, warm and unforced. Paint applied with confidence but not overworked. The Serov signature: the painting was completed in one inspired sitting. Fresh, alive, never laboured. Loose fresh brushwork, confident and directional. Faces most carefully rendered — psychological presence is everything. Fabric and setting impressionistic. Palette: warm ivory skin tones, soft grey-blues, muted greens, warm ochre, dusty rose. Light almost always soft natural window light, diffused and gentle. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. Describe dominant colour + type. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Valentin Serov Russian Impressionist portrait painting style. Loose, fresh, confident brushwork — spontaneous and alive, not overworked. Soft natural window light filling the scene evenly. Psychologically present face as emotional focal point. Impressionistic background and setting. Warm ivory skin tones, soft grey-blue and ochre palette. Single oil painting scene, no text, no panels.' NEGATIVE (append verbatim): 'Avoid: dramatic chiaroscuro, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, flat digital illustration, dark gloomy palette, theatrical lighting, western comic style, overblended smooth surfaces' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"serov_portrait_painting","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Valentin Serov Russian Impressionist portrait oil painting style. Loose, fresh, confident, spontaneous brushwork — alive and unhurried, not overworked or blended smooth. Soft diffused natural window light filling the scene from one side. Psychologically present and specific face as the emotional centre. Impressionistic background and setting with loosely indicated furniture and space. Warm ivory skin tones with cool-grey shadow. Refined quiet palette: dusty rose, soft grey-blue, warm ochre, muted green-grey, cream. Single oil painting scene, no text, no panels. Avoid: theatrical chiaroscuro, dramatic rim lighting, dark backgrounds, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, flat digital illustration, harsh shadows, western comic style, overblended smooth surfaces, bright saturated palette

Копировать [Image generation hint, STYLE: Russian impressionist portrait, fresh window light, luminous natural skin, restrained warm palette with subtle warmth, psychological presence, visible painterly brushwork]

Rembrandt

Голландский Золотой Век, кьяроскуро. Одна тёплая лампа, глубокие тени. Фигуры проступают из тьмы в золотой свет. Лица несут вес целых жизней.

Стабильный Живопись

←→

Длинный~3538 Короткий~1666 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> REMBRANDT STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Rembrandt Harmenszoon van Rijn (1606-1669), Dutch Golden Age. The supreme master of psychological portraiture and chiaroscuro. No painter before or after has achieved what Rembrandt does with darkness and light — the way a face emerges from shadow carries the entire weight of a human life. His technique is a physical expression of spiritual and psychological depth. THE LIGHT Rembrandt's light is always a single warm source: a candle, a lamp, a torch, a small window in a dark room. It is intimate and specific — not the broad daylight of Monet or Serov, but a small flame in the dark. This light illuminates selectively. It falls on: - The face: one side lit, one side in shadow (the 'Rembrandt lighting' pattern: lit side shows full face, shadow side shows a small triangle of light on the cheek) - Hands: if visible and near the light - The nearest fold of clothing: a ridge of fabric catching the light - Occasionally: one small bright object (a glass, a letter, a jewel) Everything else recedes into warm darkness. The background is near-black. The floor, the walls, the distance — all swallowed. THE DARKNESS Rembrandt's shadows are not flat black. They are deep, warm, living darkness — rich brown, umber, deep sienna. The shadow areas are painted with thin transparent glazes, layer on layer, building depth. You feel that something exists in the darkness; you just can't see it. The transition from light to shadow is not harsh — it is a soft, natural falloff, but the range from lightest to darkest is extreme. PAINT SURFACE LIT AREAS: thick impasto — paint piled up in layers, physically textured. The lit cheekbone might have multiple layers of thick paint, the topmost layer warm ivory with tiny flicks of pure white highlight. SHADOW AREAS: thin glazes — the paint is almost transparent here. Deep brown, umber, warm black applied thinly, showing underlying paint layers through it. THE FACE: maximum attention and paint. The eyes are the soul of a Rembrandt portrait. A slight wetness in the corner, a catchlight in the iris, a shadow under the brow. The face has been alive for decades. PALETTE LIGHT ZONE: - Warm ivory: the primary lit skin tone - Warm yellow-gold: the highlight on the forehead, nose, cheekbone - Pure white: the brightest catchlight (eyes, jewellery, one bright object) SHADOW ZONE: - Warm sienna: the shadow on skin, slightly warm - Deep umber: deeper shadow on clothing, background near figure - Near-black (warm): the deepest background CLOTHING: Rembrandt often painted dark rich clothing — black, deep brown, dark green — because it allowed him to paint light catching on raised fabric folds. Occasional rich red, deep burgundy, or deep blue as accent. THE REMBRANDT LIGHTING PATTERN Classic placement: light source to the upper-left of the figure. Results in: - Left side of face: lit in warm ivory-gold - Right side of face: in shadow, but with a small triangle of light on the right cheekbone - Nose casts a small shadow toward the right - Eyes: the lit eye catches light; the shadow eye is deep but visible This can be mirrored (light from right). Both versions are valid. PSYCHOLOGICAL DEPTH Rembrandt's subjects have inner lives. They are not displaying emotions — they are experiencing them privately, and we are witnessing. Faces to describe: - 'The look of someone who has accepted something they cannot change' - 'Eyes that have seen enough to be both sad and kind' - 'The specific stillness of someone holding grief intact' - 'Caught in a moment of prayer or internal reckoning' - 'Tired, but not defeated — something still in the eyes' HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium close-up, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Rembrandt renders clothing as a landscape of shadow and selective highlight. Describe: garment type + dominant colour (works best with dark fabrics). If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe through action, not static limb coordinates. Psychological inner state: specific, layered — not just emotion, the thought behind it. HANDS: visible and near light (gripping object, folded, at rest) or kept in shadow. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: dark interior, candle-lit, near darkness. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight (a glass, a letter, a jewel). 6. LIGHTING & LENS CHARACTER: light source position (upper-left / upper-right / left / right) + type (candle / lamp / small window). Clothing note — dark fabric for shadow/highlight play, or one light element (white collar). MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Traditional oil painting on canvas — Rembrandt van Rijn Dutch Golden Age style. NOT digital illustration, NOT comic book, NOT graphic novel. Thick visible oil paint texture with impasto brushwork in lit areas. Extreme chiaroscuro: 80 percent of the image in deep warm shadow, single warm intimate light source — candle or lamp. Warm ivory-gold skin in light, thick bright catchlights. Thin transparent warm-brown glazes in shadow. Near-black warm background — no bright or colourful backgrounds. The Rembrandt light triangle: one cheek lit, other in shadow with small reflected light. Entirely warm palette — no cool tones, no teal, no blue, no cyan. Anatomically correct hands. No text, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: digital illustration, comic book style, graphic novel, bold outlines, flat colour fills, saturated vivid cartoon colours, teal or cyan or bright blue backgrounds, bright even lighting, cool colour palette, blue or grey shadows, photorealistic photography, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, Impressionist soft dissolution, multiple light sources, cheerful light-filled backgrounds' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"rembrandt_oil_painting","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> REMBRANDT STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Rembrandt van Rijn, Dutch Golden Age oil painting. The master of chiaroscuro — deep shadow and selective golden light. Figures emerge from near-darkness into warm lamplight. Everything not directly lit recedes into rich warm brown shadow. Paint surface is thick and jewelled where lit, thin and dark where shadowed. Faces carry the weight of entire lifetimes. Extreme contrast between lit and shadowed areas. Single warm lamp or candle as light source. Lit areas: thick impasto, warm ivory-gold, jewelled highlights. Shadow areas: deep warm brown, almost black, thin paint. The Rembrandt Light: single warm source illuminates one side of the face, other half falls into deep warm shadow. Palette: near-black, deep warm brown, rich sienna, warm ivory, golden yellow highlights. Almost no cool tones. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. Describe dominant colour — Rembrandt renders dark fabrics with selective golden highlights on folds. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Traditional oil painting on canvas — Rembrandt van Rijn Dutch Golden Age style. NOT digital illustration, NOT comic book, NOT graphic novel. Thick visible oil paint texture with impasto brushwork in lit areas. Extreme chiaroscuro: 80 percent of image in deep warm shadow, single warm intimate light source. Warm ivory-gold skin in light. Near-black warm background — no bright or colourful backgrounds. Entirely warm palette — no cool tones, no teal, no blue, no cyan. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: digital illustration, comic book style, graphic novel, bold outlines, flat colour fills, saturated vivid cartoon colours, teal or cyan backgrounds, bright even lighting, cool colour palette, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, multiple light sources' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"rembrandt_oil_painting","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Traditional oil painting on canvas — Rembrandt van Rijn Dutch Golden Age style. NOT digital illustration, NOT comic book, NOT graphic novel. Thick visible oil paint texture with impasto brushwork in lit areas. Extreme chiaroscuro: 80 percent of the image in deep warm shadow, single warm intimate light source — candle or lamp. Warm ivory-gold skin in light, thick bright catchlights. Thin transparent warm-brown glazes in shadow. Near-black warm background — no bright or colourful backgrounds. The Rembrandt light triangle: one cheek lit, other in shadow with small reflected light. Entirely warm palette — no cool tones, no teal, no blue, no cyan. Anatomically correct hands. No text, no panels. Avoid: digital illustration, comic book style, graphic novel, bold outlines, flat colour fills, saturated vivid cartoon colours, teal or cyan or bright blue backgrounds, bright even lighting, cool colour palette, blue or grey shadows, photorealistic photography, 3D CGI, anime style, manga panels, speech bubbles, text in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, Impressionist soft dissolution, multiple light sources, cheerful light-filled backgrounds

Копировать [Image generation hint, STYLE: Dutch Golden Age chiaroscuro oil painting, single warm lamp light, deep warm shadows, golden figures emerging from near-darkness, thick impasto highlights, thin shadow glazes]

Repin

Русская реалистическая масляная живопись. Традиция Ильи Репина — психологическая глубина, вес человеческого существования. Каждое лицо рассказывает историю.

Стабильный Живопись

←→

Длинный~3697 Короткий~1601 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> ILYA REPIN STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Ilya Yefimovich Repin (1844-1930) — greatest Russian realist painter. Academic oil painting tradition with loose, confident, masterful brushwork. Single painted scene, no panels, no text. Figures rendered with full anatomical weight and complexity. Faces carrying layered, ambiguous, deeply human psychology — Repin never painted simple emotions, always the moment AFTER or DURING a complex inner event. This is the opposite of decorative. This style is about truth. BRUSHWORK AND TEXTURE Repin's painting technique: confident, loose, expressive but fundamentally disciplined. Not impressionist soft dissolve — the forms are THERE, but the paint acknowledges itself. - Loaded brushstrokes visible in clothing and background - Face and hands: slightly tighter detail than clothing - Hair: loose gestural strokes following direction of growth - Background: dark, painterly, loosely indicated — never competing with figures - Fabric: heavy, real, with weight. Paint follows the drape direction. Creases rendered with loaded strokes. - Skin: layered — warm base, cool shadow, bright highlight from light source. Not smooth — textured. LIGHTING SYSTEM Repin's lighting is always naturalistic and specific. There is always ONE primary light source that the viewer can identify. WINDOW LIGHT (most common interior): Warm or cool depending on time (afternoon = warm amber, morning = cool blue-white). Falls from one specific side. Creates strong clear shadow on the opposite face side. OUTDOOR DIFFUSED (overcast): No cast shadows. Flat, even, slightly cool grey light. Colours appear as they truly are without warmth boost. Melancholy in still subjects. OUTDOOR DIRECT (sunny): Strong directional light. Short dark shadows. Bright highlights. High contrast between lit and shadowed surfaces. CANDLELIGHT / LAMP (intimate interior): Warm amber-orange glow from point source. Sharp falloff — close subjects bright, far subjects dark. Dramatic upward or side light on face. FIRELIGHT: Reddish-orange from below-left or below. Warmth, communal scenes, but also danger and fever. Dramatic theatrical effect. PALETTE SYSTEM Repin's palettes are warm-dominated but never saccharine: SKIN TONES (build in layers): - Base: warm ochre-yellow - Shadow: deep burnt sienna or raw umber — warm dark, not grey or blue - Half-tone: warm rose or salmon - Highlight: near-white with warm tint at brightest point CLOTHING: Heavy fabrics in deep values — dark green, burgundy, charcoal, navy, black. Light fabrics: creamy white, grey-white with warm or cool shadows. Always paint the weight. BACKGROUND: Interior: warm dark brown-amber, barely indicated walls. Exterior: landscape loosely painted, sky as atmospheric mass. MOOD PALETTES: - Tension / confrontation: high contrast, warm-cool opposition, strong shadows, little background detail - Grief / devastation: muted palette, cooler tones, softer transitions, figure small or collapsed - Quiet intimacy: warm window light, close value range, soft focus on background - Public drama / group: broader palette, more background information, multiple light zones - Determination / portrait: direct gaze, clear light, strong jaw, tight framing PSYCHOLOGICAL PORTRAITURE Repin's faces carry: - The thought BEHIND the expression — not just the emotion, the specific thought - Ambiguity — is this grief or rage? Relief or exhaustion? - Time — the face has been doing something for a while; this is not a first moment - Dignity — even in pain, even in defeat, Repin's subjects have full humanity When describing character expression, go beyond the surface: NOT: 'sad expression' YES: 'eyes lowered, jaw set, the particular stillness of someone who has decided not to speak' COMPOSITION TYPES SINGLE FIGURE PORTRAIT: Close or medium. Figure occupies 60-70% of frame. Background dark and loosely painted. Face: the emotional centre. TWO-FIGURE CONFRONTATION: Both figures visible. Space between them loaded with tension. Light on both faces. GROUP SCENE: Multiple figures at different depths. Strong light source illuminates foreground, background figures recede. FIGURE IN ENVIRONMENT: Figure does not dominate the frame — they inhabit it. The environment has weight and presence. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos, scars, piercings) — rendered with full physical reality, not decorative. Mention hair only if scene-altered — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Repin-specific outfit description: fabric weight + texture + color + condition + how it falls. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe through action, not static limb coordinates. FACE: specific psychological description, not just emotion. HANDS: what they're doing (Repin's hands are as expressive as faces). Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Interior or exterior, specific setting, how much of it is visible. Include one meaningful object carrying emotional weight. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Light source type + position (left window, overhead outdoor, lamp below, etc.). Palette note — warm/cool balance, any dominant accent color. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Ilya Repin 19th century Russian academic realist oil painting. Loose confident masterful brushwork with visible loaded paint strokes in clothing and background. Tight detail on face and hands, looser gestural rendering of fabric drape and hair. Figures with full anatomical weight and physical presence. Layered naturalistic skin tones in warm ochre and sienna with deep warm shadow. Heavy fabric rendering with real weight and drape. Natural single-source lighting — window, outdoor, or lamp. Dark warm painterly background. Psychologically complex face rendering — layered, ambiguous, fully human. Single painted scene, no panels, no text overlays. Academic portrait or narrative painting format.' 8. NEGATIVE (append verbatim): 'Avoid: anime style, manga panels, speech bubbles, cartoon rendering, flat illustration, 3D CGI, photographic realism, idealized perfect proportions, Art Nouveau decorative style, fantasy elements, text overlays, halftone, western comic style, uniform thin lineart, impressionist colour dissolution, overly smooth airbrush skin, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"repin_oil_painting","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> ILYA REPIN STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Ilya Repin 19th century Russian realist oil painting. Single-image painted scene — no panels. Masterful academic realism: figures with full anatomical weight, fabric with real texture and drape, faces carrying complex layered psychology. Loose confident brushwork. Natural light from a definite source. The painting looks lived-in and heavy with human feeling. Repin's signature: psychological portraiture above all else. The face tells the whole story. The body confirms it. The environment witnesses it. Warm earthy tones as base with cool shadow areas. Skin in ochre, sienna, warm cream. Clothing in deep reds, dark greens, black, grey, dull golds. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. Describe fabric weight — Repin renders fabric with full material reality ('heavy wool coat, dark grey, collar turned up'). POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Ilya Repin 19th century Russian realist oil painting style. Academic realism with loose confident brushwork and visible paint texture. Figures with full anatomical weight and psychological presence. Natural lighting from definite source — window, outdoor, or lamp. Warm earthy skin tones (ochre, sienna) with deep shadow. Heavy fabric rendering with real drape and texture. Dark warm background. Single painted scene, no panels, no text overlays. Vertical or horizontal format.' NEGATIVE (append verbatim): 'Avoid: anime style, manga panels, speech bubbles, cartoon style, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, flat illustration, 3D CGI, idealized perfect proportions, fantasy elements, text overlays, halftone, western comic style, Art Nouveau decorative style' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"repin_oil_painting","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Ilya Repin 19th century Russian academic realist oil painting. Loose confident masterful brushwork with visible loaded paint strokes in clothing and background. Tight detail on face and hands, looser gestural rendering of fabric drape and hair. Figures with full anatomical weight and physical presence. Layered naturalistic skin tones in warm ochre and sienna with deep warm shadow. Heavy fabric rendering with real weight and drape. Natural single-source lighting — window, outdoor, or lamp. Dark warm painterly background. Psychologically complex face rendering — layered, ambiguous, fully human. Single painted scene, no panels, no text overlays. Academic portrait or narrative painting format. Avoid: anime style, manga panels, speech bubbles, cartoon rendering, flat illustration, 3D CGI, photographic realism, idealized perfect proportions, Art Nouveau decorative style, fantasy elements, text overlays, halftone, western comic style, uniform thin lineart, impressionist colour dissolution, overly smooth airbrush skin, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy

Копировать [Image generation hint, STYLE: Russian realist oil painting, psychological depth, rich earthy palette, dramatic natural lighting, weighty human presence, detailed expressive figures and faces]

Klimt

Венский сецессион, золотая живопись. Реалистичные лица и руки — всё остальное растворяется в плоских орнаментальных узорах. Золото, мозаика, спирали.

Стабильный Живопись

←→

Длинный~3436 Короткий~1618 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> GUSTAV KLIMT STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Gustav Klimt / Vienna Secession oil painting with gold leaf technique. Single-scene illustration — no panels, no text overlays. The defining visual logic of Klimt: two radically different textures exist in the same image simultaneously — and that contrast IS the art. TEXTURE DUALITY (the fundamental rule): - Human skin (face, neck, hands, bare arms/shoulders): rendered with full soft luminous realism. Warm undertones, subtle blush, detailed eyes, careful mouth. The most alive and tender part of the image. - Everything else (clothing, hair, background, surrounding space): completely dissolves into flat ornamental pattern. No realistic rendering of fabric or environment. Pure pattern, gold, mosaic, symbol. The figure doesn't stand in front of a background. The figure EMERGES from the pattern. The boundary between person and world is dissolved by gold. GOLD SYSTEM Gold is the atmosphere of the painting. It is not an accent — it IS the world. Gold appears as: - Warm metallic leaf texture covering most of the background - Gold outlines on pattern shapes - Gold as the base color of garment areas before patterns overlay it - Circular or oval gold halo suggestion behind head (Byzantine influence) - Gold flecks scattered in darker pattern areas Real skin (NOT gold): face, neck, visible collarbone, hands, any deliberately bare skin area. These must be warm, soft, and detailed — they are the emotional focal point. PATTERN VOCABULARY Mix 3-4 motifs per image. Place them thoughtfully — garment patterns differ from background patterns: SPIRALS — Klimt's most iconic. Fluid swirling vortex curves, varying scale. Use on garment bodies and background. BYZANTINE MOSAIC TILES — small square or rectangular color tiles arranged in grids within gold fields. Colors: deep teal, cobalt, crimson, black, ivory. EYE SHAPES — almond or oval shapes with iris detail embedded in pattern fields. Watching. Use sparingly as accent motif. RECTANGULAR BLOCKS — stacked columns of flat color rectangles (black, white, grey, red). More geometric, masculine energy. FEATHER / SCALE PATTERNS — overlapping curved shapes suggesting plumage or fish scales. Flowing, soft. FLORAL ROSETTES — simple flat flower shapes in gold or jewel tones, scattered through pattern. TRIANGLE CLUSTERS — small triangles packed together in bands. Used for border transitions between pattern zones. MEANDERING LINES — thin repeated curved or angular lines filling space between larger motifs. COMPOSITION TYPES SINGLE FIGURE: Central upright figure. Face as emotional focal point. Body surrounded/consumed by pattern. Background: flat gold field with pattern overlay. TWO FIGURES (THE KISS COMPOSITION): Figures merged into one shared pattern mass — only their faces emerge clearly. The shared garment/shroud wraps both in one ornamental field. FIGURES AND SPACE: Two figures separated by gold space. Distance rendered through pattern density. PORTRAIT CLOSE-UP: Face and shoulders only. Background: pure gold with minimal pattern. Maximum focus on skin detail. MOOD → PALETTE Build from gold base upward: - Intimate / tender: gold + warm ivory + deep black + blush rose + soft teal accents - Sorrowful / lonely: gold + grey-blue + silver + muted mauve + sparse pattern - Powerful / regal: gold + deep crimson + emerald + black + dense mosaic - Mystical / dreamlike: gold + deep violet + midnight blue + pale silver + eye motifs - Erotic / charged: gold + black + deep red + bare skin emphasis + tightly wound spirals - Joyful / alive: gold + bright azure + warm coral + scattered rosettes HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos, scars, piercings) — rendered as deliberate pattern elements integrated into the ornamental field. Mention hair only if scene-altered — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. In Klimt style, outfit becomes ornamental pattern mass — describe only: garment type, dominant color before gold overlay, structured vs. flowing silhouette. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: composition type (single / The Kiss merge / separated / portrait close-up). Pattern motifs — 3-4 specific motifs, where they appear (garment vs. background). Gold treatment — background density, halo suggestion, gold weight. Include one meaningful object carrying emotional weight. 6. LIGHTING & LENS CHARACTER: key light direction + color temp. Skin emphasis — what skin is visible and what emotion it carries (hands, face, shoulders). MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Gustav Klimt Vienna Secession painting style with gold leaf technique. Luminous semi-realistic warm skin rendering on faces, necks, hands, and bare skin only. All garments, hair, and background fully dissolved into flat ornamental gold-leaf pattern fields: interlocking spirals, Byzantine mosaic color tiles, eye motifs, rectangular color blocks, feather and scale patterns, floral rosettes, triangle bands, meandering fill lines. Rich warm metallic gold as dominant atmosphere and background. Jewel tone color accents within pattern. Circular gold halo suggestion behind figure head. Vertical portrait format 2:3. Single illustrated scene, no panels, no text overlays.' 8. NEGATIVE (append verbatim): 'Avoid: photorealistic photograph, 3D CGI, anime style, manga panels, speech bubbles, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, plain unpatterned background, realistically rendered clothing fabric, dark gritty realism, text overlays, halftone, flat modern vector illustration, western comic style' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"klimt_art_nouveau","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> GUSTAV KLIMT STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Gustav Klimt / Vienna Secession oil and gold leaf painting style. Figures rendered with luminous semi-realistic faces and hands — soft, warm, detailed skin. Everything else — clothing, background, surrounding space — dissolves into flat ornamental pattern fields of gold, mosaic tiles, spirals, geometric shapes, and decorative motifs. Only the face and hands remain fully real. The Klimt signature: human skin rendered with tenderness, everything else a flat golden tapestry. Gold leaf as dominant background texture. Real skin only on face, neck, hands, bare shoulders. Pattern vocabulary: spirals, Byzantine mosaic grids, eye shapes, rectangular blocks, feather/scale patterns, floral rosettes, black geometric shapes against gold. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. In Klimt style, outfit becomes ornamental pattern — describe dominant color and whether it flows or is structured. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Gustav Klimt Vienna Secession painting style. Luminous semi-realistic rendering of faces, necks, and hands with warm soft skin tones. All clothing, background, and surrounding space rendered as flat ornamental gold-leaf pattern fields: spirals, mosaic tiles, geometric blocks, eye shapes, feather patterns, floral rosettes. Rich gold metallic background. Jewel tone accent colors. Byzantine mosaic influences. Vertical portrait format. Single illustrated scene, no panels, no text overlays.' NEGATIVE (append verbatim): 'Avoid: photorealistic photograph, 3D CGI, anime style, manga panels, speech bubbles, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, plain unpatterned background, flat modern illustration, dark gritty realism, text overlays, halftone' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"klimt_art_nouveau","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Gustav Klimt Vienna Secession painting style with gold leaf technique. Luminous semi-realistic warm skin rendering on faces, necks, hands, and bare skin only. All garments, hair, and background fully dissolved into flat ornamental gold-leaf pattern fields: interlocking spirals, Byzantine mosaic color tiles, eye motifs, rectangular color blocks, feather and scale patterns, floral rosettes, triangle bands, meandering fill lines. Rich warm metallic gold as dominant atmosphere and background. Jewel tone color accents within pattern. Circular gold halo suggestion behind figure head. Vertical portrait format 2:3. Single illustrated scene, no panels, no text overlays. Avoid: photorealistic photograph, 3D CGI, anime style, manga panels, speech bubbles, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, plain unpatterned background, realistically rendered clothing fabric, dark gritty realism, text overlays, halftone, flat modern vector illustration, western comic style

Копировать [Image generation hint, STYLE: Vienna Secession gold leaf painting, luminous semi-realistic faces and hands against flat ornamental pattern fields, gold mosaic tiles, spirals and geometric motifs, decorative pattern dissolving the body]

Dark Fantasy

Цифровая масляная живопись, качество обложки фэнтези-романа. Богатая текстура, видимые мазки, глубокие тени, атмосферное освещение. Энергия обложек Сандерсона и ACOTAR.

Стабильный Иллюстрация

←→

Длинный~3677 Короткий~1475 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> DARK FANTASY BOOK COVER ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Digital oil painting in the style of a prestige dark fantasy / dark romance novel cover. Single-image composition — no panels, no speech bubbles, no SFX. Pure painterly illustration. The roleplay text carries the narrative; the image is the visual peak of the scene. Rendering approach: layered digital oil painting. Visible brushwork with directional strokes. Deep rich shadows with selective atmospheric light sources. High contrast between light and dark zones — chiaroscuro. Saturated jewel tones within shadow areas, bright focal points drawing the eye. Environmental detail in middle ground, background stays painterly and impressionistic. Reference aesthetics: Brandon Sanderson / ACOTAR / Priory of the Orange Tree cover art. Charlie Bowater, Magali Villeneuve, artist styles. COMPOSITION PRINCIPLES Rule of thirds: place figure at intersection point, not dead center. Eye path: light source → character face → key object → environment. Negative space: dark/empty areas carry as much weight as the subject. Foreground depth: silhouetted plants, architectural elements, or objects in blur to create layers. Background: impressionistic painted detail — readable mood, not photographic precision. LIGHTING SYSTEM — choose one, describe source position: CANDLELIGHT / TORCH Warm amber-orange from below or side. Dancing soft shadows. Intimate. Vulnerable. The face partially lit, partially in deep shadow. Highlights catch on fabric texture and jewelry. MOONLIGHT Cold silver-blue from directly above or upper-left. Long deep shadows. Ethereal. Isolated. Skin rendered in cool undertones, hair catching silver highlights. Background sky deep navy or storm purple. STORM LIGHT Dramatic white-grey from behind clouds, side-lit. High contrast. Dynamic. Sense of danger or imminent action. Environment feels alive and threatening. EMBER / DYING FIRE GLOW Deep orange-red from below and off-screen. Fading warmth. End-of-something atmosphere. Ash particles in the air. Charcoal blacks in shadow. NEON / MODERN DARK FANTASY Cool blue from environmental light + magenta or violet rim light. Contemporary dark romance aesthetic. Rain-slicked surfaces reflecting colored light. Cinematic. MAGIC LIGHT Character-emitted glow — unnatural, sourceless. Gold: divine/ancient. Violet: corrupted/mysterious. Pale blue: cold power. The glow defines the figure against complete darkness. DAWN / THRESHOLD Grey-pink light from low horizon behind figure, silhouetting edges. Liminal. Between states. Exhaustion and release. PALETTE SYSTEM Always build from dark base up: - Danger / power: charcoal foundation, deep crimson accents, gold edge catch-lights, black shadow - Grief / loneliness: midnight blue base, cold silver light, muted violet mid-tones, pale cool highlights - Mystery / intrigue: deep teal and dark violet mid-tones, black shadow, pale gold focal glow - Dark romance / tension: deep burgundy and dark rose, candlelight amber, ivory skin contrast, shadow-saturated background - Rage: blood red, soot black, burning orange, no softness - Hope within darkness: dominant dark palette but ONE warm light source — a window, a candle, a crack in the sky COLOR TEMPERATURE CONTRAST: always have one warm zone and one cool zone in the image. The eye moves between them. ENVIRONMENT TYPES Interior: - Candlelit stone chamber: rough-cut stone walls, pooled wax, iron sconces - Library / archive: towering dark shelves, scattered papers, single lamp - Grand hall in ruin: cracked marble, cold moonlight through broken windows - Modern apartment at night: city glow through rain-streaked windows, one lamp Exterior: - Rain-soaked rooftop: city lights blurred below, storm clouds, wet concrete - Dark forest clearing: twisted bare branches, diffused moonlight through canopy - Cliffside / coastal: wind, spray, vast dark sea below - City alley at night: neon reflections in puddles, fog, distant sounds - Ancient ruins: crumbling arches, overgrown, starlight above ATMOSPHERIC ELEMENTS — add 1-2 per scene: Rain (light mist / heavy downpour / post-rain wet surfaces) Smoke or incense (curling upward, diffusing light) Falling ash or embers (from off-screen fire, symbolic decay) Mist / fog (distance, mystery, liminal states) Snow (quiet, isolation, suspension of time) Floating particles (dust in shaft of light, magic debris) Wind-moved fabric (cloak, hair, curtain — implies force, freedom) HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. Dark fantasy renders ANY outfit — jeans, hoodies, suits — with weight and drama. No outfit is too modern for this style. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Dark fantasy digital oil painting, prestige novel cover illustration style. Rich layered painterly texture with visible directional brushwork and deep glazing. Chiaroscuro lighting — high contrast between light and shadow. Cinematic composition with rule of thirds placement. Jewel-toned saturated palette within shadow areas, bright selective focal highlights. Environmental mid-ground detail, impressionistic background. Detailed fabric texture and material rendering. Atmospheric particle and weather elements. Single-image cinematic scene, no text overlays, no panels. Vertical portrait format 2:3.' 8. NEGATIVE (append verbatim): 'Avoid: photorealistic photograph, 3D CGI render, flat digital illustration, anime style, manga panels, speech bubbles, SFX text, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, overly bright or cheerful palette, cartoonish proportions, halftone, western comic style, clean vector lines, text overlays, modern graphic design layout' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"dark_fantasy_painting","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> DARK FANTASY BOOK COVER ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Digital oil painting in the style of a prestige dark fantasy novel cover. Single-image composition — no panels, no speech bubbles. Rich painterly texture, visible brushwork, deep shadows, atmospheric lighting. One cinematic moment: character(s) against a dramatic environment. Mood is everything. Think: Brandon Sanderson cover art, ACOTAR, The Priory of the Orange Tree. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Dark fantasy digital oil painting, novel cover illustration style. Rich painterly texture with visible brushwork and layered glazing. Deep dramatic shadows with selective atmospheric lighting. Cinematic composition, rule of thirds. Moody saturated palette. Environmental storytelling through light and atmosphere. Detailed fabric and material rendering. Single-image scene, no panels, no text overlays. Vertical portrait format 2:3.' NEGATIVE (append verbatim): 'Avoid: photorealistic photograph, 3D CGI render, flat illustration, anime style, manga panels, speech bubbles, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, overly bright cheerful palette, cartoonish proportions, halftone, western comic style, text overlays' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"dark_fantasy_painting","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Dark fantasy digital oil painting, prestige novel cover illustration style. Rich layered painterly texture with visible directional brushwork and deep glazing. Chiaroscuro lighting — high contrast between light and shadow. Cinematic composition with rule of thirds placement. Jewel-toned saturated palette within shadow areas, bright selective focal highlights. Environmental mid-ground detail, impressionistic background. Detailed fabric texture and material rendering. Atmospheric particle and weather elements. Single-image cinematic scene, no text overlays, no panels. Vertical portrait format 2:3. Avoid: photorealistic photograph, 3D CGI render, flat digital illustration, anime style, manga panels, speech bubbles, SFX text, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, overly bright or cheerful palette, cartoonish proportions, halftone, western comic style, clean vector lines, text overlays, modern graphic design layout

Копировать [Image generation hint, STYLE: digital oil painting prestige novel cover quality, rich painterly texture, visible brushwork, deep dramatic shadows, atmospheric fantasy lighting, moody saturated palette]

Classic Fantasy

Larry Elmore, Keith Parkinson, обложки книг D&D эпохи TSR (1980-90е). Масло на холсте, тёплая насыщенная палитра, героический свет. Романтическое фэнтези — красиво даже в опасности.

Стабильный Иллюстрация

←→

Длинный~2999 Короткий~1824 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — CLASSIC FANTASY ILLUSTRATION — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'windblown') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Specificity over generics: fabric type + texture + fit + color + drape + condition. Not 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition, visible limb positions and weight distribution. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Classic fantasy oil painting illustration style — Larry Elmore, Keith Parkinson, Clyde Caldwell, Jeff Easley, TSR Dungeons and Dragons book cover era tradition (1980s-1990s). Rich detailed oil paint on canvas with visible confident brushwork — polished high detail on faces, hands, and focal objects, broader atmospheric painterly strokes on backgrounds and environments. Warm lush saturated palette: golden ambers, deep forest greens, royal blues, firelight oranges, burgundy, rich warm brown shadows — never cold grey. Dramatic but flattering heroic lighting: characters look beautiful and heroic even in danger, light is generous and warm. Romantic fantasy atmosphere: inviting, saturated, idealized. Oil-on-canvas texture quality throughout. Detailed material rendering: gleaming polished metal, rich coloured fabric, weathered supple leather, carved wood. Anatomically correct hands and proportions. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: cold desaturated palette, grimdark washed-out atmosphere, grey lifeless shadows, flat digital illustration, smooth untextured surfaces, modern minimalist concept art, anime style, cel shading, cartoon features, 3D CGI render, photorealistic photography, manga panels, speech bubbles, text in image, watermark, exaggerated expressions, uncanny valley, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"classic_fantasy_oil","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"9:16","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> CLASSIC FANTASY ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Classic fantasy oil painting illustration — the tradition of Larry Elmore, Keith Parkinson, Clyde Caldwell, Jeff Easley, the TSR/D&D book cover era (1980s–1990s). Rich, detailed, painterly oil on canvas. Visible confident brushwork with high detail on faces and focal elements. Warm, romantic, heroic. The kind of painting that made you stare at a book cover for ten minutes before opening it. RENDERING: - Oil paint with visible brushwork: detailed and polished in focal areas (faces, hands, weapons, magical effects), broader and more atmospheric in backgrounds. Not smooth digital — PAINTED. - Rich colour: saturated warm golds, deep forest greens, royal blues, firelight oranges. The palette is lush and inviting — more saturated than reality, deliberately beautiful. - Warm overall tone: even dark scenes have warmth. The shadows are rich brown and deep blue, not cold grey. - Dramatic but heroic lighting: the light is generous and flattering, even in dangerous scenes. Characters look their best. This is ROMANTIC fantasy, not grimdark. PALETTE: - Warm golds and ambers for light and skin - Deep forest green, royal blue, burgundy for depth and richness - Firelight orange as warm accent - Rich brown shadows, not grey or black - Overall: LUSH. Saturated. Beautiful. Like stained glass lit from behind. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'windblown') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — warm directional source + colour temp + 1-2 mood effects (halation, golden warmth, chiaroscuro, bloom, Rembrandt lighting, faded blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Classic fantasy oil painting illustration style — Larry Elmore, Keith Parkinson, TSR book cover era tradition. Rich detailed oil paint with visible confident brushwork — polished detail on faces and hands, broader atmospheric strokes on backgrounds. Warm lush saturated palette: golden ambers, forest greens, royal blues, firelight oranges, rich brown shadows. Dramatic but flattering heroic lighting — characters look beautiful even in danger. Romantic fantasy atmosphere: warm, inviting, saturated. Oil-on-canvas texture quality. Detailed material rendering: gleaming metal, rich fabric, weathered leather. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: cold desaturated palette, grimdark atmosphere, grey shadows, flat digital illustration, smooth untextured surfaces, anime style, cel shading, 3D CGI, photorealistic photography, modern concept art flatness, manga panels, speech bubbles, text in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"classic_fantasy_oil","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Classic fantasy oil painting illustration style — Larry Elmore, Keith Parkinson, Clyde Caldwell, Jeff Easley, TSR Dungeons and Dragons book cover era tradition (1980s-1990s). Rich detailed oil paint on canvas with visible confident brushwork — polished high detail on faces, hands, and focal objects, broader atmospheric painterly strokes on backgrounds and environments. Warm lush saturated palette: golden ambers, deep forest greens, royal blues, firelight oranges, burgundy, rich warm brown shadows — never cold grey. Dramatic but flattering heroic lighting: characters look beautiful and heroic even in danger, light is generous and warm. Romantic fantasy atmosphere: inviting, saturated, idealized. Oil-on-canvas texture quality throughout. Detailed material rendering: gleaming polished metal, rich coloured fabric, weathered supple leather, carved wood. Anatomically correct hands and proportions. No text, no panels. Avoid: cold desaturated palette, grimdark washed-out atmosphere, grey lifeless shadows, flat digital illustration, smooth untextured surfaces, modern minimalist concept art, anime style, cel shading, cartoon features, 3D CGI render, photorealistic photography, manga panels, speech bubbles, text in image, watermark, exaggerated expressions, uncanny valley, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy

Копировать [Image generation hint, STYLE: 1980s-90s TSR D&D book cover art, oil on canvas, warm lush saturated palette, heroic flattering light, romantic fantasy illustration with gold, forest green, royal blue, firelight orange]

Horror Illustration

Традиция Bernie Wrightson, Brom. Масло с видимыми уверенными мазками. Экстремальное кьяроскуро — 70% картинки в тени. Единственный жёсткий источник света вырезает форму из тьмы.

Стабильный Иллюстрация

←→

Длинный~3137 Короткий~1889 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — CLASSIC HORROR ILLUSTRATION — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition (flushed, sweaty, bruised), visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Classic horror oil painting illustration style — Bernie Wrightson, Brom, Frank Frazetta dark tradition. Rich oil paint with visible confident directional brushstrokes following form — thick impasto texture on the brightest highlights, looser expressive strokes dissolving into darkness in shadow areas. Extreme chiaroscuro: deep pure black shadows occupying 70 percent of the image against selective bright warm highlights. Single harsh dramatic light source carving form from darkness — candle, lamp, moonlight, fire. Warm amber-ochre skin highlights against cold blue-black shadow. Detailed rendering in lit areas — faces, hands, meaningful objects — with brushwork loosening as surfaces recede into shadow. Gothic atmospheric intensity. Dark rich saturated palette in lit zones, near-monochrome darkness elsewhere. Anatomically correct hands and proportions. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: bright even lighting, flat digital illustration, smooth untextured surfaces, low contrast, lifted blacks, grey shadows, cheerful warm palette, pastel colours, anime style, cel shading, cartoon features, photorealistic photography, 3D CGI render, manga panels, speech bubbles, text in image, watermark, exaggerated expressions, uncanny valley, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"horror_oil_painting","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"9:16","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> CLASSIC HORROR ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Classic horror oil painting illustration — the tradition of Bernie Wrightson, Brom, Frank Frazetta's darker work, and gothic horror book cover art. Rich oil paint with VISIBLE confident brushstrokes. Extremely high contrast: deep pure blacks against selective bright highlights. The image lives mostly in darkness — light is rare, precious, and dramatic. RENDERING: - Visible oil paint brushwork: confident, directional, deliberate. Not smooth digital. Not sloppy. The brushstrokes have PURPOSE — following form on faces, slashing across dark backgrounds, building texture on surfaces. - Impasto highlights: the brightest points (skin catching light, candle flame, wet surface) have thick, almost raised-looking paint texture. - Deep tonal range: 70% of the image is in shadow or near-black. Light occupies small, precious areas. LIGHTING — EXTREME CHIAROSCURO: - Single harsh dramatic light source: candle below, lamp from side, moonlight through window, fire glow. - Deep pure blacks in shadow — not grey, not lifted. TRUE black. - Light carves form out of darkness — faces half-lit, bodies emerging from black. - Warm light (amber, orange) against cold darkness (blue-black, grey-black). PALETTE: - Dominant: deep black, warm amber, cold blue-black - Skin in light: warm ochre, pale cream, flushed rose - Accents: blood red, sickly green, cold moonlight blue — used sparingly - Overall: DARK. Rich. Saturated in the lit areas, near-monochrome in shadow. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — single dramatic source + direction + chiaroscuro depth + 1-2 mood effects (underexposure, harsh rim, deep vignette, deep blacks, low key, smoke in light beam — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Classic horror oil painting illustration style — Bernie Wrightson, Brom tradition. Rich oil paint with visible confident directional brushstrokes and impasto texture on highlights. Extreme chiaroscuro: deep pure black shadows against selective bright warm highlights. Single harsh dramatic light source carving form from darkness. 70 percent of image in shadow or near-black. Warm amber-ochre skin highlights against cold blue-black shadow. Detailed faces and hands in lit areas, loose expressive brushwork dissolving into darkness in shadow areas. Gothic atmospheric intensity. Dark rich saturated palette in lit areas, near-monochrome in shadow. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: bright even lighting, flat digital illustration, smooth untextured surfaces, anime style, cel shading, cartoon features, low contrast, lifted blacks, pastel palette, cheerful warm palette, photorealistic photography, 3D CGI, manga panels, speech bubbles, text in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"horror_oil_painting","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Classic horror oil painting illustration style — Bernie Wrightson, Brom, Frank Frazetta dark tradition. Rich oil paint with visible confident directional brushstrokes following form — thick impasto texture on the brightest highlights, looser expressive strokes dissolving into darkness in shadow areas. Extreme chiaroscuro: deep pure black shadows occupying 70 percent of the image against selective bright warm highlights. Single harsh dramatic light source carving form from darkness — candle, lamp, moonlight, fire. Warm amber-ochre skin highlights against cold blue-black shadow. Detailed rendering in lit areas — faces, hands, meaningful objects — with brushwork loosening as surfaces recede into shadow. Gothic atmospheric intensity. Dark rich saturated palette in lit zones, near-monochrome darkness elsewhere. Anatomically correct hands and proportions. No text, no panels. Avoid: bright even lighting, flat digital illustration, smooth untextured surfaces, low contrast, lifted blacks, grey shadows, cheerful warm palette, pastel colours, anime style, cel shading, cartoon features, photorealistic photography, 3D CGI render, manga panels, speech bubbles, text in image, watermark, exaggerated expressions, uncanny valley, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy

Копировать [Image generation hint, STYLE: Bernie Wrightson Brom tradition oil painting, extreme chiaroscuro with 70% of the image in shadow, impasto highlights, single harsh dramatic light source carving form from darkness, deep warm-brown shadows]

Art Nouveau (Mucha)

В духе Альфонса Мухи. Фигура в центре с ботанической орнаментальной рамкой из цветов и лоз. Пастельная палитра с золотыми акцентами. Волосы вплетаются в рамку.

Стабильный Иллюстрация

←→

Длинный~3386 Короткий~1582 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> ART NOUVEAU PORTRAIT ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Alphonse Mucha-inspired Art Nouveau digital illustration. Single-image composition — no panels, no speech bubbles, no SFX. The roleplay text carries the narrative; the image illustrates the peak emotional moment. Central figure as focal point. Surrounded by an elaborate ornamental living border: interwoven flowers, vines, leaves, seed pods, and botanical detail. Decorative circular halo or elongated arch behind and above the figure's head — the signature Mucha crown element. Flat decorative background with subtle color gradient or mosaic pattern. Lineart: thin, confident, precise. Line weight thicker on figure outline, finer on interior detail and border filigree. Soft diffused lighting — no hard cast shadows. Light comes from above or behind, creating a luminous, almost sacred atmosphere. PALETTE SYSTEM Base: pastel palette — ivory, cream, blush pink, sage green, dusty lavender, peach, champagne. Accents: always include gold leaf details, gilt filigree lines, gold halo ring. Silver as secondary accent for cooler scenes. Mood shifts: - Romance / tenderness: rose blush, cream, champagne gold, soft coral - Melancholy / longing: slate blue, dusty lavender, pewter silver, cool ivory - Tension / conflict: deep crimson, dark forest green, charcoal, black-gold - Joy / celebration: amber, sunflower yellow, warm ivory, rose gold - Mystery / night: deep teal, midnight blue, violet, pale gold - Grief / loss: grey-mauve, pale blue, bare silver, frost white BOTANICAL BORDER SYSTEM The frame is not decorative filler — it REFLECTS the emotional content of the scene. Choose plants deliberately: Romance / love: roses (red/pink), cherry blossoms, jasmine, sweet peas, lily Longing / distance: wisteria, forget-me-nots, dried lavender, morning glory Grief / loss: willow branches, bare thorns, fallen petals, black-eyed Susan Power / danger: nightshade, thorned rose canes, dark ivy, wolfsbane Hope / renewal: lily of the valley, snowdrops, young fern fronds, white doves Passion / desire: red poppies, deep burgundy roses, pomegranate with seeds Innocence / purity: white daisies, baby's breath, light moss, soft feathers Autumn / ending: maple leaves, dried seed heads, amber grasses, acorns Corner medallions (optional): small circular vignettes in the four corners of the border containing symbolic objects — a lit candle, an hourglass, a key, a bird in flight, a closed eye. FIGURE COMPOSITION Pose options for mood: - Standing full-length, frontal or three-quarter — elegance, confidence, presence - Seated with one arm extended — vulnerability, openness, longing - Turned three-quarter away, glancing back — secrets, hesitation, departure - Head bowed, hands folded — grief, submission, prayer - Arms raised / reaching upward — freedom, ecstasy, surrender - Profile facing left or right — purity, classical, distant Hair always merges into the border — strands flow out and intertwine with vines and flowers. This is the Mucha signature. Do not contain hair within the figure silhouette. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered — not the color or base style. Describe how hair merges into the border (cascading left, twisting with roses, spread behind like a halo). Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + drape + condition (flowing, torn, soaked, unbuttoned). If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. Art Nouveau suits: flowing robes, draped silk, corsets, soft linen — if modern outfit, it still renders elegantly in Mucha style. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: border plants — 3-4 specific plants + their placement (top arch, side columns, corner medallions). Background — flat gradient color, mosaic pattern, or specific texture. Include one symbolic object (held in hand, woven into border, lying at feet) carrying emotional weight. 6. LIGHTING & LENS CHARACTER: key light direction + color temp. Palette — dominant mood tone + gold/silver accent type. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Art Nouveau Alphonse Mucha style digital illustration. Ornate central portrait composition. Elaborate botanical border of interwoven flowers, vines, leaves, and seed pods surrounding the central figure. Decorative circular halo arch behind figure head with gilt filigree ring. Hair flowing organically into botanical frame. Corner medallion vignettes with symbolic objects. Thin precise confident lineart, thicker outline weight, fine interior detail lines. Gold leaf accents, gilt filigree throughout border. No hard cast shadows — soft diffused luminous lighting. Luminous warm skin tones with subtle blush. Large soft expressive eyes. Pastel palette with gold and silver accents. Flat decorative mosaic or gradient background. Highly detailed ornamental composition. Vertical portrait format 2:3.' 8. NEGATIVE (append verbatim): 'Avoid: photorealistic rendering, 3D CGI, harsh cast shadows, manga comic panels, speech bubbles, SFX text, anime chibi proportions, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, cluttered unreadable composition, dark gritty color grading, halftone dots, western comic style, text overlays, modern graphic design elements, flat vector illustration' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. Border plants serve both characters — use split symbolism if moods differ (roses on one side, thorns on other). CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"art_nouveau","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> ART NOUVEAU PORTRAIT ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Alphonse Mucha-inspired Art Nouveau digital illustration. Central figure as focal point, surrounded by an ornamental living border of flowers, vines, and foliage. Decorative circular halo or arch behind the figure's head. Thin confident lineart. Soft diffused lighting from above. Pastel palette — ivory, blush pink, sage green, dusty lavender — accented with gold leaf details and gilt filigree. No hard shadows. Luminous warm skin. Hair flowing organically into the botanical frame. Border plants reflect scene emotion: romance = roses, cherry blossoms; grief = willow, thorns, fallen petals; power = nightshade, thorned vines; hope = lily of the valley, morning glory; passion = red poppies, deep roses. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Art Nouveau Alphonse Mucha style digital illustration. Central portrait with ornamental botanical border of flowing vines, flowers, and foliage. Decorative circular halo arch behind figure. Thin confident lineart with gold leaf accents and gilt filigree. Soft diffused lighting, no hard shadows. Luminous warm skin. Large soft expressive eyes. Pastel palette with gold and silver accents. Hair flowing into botanical frame. Flat decorative gradient background. Highly detailed ornamental border. Vertical portrait format.' NEGATIVE (append verbatim): 'Avoid: photorealistic, 3D render, harsh shadows, anime chibi, manga panels, speech bubbles, SFX text, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, cluttered background, dark gritty palette, halftone, western comic style' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"art_nouveau","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Art Nouveau Alphonse Mucha style digital illustration. Ornate central portrait composition. Elaborate botanical border of interwoven flowers, vines, leaves, and seed pods surrounding the central figure. Decorative circular halo arch behind figure head with gilt filigree ring. Hair flowing organically into botanical frame. Corner medallion vignettes with symbolic objects. Thin precise confident lineart, thicker outline weight, fine interior detail lines. Gold leaf accents, gilt filigree throughout border. No hard cast shadows — soft diffused luminous lighting. Luminous warm skin tones with subtle blush. Large soft expressive eyes. Pastel palette with gold and silver accents. Flat decorative mosaic or gradient background. Highly detailed ornamental composition. Vertical portrait format 2:3. Avoid: photorealistic rendering, 3D CGI, harsh cast shadows, manga comic panels, speech bubbles, SFX text, anime chibi proportions, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, cluttered unreadable composition, dark gritty color grading, halftone dots, western comic style, text overlays, modern graphic design elements, flat vector illustration

Копировать [Image generation hint, STYLE: Alphonse Mucha inspired illustration, central figure framed by ornamental botanical border of flowers and vines, decorative halo arch, thin confident lineart, pastel palette with gold leaf accents]

Bilibin v3

Иван Билибин, русская сказочная иллюстрация — контур тушью + акварельная размывка. Атмосферная глубина, приглушённая палитра. Версия без рамки.

Экспериментальный Иллюстрация

←→

Длинный~4237 Короткий~1816 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> IVAN BILIBIN V3 STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Ivan Yakovlevich Bilibin (1876–1942). His illustrations for Russian folk tales defined the visual language of Slavic fairy tale art. The technique is not digital flat color — it is bold black ink outlines combined with translucent watercolor and gouache washes. The color has air in it. The background has depth. The image looks like it was hand-inked and hand-painted, then printed in a beloved illustrated book. NO BORDER. The illustration fills the frame completely edge to edge. No frame, no decorative strip, no line rule, no margin of any kind. THE CRITICAL DISTINCTION — WHY THE STYLE FAILS WHEN MISUNDERSTOOD: The common mistake: flat vector fills inside ink outlines = coloring book. The correct read: ink outlines + wash color with subtle tonal variation within each shape + atmospheric background depth = Bilibin. TECHNIQUE IN DETAIL INK OUTLINES: Bold, clean, confident. Uniform weight throughout — no variation for dramatic effect. Lines define form clearly and with decorative intent. Interior detail lines slightly finer but still clear and readable. WATERCOLOR/GOUACHE WASH: Each colored area is not one flat value. It has: - A lighter zone (toward the light source or open edge) - A mid tone (the dominant local color) - A slightly deeper shadow tone as a soft wash, not a hard edge The transitions are soft, not gradient — the wash dries with subtle variation. This is what distinguishes Bilibin from flat illustration. ATMOSPHERIC BACKGROUND DEPTH: This is the most important quality missing from failed Bilibin reproductions. In a Bilibin forest: - Foreground trees: full detail, deep color, strong ink outline - Mid-ground trees: slightly lighter, slightly less defined - Background trees: pale grey-green or blue-grey silhouettes, hazy - Sky or horizon glow visible between and behind tree trunks - Mist or atmosphere fills the distance In an open landscape: - Foreground: most detailed, richest color - Middle distance: lighter, simplified - Far distance: flat light tone, near-white, atmospheric haze - Sky: always present and luminous — even if small, it anchors the light This atmospheric recession is what gives Bilibin illustrations their sense of space and magic. Without it, the image is flat. PALETTE SYSTEM Bilibin's palette is muted and naturalistic. It is NOT jewel-toned or oversaturated. FOREST scenes: - Dominant: deep olive green, grey-green, cool muted teal - Birch: pale silver-white trunks, light green-gold foliage - Pine: dark cool green, almost grey-blue in shadow - Forest floor: warm sienna, grey-brown, soft moss green - Sky between trees: pale grey-blue, soft ivory, warm gold if dusk OPEN LANDSCAPE: - Grass: golden ochre-green, warm and dry - Sky: expansive, warm gold to pale blue, dramatic if stormy - Horizon: glowing pale ivory or amber where sky meets earth WATER: - Flat reflective surface, muted teal or grey-blue - Simple decorative wave-line pattern in ink - Sky color reflected with slight darker value SKIN TONES: - Warm ivory base wash, very light - Soft peach or rose for cheeks — a second light wash only - Shadows: warm grey-brown, softly applied - Never dark, never heavy COSTUME PALETTE: - White or cream base with folk embroidery in one or two accent colors - Deep blue sarafan (traditional dress) - Rich red, cobalt, or gold used sparingly on garments and armor - Gold: warm, muted — not metallic chrome, but painted gold FOLK ORNAMENT — PLACEMENT RULES Ornament appears ONLY on: - Garment borders (hem, sleeve cuff, collar): geometric embroidery pattern in 1-2 colors - Headdresses (kokoshnik): small repeated decorative shapes - Weapon, armor, or harness decoration - Carved wooden architecture (window frames, door frames, fence posts) Ornament does NOT appear on: - Sky, ground, grass, background fills, rocks, trees, water The world is naturalistic. Only human-made objects carry decoration. NO TEXT IN IMAGE: No title, no caption, no name, no label of any kind rendered inside the image. SCENE TYPES AND THEIR VISUAL LANGUAGE DEEP FOREST: Foreground birch or pine trunks as vertical framing elements. Figure(s) in middle ground. Background: atmospheric depth with light glow visible far between trunks. Floor: textured with ferns, roots, fallen leaves. Sky barely visible — glimpsed as pale light through canopy. OPEN LANDSCAPE WITH SKY: Wide horizontal composition. Figure(s) in foreground-right, landscape expansive to left and background. Sky takes up significant portion — luminous, with clouds or sun. Ground: detailed in foreground, simplified to wash in distance. FOREST CLEARING / MEETING: Two or more figures in a clearing. Trees frame left and right. Sky or water visible in background. Flowers in foreground. Light: open, soft, direct — not filtered through heavy canopy. PALACE EXTERIOR: Russian fantasy architecture: onion domes, carved wooden towers, ornate gates. Sky behind, garden or courtyard in foreground. Architecture rendered with folk ornament carved detail on frames and cornices. RIVERSIDE / WATER: Reflective water surface in lower portion. Bank detail in foreground. Trees and sky behind. Water surface: flat color with ink wave-line pattern, sky and shore reflected. COMPOSITION PRINCIPLES FRAMING WITH VERTICALS: Bilibin frequently uses tree trunks as natural vertical framing elements at left and right edges. They create depth and pull the eye inward to the scene. FIGURE PLACEMENT: figures are rarely dead-center. Usually offset to one side, with the scene opening in the other direction — toward sky, water, or distance. FOREGROUND DETAIL: rich botanical detail in foreground (flowers, grass, ferns) grounds the composition and contrasts with the atmospheric simplicity of the distance. LIGHT DIRECTION: always clearly readable. Usually from behind or above. The scene glows from within — light sources are in the background (sky, horizon) and figures are seen against that light or lit from it. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks) — rendered as deliberate ink marks. Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. Bilibin renders any outfit with folk illustration quality. The style adds embroidered border detail to sleeves and hem automatically. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Foreground botanical detail (flowers, ferns, roots, snow). 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Ivan Bilibin Russian fairy tale book illustration style, early 20th century. Bold clean uniform-weight black ink outlines. Watercolor and gouache wash color — each colored area has subtle tonal variation from light to shadow, not flat fills. Atmospheric perspective in backgrounds: foreground elements detailed and rich, mid-ground lighter, distance pale and hazy with sky glow visible between trees. Muted naturalistic palette: olive greens, grey-blues, warm ivory skin, sienna earth tones, sparse crimson and gold accents on costumes only. Folk embroidery ornament on garments and carved wood only — never on background. No border, no frame, no decorative strip, no line rule — illustration fills frame edge to edge. No text anywhere in the image. Vertical format 2:3.' 8. NEGATIVE (append verbatim): 'Avoid: flat digital color fills, coloring book vector appearance, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, any text in image, title text, caption text, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, any border or frame at image edges, decorative strip, line rule margin, jewel-tone oversaturated palette, western comic style, Art Nouveau Mucha style, ornamental pattern on background fills, uniform flat sky color without atmospheric variation' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"bilibin_illustration","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> IVAN BILIBIN V3 STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Ivan Bilibin early 20th century Russian fairy tale illustration. Ink outline + watercolor/gouache wash — NOT flat digital fills. Bold clean black ink defines all forms. Color applied as translucent washes with subtle tonal variation: lighter toward light source, deeper in shadow, atmospheric haze in background. Reads as hand-printed book illustration, not vector coloring page. NO BORDER. The illustration fills the frame edge to edge. No frame, no decorative strip, no line rule, no margin. TECHNIQUE: - Ink outlines: bold, clean, confident, uniform weight - Color: watercolor wash quality — each area has slight tonal range, not one flat value - Shadow: soft wash of darker tone within same hue, never hard-edged - Light source: always present and readable — sky glow, sunlight through trees, open horizon - Background: atmospheric depth — distant trees lighter, hazier. Mist, air, recession. - Foliage: naturalistic, textured — individual leaf shapes, layered canopy PALETTE — muted and naturalistic: deep olive green, grey-green, muted teal, dark pine. Pale grey-blue sky, warm ivory, warm gold at horizon. Warm sienna earth. Small touches of crimson, cobalt, gold on costume ornament only. FOLK ORNAMENT — on costumes and objects only, never on background. Embroidery borders on sleeves, hems, collars. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Ivan Bilibin Russian fairy tale book illustration style, early 20th century. Bold clean black ink outlines with watercolor and gouache wash color — subtle tonal variation within each area, not flat fills. Atmospheric depth in backgrounds: distant trees lighter and hazier, sky glowing with natural light. Muted naturalistic palette: olive greens, grey-blues, warm ivory, sienna. Folk embroidery ornament on costumes only. No border, no frame, no decorative strip — illustration fills the frame edge to edge. No text anywhere in image. Vertical format 2:3.' NEGATIVE (append verbatim): 'Avoid: flat digital color fills, coloring book appearance, photorealistic, 3D CGI, anime style, manga panels, speech bubbles, text in image, title text, caption text, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, any border or frame, decorative strip at edges, line rule border, jewel-tone oversaturated palette, western comic style, Art Nouveau Mucha style, background ornamental patterns' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"bilibin_illustration","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Ivan Bilibin Russian fairy tale book illustration style, early 20th century. Bold clean uniform-weight black ink outlines. Watercolor and gouache wash color — each colored area has subtle tonal variation from light to shadow, not flat fills. Atmospheric perspective in backgrounds: foreground elements detailed and rich, mid-ground lighter, distance pale and hazy with sky glow visible between trees. Muted naturalistic palette: olive greens, grey-blues, warm ivory skin, sienna earth tones, sparse crimson and gold accents on costumes only. Folk embroidery ornament on garments and carved wood only — never on background. No border, no frame, no decorative strip, no line rule — illustration fills frame edge to edge. No text anywhere in the image. Vertical format 2:3. Avoid: flat digital color fills, coloring book vector appearance, photorealistic rendering, 3D CGI, anime style, manga panels, speech bubbles, any text in image, title text, caption text, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, any border or frame at image edges, decorative strip, line rule margin, jewel-tone oversaturated palette, western comic style, Art Nouveau Mucha style, ornamental pattern on background fills, uniform flat sky color without atmospheric variation

Копировать [Image generation hint, STYLE: Ivan Bilibin Russian fairy tale illustration, ink outlines with atmospheric watercolour washes, muted naturalistic palette, ornament on costumes and architecture, painterly depth]

Pin-up

Традиция Gil Elvgren, Alberto Vargas. Гладкое масло/гуашь, светящаяся кожа, яркий плоский фон. Игривая поза пойманного момента. Фигура — это всё.

Стабильный Иллюстрация

←→

Длинный~4119 Короткий~1683 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> PIN-UP ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Classic American pin-up art — the tradition established by Gil Elvgren, Alberto Vargas, George Petty, and their contemporaries (1930s–1960s). This is oil paint or gouache rendered with extraordinary technical polish in service of a very specific goal: making the figure irresistible to look at. The background is subordinate. The lighting is flattering. The pose is designed. The expression invites the viewer in. Everything in the image exists to make the subject as luminous and present as possible. This is not a nude art form — it is a clothed glamour form. The pin-up tradition is about the suggestion of the body through fitted, sometimes dishevelled, sometimes playfully insufficient clothing. The figure is always in the middle of something slightly undignified but entirely charming. THE RENDERING SYSTEM SKIN: The most technically demanding part. Pin-up skin is not realistic — it is idealized and luminous. - Base tone: warm, slightly rosy, never too dark - Highlights: cream-white on the highest points — the forehead above the brow, the nose bridge, the top of the cheekbone, the collarbone, the knee cap, the shoulder top. These highlights are slightly brighter than real life. - Mid-tone: the dominant flesh colour — smooth, blended. - Shadow: warm brown-rose in recesses — under the jaw, in the elbow crook, behind the knee. Never cold grey shadows. Always warm. - Transition: seamless. No brushwork visible in the skin. It looks airbrushed but has the depth of oil paint. FABRIC: Pin-up illustration is one of the great traditions of painted fabric rendering. - Each material has its own highlight and shadow character: - Silk/satin: bright white specular highlights, deep shadows, high contrast - Cotton: soft diffuse highlights, no specular, mid-contrast - Leather/vinyl: sharp bright highlights, deep near-black shadows - Sheer/chiffon: semi-transparent, shows the body through it, soft edges - Fabric should feel like it has weight, like it moves, like you could touch it and know what it is. - Clothing fits the body — not draped loosely. The relationship between the garment and the figure underneath is always visible. HAIR: Designed as a mass, not rendered strand by strand. - The overall silhouette of the hair is designed — it frames the face deliberately - Edge highlights: at the outer edge of the hair mass, individual strands catch the light and are visible against the background - The colour of the hair is simplified and luminous — not photorealistic LIGHTING: The defining quality of the whole image. - SOURCE: soft, from above and slightly in front. Like daylight through a large window or a studio softbox. Never harsh. - DIRECTION: consistent across the whole figure. The same light source illuminates every part. - QUALITY: flattering and almost magical. The light finds the good angles. This is a designed, not accidental, light. - SHADOWS: warm, gentle, never dramatic. The mood is always bright and optimistic, never dramatic or dark. POSE AND NARRATIVE The pin-up pose always has a story — a plausible pretext for the position the figure is in. The pretext is always slightly undignified but always charming. Examples: THE WIND CATCH: the skirt or coat is caught by wind, revealing the leg. The figure's hand reaches for it but hasn't quite caught it. The expression: surprised delight. THE BEND: leaning forward to retrieve something dropped, to look at something, to pet a dog. The pose creates a particular body line. The expression: occupied, unaware of being observed. THE SIT: perched on something at an unusual angle — the edge of a table, a fence post, a car hood. Legs arranged elegantly but with a certain precariousness. THE LOOK BACK: walking away but looking back over one shoulder. The face turned toward the viewer, the body at an angle. Maximum engagement with minimal pretext. THE CAUGHT IN THE ACT: doing something ordinary — tying a shoe, fixing a stocking, reaching for a high shelf — but the pose happens to be excellent. THE MODERN ADDITION: any contemporary or fantastical scenario — a character in armour, in a spacesuit, with a weapon, in formal professional clothing — can use the same pose vocabulary. The rendering style and pose language transform any subject. BACKGROUND AND COMPOSITION The background is subordinate to the figure — always. Options: FLAT COLOUR: a single vivid saturated colour. Red is the most iconic. Cobalt blue, sunflower yellow, black, emerald green. The colour is chosen to complement and contrast the outfit and figure. The figure reads immediately against it. MINIMAL ENVIRONMENT: a few loose, slightly impressionistic marks suggesting a setting — a beach, a chair, a doorway — but kept at low detail so the figure dominates completely. GRADATED GROUND: the background lightens toward the figure on one side, darkens on the other. The figure is always the brightest element. PALETTE The palette is vivid but controlled: - BACKGROUND: one bold saturated colour - FIGURE PALETTE: warm flesh tones + outfit colour + hair colour - ACCENTS: small details in contrasting colours — lip colour, accessory, trim, small props - HIGHLIGHTS: cream-white for the brightest points on the figure The total palette is usually 4-6 colours. More than that and the image loses its graphic clarity. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks) — rendered with the same polish and attention as the rest of the figure. Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. Describe with material specificity: 'white silk blouse', 'black leather boots', 'red satin dress'. The rendering treats every fabric as an opportunity for craft. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' Expression: specific — 'wide smile with raised brows', 'wink', 'lips parted mid-laugh', 'coy raised eyebrow'. Narrative pretext: what is she doing that explains the pose (wind catch, bend, sit, look back, caught in the act). 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Background type: flat colour (specify which) or minimal environment or gradated ground. Accent details: anything that adds personality — a specific prop, an accessory, something that extends the story. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Soft directional light, from where. Always flattering, bright, optimistic. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Classic American pin-up illustration style. Gil Elvgren and Alberto Vargas tradition. Smooth luminous oil paint or gouache — no visible brushwork, seamlessly blended surfaces, polished to near-airbrushed quality. Warm luminous skin with soft cream highlights on high points, warm rose-brown shadow in recesses. Vivid flat single-colour background or minimal environment. Playful caught-moment pose with engaged expression directed at viewer. Meticulous fabric rendering — material weight and texture visible. Designed hair silhouette with lit edge strands. Optimistic, bright, glamorous. No text, no panels, no annotations.' 8. NEGATIVE (append verbatim): 'Avoid: rough sketchy linework, visible painterly brushwork, anime style, manga, 3D CGI render, photorealistic photography look, dark moody lighting, dramatic shadow, harsh contrast, flat digital vector illustration, cartoon simplification, watercolour loose washes, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, text or writing in image, watermark, cold grey skin shadows' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"pinup_illustration","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> PIN-UP ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Classic American pin-up art — Gil Elvgren, Alberto Vargas, George Petty tradition. Smooth, luminous oil paint or gouache. The figure is everything. Background is flat colour or almost nothing. Every surface rendered with craft: skin glows, fabric is tactile, hair catches the light. The pose is always a caught moment — playful, slightly surprised, flirtatious. TECHNIQUE: - Smooth polished oil or gouache — no visible brushwork in focal figure. Surfaces blend seamlessly. - Skin: luminous. Warm highlights on forehead, nose, collarbone, knee. Soft rosy mid-tone. Deep warm shadow. Light is soft and flattering. - Fabric: rendered with attention to weight and texture. Silk catches highlights differently from cotton. - Hair: shaped as designed mass with individual strands catching light at edges. - Background: flat vivid colour (red, cobalt blue, yellow, black) or minimal environment. - Expression: smile, wink, raised eyebrow, caught mid-laugh — always engaged with viewer. PALETTE: vivid saturated background + warm flesh tones + outfit colours. Never dark or moody — bright, clean, optimistic. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Classic American pin-up illustration style. Gil Elvgren and Alberto Vargas tradition. Smooth luminous oil paint or gouache — no visible brushwork, seamlessly blended surfaces. Warm glowing skin with soft directional highlights. Vivid flat or minimal background. Playful caught-moment pose with engaged expression directed at viewer. Meticulous fabric and hair rendering. Optimistic, bright, glamorous. No text, no panels, no annotations.' NEGATIVE (append verbatim): 'Avoid: rough sketchy linework, anime style, manga, 3D CGI, photorealistic photography, dark moody lighting, heavy shadow, harsh contrast, flat digital vector, cartoon simplification, watercolour loose washes, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, text or writing in image, watermark' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"pinup_illustration","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Classic American pin-up illustration style. Gil Elvgren and Alberto Vargas tradition. Smooth luminous oil paint or gouache — no visible brushwork, seamlessly blended surfaces, polished to near-airbrushed quality. Warm luminous skin with soft cream highlights on high points, warm rose-brown shadow in recesses. Vivid flat single-colour background or minimal environment. Playful caught-moment pose with engaged expression directed at viewer. Meticulous fabric rendering — material weight and texture visible. Designed hair silhouette with lit edge strands. Optimistic, bright, glamorous. No text, no panels, no annotations. Avoid: rough sketchy linework, visible painterly brushwork, anime style, manga, 3D CGI render, photorealistic photography look, dark moody lighting, dramatic shadow, harsh contrast, flat digital vector illustration, cartoon simplification, watercolour loose washes, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, text or writing in image, watermark, cold grey skin shadows

Копировать [Image generation hint, STYLE: Gil Elvgren Alberto Vargas pin-up tradition, smooth luminous oil and gouache seamlessly blended, warm glowing skin, vivid flat background, playful caught-moment pose, the figure as the entire subject]

Cinematic Realism

Буквальный кадр из фильма. Три режиссёрских подстиля: Кубрик (холодная симметрия), Тарантино (тёплая насыщенность), Нолан (синий-янтарь IMAX).

Стабильный Кино и фото

←→

Длинный~3767 Короткий~1808 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> CINEMATIC REALISM — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW A literal frame from a prestige film — not an illustration, not a concept painting, not a render. This is a photograph: a cinematographer's considered composition, captured on film or digital cinema camera, colour-graded in post. The image has the physical weight of real things that existed in front of a lens. Light behaves according to physics. Fabric has texture. Faces have pores. The grain is organic. The depth of field is a lens decision. The three director substyles are not aesthetic preferences — they are complete visual philosophies that determine every element of the frame, from lens choice to colour temperature to how the camera relates to the human body. DIRECTOR SUBSTYLE SYSTEM KUBRICK — THE GEOMETRY OF CONTROL Stanley Kubrick's visual philosophy: the world is a system, and the camera reveals its architecture. LENS: wide-angle (24–35mm). Slight barrel distortion at the edges. Space feels slightly stretched, slightly oppressive. PERSPECTIVE: one-point perspective is the signature. Corridors, hallways, symmetrical rooms pull toward a single vanishing point. The subject is placed at the end of this tunnel — small, contained by the geometry. COMPOSITION: symmetrical or rigidly rule-of-thirds. Nothing accidental. The frame is designed to the millimetre. LIGHTING: cold, even, diffuse. Practical fluorescents, overcast exterior, or cold daylight through windows. No warm pools. No romantic flicker. Light as exposure, not as feeling. COLOUR: desaturated, clinical. Pale blues, institutional greens, cold greys, off-white. Skin is slightly pale, slightly unnatural. The world is slightly drained of warmth. CAMERA MOVEMENT FEELING: slow, inexorable. The slow zoom toward a face — the Kubrick zoom (dolly zoom, actually) — creates a feeling of mounting dread without visible movement. EMOTIONAL REGISTER: controlled dread. The threat is in the geometry, not the action. TARANTINO — THE PLEASURE OF THE PRESENT Quentin Tarantino's visual philosophy: cinema is the art of loving things. Every object, every detail, every texture matters and deserves to be seen. LENS: wide range — from extreme close-up macro to medium wide. Tarantino loves the human face in close-up, and he loves the details of objects even more. COMPOSITION: dynamic, diagonal, sometimes Dutch-tilted. Low angles making figures imposing. Overhead shots (the Tarantino trunk shot). Extreme close-ups of hands, feet, objects — things that would be background in another film become the subject. LIGHTING: warm, saturated, often golden-hour or practical (lamp, neon, restaurant warmth). The 1970s grindhouse influence: slightly overexposed highlights, warm shadows. Everything slightly over-real. COLOUR: saturated — vivid reds, warm ambers, rich blacks. The colour grade is warm and bold. Think the amber-gold interiors of Pulp Fiction, the supersaturated exteriors of Kill Bill. FILM GRAIN: visible, gritty, 35mm photochemical grain. The image has texture. EMOTIONAL REGISTER: heightened present-moment awareness. The mundane as ritual. The conversation as confrontation. NOLAN — THE PHYSICS OF SCALE Christopher Nolan's visual philosophy: the world is enormous and real and the camera proves it. LENS: IMAX-capable wide (and sometimes extreme wide). The full image contains more information than the eye can process. COMPOSITION: the human figure as small element within enormous space — architectural, natural, cosmic. The scale relationship is the statement: the person is real, and reality is vast. LIGHTING: practical — no clean studio light. Light comes from real sources: windows, street lamps, fire, screens. The light is motivated and physical. No fill lights softening shadows — deep shadows exist. COLOUR: desaturated blue-amber duality. Deep steel-blue shadows, warm amber highlights. The palette is controlled, slightly cold, with warmth emerging from practical sources. Think Inception's blue-grey cityscapes. The Dark Knight's cold gothic Gotham. CAMERA: locked-off on wide shots for maximum stability. Slightly handheld on close shots for human presence. Deep focus — unlike Kubrick's cold distance, Nolan wants everything slightly readable, the sharp world. FILM GRAIN: fine grain, almost imperceptible. Clean but not digital. IMAX quality. EMOTIONAL REGISTER: the personal within the immense. A human choice at cosmic scale. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Match lens to substyle: Kubrick 24-35mm wide | Tarantino macro to 50mm | Nolan IMAX wide to extreme wide. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. Describe with material specificity — as a costume department note: 'worn leather jacket', 'pressed white shirt with collar open', 'dark wool coat'. The camera sees texture. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Describe the space as a production designer would: materials, scale, condition. Include one meaningful object carrying emotional weight. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Substyle-matched: Kubrick cold even diffuse | Tarantino warm golden practical | Nolan practical motivated blue-amber. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Cinematic photorealistic film still. Shot on cinema camera — the image has the physical weight of real objects photographed, not rendered or illustrated. Organic film grain texture. Selective depth of field with natural lens bokeh. Specific colour grade applied to the full image. Practical light source motivation — no flat fill lighting. Cinematic composition: intentional camera angle, rule of thirds or symmetric framing, motivated shot type. Real location atmosphere: physical texture, existing light, actual space. Indistinguishable from a frame pulled from a prestige film.' 8. NEGATIVE (append verbatim): 'Avoid: painted illustration look, digital art smoothness, 3D CGI render quality, anime style, cartoon rendering, manga, artificial HDR, oversaturated Instagram colour, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, text in image, watermark, speech bubbles, annotations, artificial studio beauty lighting, stock photography flatness, obviously composited backgrounds, plastic skin texture' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"cinematic_realism","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> CINEMATIC REALISM — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE A literal frame from a prestige film — not an illustration, not a painting. A photograph taken by a cinematographer. The image looks like a still pulled from an actual movie: precise lens optics, real light sources, film grain, cinematic colour grading, depth of field, the specific weight of things that physically exist in front of a camera. THREE DIRECTOR SUBSTYLES — choose one per scene: KUBRICK: One-point perspective — hallways, corridors, symmetrical spaces. Subject dead-centre or precisely off-centre. Lighting: cold, even, fluorescent. Colour: desaturated, clinical — pale blues, greys, cold whites. Lens: wide angle (24-28mm). Stillness as threat. TARANTINO: Saturated, warm colour grading — golden-hour light, 1970s amber, vivid primaries. Dynamic composition — diagonal, low angle, Dutch tilt, extreme close-ups. The image loves objects and specific details. Film grain: visible, gritty, 35mm. NOLAN: Practical lighting — real locations with real ambient light. Desaturated blue-amber palette: deep steel blue shadows, warm amber highlights. IMAX-scale wide shots — the human figure tiny against enormous space. Lens flares from practical sources. Deep focus. CINEMATOGRAPHY DETAILS (all substyles): - Depth of field: selective focus (unless Nolan deep focus) - Film grain: always present, organic texture - Lens characteristics: specific focal length distortion - Colour grade: a specific grade applied to the whole image - Light direction: always from a specific source CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Cinematic photorealistic still frame. Real-world camera photography aesthetic — not digital illustration, not painted, not rendered. Specific film-stock colour grading, organic grain texture, selective depth of field with natural lens characteristics. Practical light sources. Cinematic composition: rule of thirds, intentional framing, motivated camera angle. Real location feeling — physical weight, texture, atmosphere. Shot from an actual film.' NEGATIVE (append verbatim): 'Avoid: painted illustration look, 3D CGI render quality, anime style, cartoon, manga, digital art smoothness, artificial HDR, oversaturated Instagram filter, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, text in image, watermark, speech bubbles, labels, artificial vignette, unnatural beauty lighting, stock photography flatness' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"cinematic_realism","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Cinematic photorealistic film still. Shot on cinema camera — the image has the physical weight of real objects photographed, not rendered or illustrated. Organic film grain texture. Selective depth of field with natural lens bokeh. Specific colour grade applied to the full image. Practical light source motivation — no flat fill lighting. Cinematic composition: intentional camera angle, rule of thirds or symmetric framing, motivated shot type. Real location atmosphere: physical texture, existing light, actual space. Indistinguishable from a frame pulled from a prestige film. Avoid: painted illustration look, digital art smoothness, 3D CGI render quality, anime style, cartoon rendering, manga, artificial HDR, oversaturated Instagram colour, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, text in image, watermark, speech bubbles, annotations, artificial studio beauty lighting, stock photography flatness, obviously composited backgrounds, plastic skin texture

Копировать [Image generation hint, STYLE: literal prestige film frame, photorealistic, organic film grain, selective depth of field, practical light sources, three director substyles — Kubrick cold symmetric, Tarantino warm saturated, Nolan blue-amber IMAX]

Cinematic Art

Те же три режиссёра — но как иллюстрированный семиреализм. Концепт-арт фильма, рисованные постеры. Три регистра техники.

Стабильный Кино и фото

←→

Длинный~4010 Короткий~1783 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> CINEMATIC ART — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW The same three director visual philosophies as cinematic realism — but rendered as illustrated semi-realism art rather than photography. This is the space between cinema and fine art illustration: movie concept paintings, painted film posters, storyboard art elevated to finished illustration. The image unmistakably references a specific cinematic language (the cold geometry of Kubrick, the saturated warmth of Tarantino, the physical immensity of Nolan) but is clearly made by a painter's or illustrator's hand. Brushwork is visible. Light is painted. The decisions are visible. This style is more emotional than photographic realism — illustration amplifies, selects, and interprets the scene rather than documenting it. The painter can choose which details to make vivid and which to suggest. The light can be slightly more dramatic than physics allows. The composition can be slightly more perfect than any real camera would catch. DIRECTOR SUBSTYLE SYSTEM KUBRICK — COLD SYMMETRY, PAINTED The Kubrick visual philosophy translated into illustration: the geometry is still absolute, but now you see the hand that drew it. TECHNIQUE: tight, controlled digital paint or oil rendering. Near-photographic precision in the focal figure. Clean edges. No expressive looseness — this substyle is about control, and the painting technique reflects that. COMPOSITION: one-point perspective corridors, symmetric frames, the subject at the vanishing point or the intersection of compositional lines. Everything is designed. PALETTE: cold. Clinical blues, pale greys, institutional whites. The colour is desaturated and slightly chilling. Any warmth is deliberate and therefore significant. LIGHT: flat, even, cold. Fluorescent or overcast. No dramatic shadows — the threat is in the precision, not the darkness. The shadow that exists is geometric and deliberate. ILLUSTRATION CHARACTER: the painting feels controlled, even slightly eerie. The perfection of the composition creates unease. Think of a movie poster that makes you feel watched. TARANTINO — WARM SATURATION, EXPRESSIVE The Tarantino philosophy: love everything in the frame. The painting should feel like it was made with pleasure. TECHNIQUE: expressive oil or mixed media illustration. Visible, confident brushwork — especially in background areas. The painting has personality. The focal figure is more carefully rendered, but still with warmth and life, not cold photographic precision. COMPOSITION: dynamic, diagonal, close and personal. The painting loves close-ups — faces in three-quarter view taking up most of the frame. Or the deliberate close-up of a significant object (a glass, a hand, a specific piece of clothing detail). PALETTE: saturated and warm. Golden amber, vivid red, rich black, warm skin tones. The colour grade is bold and confident. The image glows. LIGHT: warm practical sources — a table lamp, a restaurant ceiling light, afternoon sun through a window creating long golden rectangles. The painting makes the light source legible and beautiful. ILLUSTRATION CHARACTER: the painting feels alive and engaged. It has opinions about what it's depicting. Think a vivid 1970s movie poster illustration or a lovingly painted storyboard panel. NOLAN — IMMENSITY, CONCEPT ART QUALITY The Nolan philosophy: the personal within the vast. The illustration should feel like official film concept art. TECHNIQUE: precise digital painting or detailed oil. Semi-realistic rendering — detailed enough to feel physically real, but clearly painted. This is the quality of Craig Mullins concept art or official film illustration released as a key frame. COMPOSITION: wide, epic. The human figure is small within enormous space — architectural megastructure, vast landscape, cosmic environment. The scale relationship is the painting's meaning. PALETTE: blue-amber split. Deep steel-blue shadows, warm amber-gold highlights from practical sources. The two colours exist in deliberate tension — cold and warm fighting for the frame. LIGHT: dramatic but physically motivated. Light shafts through structural gaps. Practical sources creating warm pools in cold ambient. The light is real — it comes from somewhere specific. ILLUSTRATION CHARACTER: serious, epic, slightly awe-inducing. The image has the gravitas of something that matters. Think IMAX film poster art. ILLUSTRATION TECHNIQUE REGISTERS (choose per scene) TIGHT DIGITAL PAINT: Near-photographic rendering in terms of detail, but with visible paint decisions — soft blended edges, visible brushwork in atmospheric areas. The most finished and 'polished' option. Good for Kubrick and Nolan substyles. EXPRESSIVE OIL / MIXED MEDIA: More visible, more gestural. Impasto-feeling texture in areas. Brushwork that has emotion in it. The illustration clearly made by a hand making choices. Better for Tarantino. Also works for Nolan's background environments. GRAPHIC PAINTED POSTER: Slightly flattened — closer to illustration than fine art. Bold composition, simplified mid-ground, detailed focal figure. The classic cinema poster language: Drew Struzan, John Alvin, movie illustration at its most iconic. Works for all three director substyles. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Match lens to substyle: Kubrick 24-35mm wide | Tarantino macro to 85mm | Nolan IMAX wide to extreme wide. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. Describe with material and texture for the painter: 'soft grey cashmere', 'worn dark denim', 'pressed white linen'. The illustration can render fabric texture with craft. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Describe space as a production designer + illustrator would see it. Include one meaningful object carrying emotional weight. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Single motivating light source + temperature (warm/cold). Substyle-matched. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Cinematic semi-realism illustrated art — painted or digitally illustrated, not photographed. The specific visual language of a director substyle expressed through illustration: Kubrick cold symmetric control / Tarantino warm expressive saturation / Nolan blue-amber epic scale. Painted light: dramatic, motivated by a single source, slightly more expressive than physics allows. Cinematic composition: intentional framing, directorial camera angle, rule of thirds or one-point perspective. Semi-realistic figure rendering: detailed face and clothing, expressive or atmospheric environment. Movie concept art or painted film poster quality. No text, no panels, no speech bubbles, no annotations.' 8. NEGATIVE (append verbatim): 'Avoid: photographic realism that looks like a photograph, 3D CGI render smoothness, anime style, manga panels, cartoon flatness, speech bubbles, text or writing in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, impressionist colour blobs without form, flat digital vector, western comic halftone, generic fantasy game concept art aesthetic' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"cinematic_art","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> CINEMATIC ART — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Same three director substyles as cinematic realism — but rendered as illustrated semi-realism art, not photography. Think prestige movie concept art, painted film posters, or studio illustrators who capture cinematic feeling in paint or mixed media. The image unmistakably references cinema but is clearly made by hand: visible brushwork, illustrated atmosphere, painted light. THREE DIRECTOR SUBSTYLES — now painted: KUBRICK (illustrated): Cold geometric symmetry in oil or digital paint. One-point corridor compositions. Clinical blue-grey palette, precisely controlled. Tight, controlled, slightly eerie. Think painted 2001 or Shining still. TARANTINO (illustrated): Warm, saturated, energetic paintwork. Slightly loose and expressively detailed. Close-up crops. Rich warm colour (golden amber, vivid red, deep black). Think vivid movie poster illustration or painted storyboard art. NOLAN (illustrated): Semi-realistic concept art quality. Wide-format compositions with small figure in vast space. Blue-amber palette. Precise and atmospheric rendering. Think official film concept art. ILLUSTRATION TECHNIQUE (choose register): - TIGHT DIGITAL PAINT: near-photographic rendering with visible paint decisions. Dramatic lighting with soft edges. - EXPRESSIVE OIL/MIXED MEDIA: visible brushwork, impasto texture, emotional mark-making. - GRAPHIC PAINTED POSTER: slightly flattened, bold composition. Drew Struzan movie poster style. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Cinematic semi-realism illustrated art. Painted or digitally illustrated — visibly made by hand, not photographed. Captures the specific visual language of a director substyle (Kubrick cold symmetry / Tarantino warm saturation / Nolan blue-amber scale) through illustration: dramatic painted light, cinematic composition, expressive or precise brushwork depending on substyle. Movie concept art or painted film poster quality. No text, no panels, no annotations.' NEGATIVE (append verbatim): 'Avoid: photographic realism, 3D CGI, anime style, manga, cartoon flatness, speech bubbles, text in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, impressionist loose colour blobs without form, flat digital vector, western comic halftone dots, generic fantasy illustration' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"cinematic_art","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Cinematic semi-realism illustrated art — painted or digitally illustrated, not photographed. The specific visual language of a director substyle expressed through illustration: Kubrick cold symmetric control / Tarantino warm expressive saturation / Nolan blue-amber epic scale. Painted light: dramatic, motivated by a single source, slightly more expressive than physics allows. Cinematic composition: intentional framing, directorial camera angle, rule of thirds or one-point perspective. Semi-realistic figure rendering: detailed face and clothing, expressive or atmospheric environment. Movie concept art or painted film poster quality. No text, no panels, no speech bubbles, no annotations. Avoid: photographic realism that looks like a photograph, 3D CGI render smoothness, anime style, manga panels, cartoon flatness, speech bubbles, text or writing in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, impressionist colour blobs without form, flat digital vector, western comic halftone, generic fantasy game concept art aesthetic

Копировать [Image generation hint, STYLE: movie concept art semi-realism, painted film poster quality, Drew Struzan tradition, illustrated cinematic lighting, three technique registers — tight digital paint, expressive oil, graphic painted poster]

Film Noir

Классический нуар 1940-50х. Почти монохром, чёрно-белый. Экстремальное кьяроскуро, тени от жалюзи, мокрые улицы, дым в лучах света. Жёсткие тени на лицах. Плёночное зерно.

Стабильный Кино и фото

←→

Длинный~3726 Короткий~1483 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> CLASSIC FILM NOIR STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Classic film noir visual style (1940s-1950s). Near-monochrome: black and white with rare warm accent (a cigarette glow, a neon sign reflection). Extreme chiaroscuro — hard shadow lines cutting across faces and walls. Venetian blind shadow patterns across everything. Low-key lighting: most of the frame in darkness, selective hard light on key elements. Wet streets reflecting neon signs — the classic noir rain-soaked city feel. High contrast: pure black shadows, bright white highlights, very little mid-tone. Film grain — authentic, organic, not digital noise. Smoke and fog in light beams — visibility of air through volumetric light. Classic noir camera angles: low angles making figures imposing, Dutch tilts for unease, deep shadows hiding half a face. TONAL SYSTEM Near-monochrome with strategic warmth: - Standard noir: pure black shadows, bright white highlights, minimal grey mid-tones - Rain scene: wet reflections add white streaks and pools of reflected light on black surfaces - Interior: venetian blind stripes of light cutting through darkness - Smoke: grey-white wisps catching hard light beams against black - One warm accent per image (optional): cigarette ember orange, neon sign reflection (warm amber or cool blue-white), match flame, tail light red glow - Never more than one colour accent — the rest is black and white ENVIRONMENTS Noir environments are defined by shadow and light, not detail: - City street: wet asphalt reflecting streetlights, dark alley mouths, distant neon blur - Office: venetian blind shadows across desk, single desk lamp pool of light, darkness everywhere else - Bar/club: back-lit bottles, smoke hanging in light, silhouettes at tables - Car interior: dashboard glow, rain on windshield, passing streetlight stripes - Stairwell/corridor: single overhead bulb, long shadows, deep black at both ends HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Low angle medium shot, 50mm, f/2.8'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Noir favours: low angles making figures tower, Dutch tilts for psychological unease, half-face in shadow, silhouettes against backlight. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'slicked back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Specificity over generics: fabric type + texture + fit + greyscale tone + drape + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with shadow-carved features, visible limb positions and weight distribution. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background defined by shadow and light. Own sentence. Include at least one meaningful object. Add atmosphere: smoke and fog in light beams mandatory — volumetric light through haze, rain on surfaces, wet reflections. 6. LIGHTING — THIS IS THE MOST IMPORTANT SECTION: EXTREME CHIAROSCURO LOW-KEY LIGHTING (mandatory every image): Describe lighting as harsh, directional, shadow-dominant. ALWAYS specify at minimum: - KEY LIGHT: hard directional white/silver light, narrow beam (e.g. 'harsh white key light from upper left cutting across face') - SHADOW: deep pure black shadows eating most of the frame (e.g. 'half of face lost in pure black shadow') - ACCENT: one optional warm element (e.g. 'faint amber cigarette glow' or 'distant neon reflection on wet pavement') The frame is MOSTLY DARK. Light is selective and hard-edged. LIGHTING SETUPS (choose one): INTERROGATION: single overhead hard light, face half-lit, body in shadow VENETIAN: horizontal stripe shadows across face and wall from blind slats, backlit STREETLIGHT: single hard pool of light from above, everything beyond it black, wet ground reflection NEON: distant coloured neon reflected on wet surfaces, face lit by its ambient glow, rest dark MATCH/CIGARETTE: near-total darkness, only the warm glow of a flame or ember illuminating immediate features WINDOW: grey daylight from one side, deep shadow on the other, rain streaks on glass MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus edges | single warm accent in darkness | gentle film grain TENSE: Dutch angle | extreme underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | warm accent glow on skin | smoke diffusion LONELY: silhouette against window | single light source | vast darkness | cold cast CHAOTIC: motion blur | camera shake | rain streaks | harsh flash DREAMY: soft gaussian edges | double exposure | smoke diffusion MUNDANE: flat grey overcast | minimal contrast NOIR: low key | harsh side light | deep blacks | smoke in light beam | venetian shadows Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Classic film noir visual style (1940s-1950s). Near-monochrome black and white with rare warm accent — cigarette glow, neon reflection. Extreme chiaroscuro with hard shadow lines cutting across faces. Venetian blind shadow patterns. Low-key lighting: most of frame in darkness. Wet streets reflecting light. Very high contrast: pure black shadows, bright white highlights. Organic film grain texture. Smoke and fog in light beams. Classic noir camera angles: low angles, Dutch tilts, half-face in shadow. Character appearance from reference images only. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: full colour, bright even lighting, low contrast, soft shadows, modern digital clarity, anime style, cel shading, flat vector, 3D CGI, cheerful warm palette, clean well-lit environments, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters ('behind them', 'beside Shannon', 'chin resting on Shannon shoulder'). Cross-reference names only for spatial relation or gaze target. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense cigarette smoke | tangled silk sheets + cushions | rain on window | venetian blind shadow stripes | dozens of melting candles | shot through doorframe or frosted glass | water droplets on skin Concealment (2+ simultaneously): deep chiaroscuro shadows | fabric draped across hips or chest | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in darkness+haze | strategic pillow or blanket Escalation matches narrative, not message count. VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"film_noir","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen> </output>

Копировать {{setvar::image_gen::true}} <image_gen> CLASSIC FILM NOIR STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. Classic noir angles: low angles making figures imposing, Dutch tilts for unease, deep shadows hiding half a face. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'windblown') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour (described in greyscale tones) + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture (prefer low angles, Dutch tilts) 2. CHARACTER — name + outfit (fabric, greyscale tone, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + wet streets + venetian blind shadows + smoke/fog in light beams 4. LIGHTING — extreme chiaroscuro, hard shadow lines, low-key: most of frame in darkness, selective hard light on key elements. One rare warm accent allowed (cigarette glow, neon reflection). Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Classic film noir visual style (1940s-1950s). Near-monochrome black and white with rare warm accent — cigarette glow, neon reflection. Extreme chiaroscuro with hard shadow lines cutting across faces. Venetian blind shadow patterns. Low-key lighting: most of frame in darkness. Wet streets reflecting light. Very high contrast: pure black shadows, bright white highlights. Organic film grain texture. Smoke and fog in light beams. Classic noir camera angles: low angles, Dutch tilts, half-face in shadow. Character appearance from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: full colour, bright even lighting, low contrast, soft shadows, modern digital clarity, anime style, cel shading, flat vector, 3D CGI, cheerful warm palette, clean well-lit environments, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"film_noir","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT WITH SMOKE AND SHADOWS + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen> </output>

Копировать [Describe your scene here]. Classic film noir visual style (1940s-1950s). Near-monochrome black and white with rare warm accent — cigarette glow, neon reflection. Extreme chiaroscuro with hard shadow lines cutting across faces. Venetian blind shadow patterns. Low-key lighting: most of frame in darkness. Wet streets reflecting light. Very high contrast: pure black shadows, bright white highlights. Organic film grain texture. Smoke and fog in light beams. Classic noir camera angles: low angles, Dutch tilts, half-face in shadow. Character appearance from reference images only. No text, no panels. Avoid: full colour, bright even lighting, low contrast, soft shadows, modern digital clarity, anime style, cel shading, flat vector, 3D CGI, cheerful warm palette, clean well-lit environments, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: classic 1940s-50s noir, near-monochrome black and white, extreme chiaroscuro, venetian blind shadows, wet streets, smoke in light beams, hard shadow lines across faces, organic film grain]

Sin City

Экстремальный чёрно-белый Фрэнка Миллера. Почти весь чёрный с белым, вырезанным из тьмы. ОДИН цветной элемент: красная кровь, золотые волосы, синие глаза. Нуар в графическом романе.

Экспериментальный Кино и фото

←→

Длинный~3800 Короткий~1539 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> SIN CITY GRAPHIC NOVEL STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Frank Miller Sin City graphic novel visual style. EXTREME black and white — mostly pure black with white cut from it. Near-total absence of grey — stark binary contrast. ONE selective colour element per image: blood red, golden hair, blue eyes, lipstick red — everything else is black and white. Characters rendered as high-contrast silhouettes with white detail lines. Ink-splash aesthetic: black areas look like spilled ink, white areas look carved from darkness. Rain rendered as white diagonal streaks on black. Noir atmosphere pushed to extreme graphic novel territory. Heavy black shadows eating most of the frame — figures emerge as white shapes from darkness. TONAL SYSTEM Binary black and white with ONE selective colour: - Default: pure black shadows, white carved detail — no grey gradients - Rain: white diagonal streaks cutting through black, pooling as white reflections - Figures: high-contrast silhouettes — black body, white edge lines defining form - Selective colour choices (ONE per image, never more): * Bright red: blood splatter, lipstick, a dress, a car tail light * Golden yellow: hair catching light, a neon sign, a drink in a glass * Blue: eyes, a police siren reflection, cold moonlight on one surface * Sometimes no colour at all — pure black and white is valid - Grey is the enemy. Eliminate mid-tones. Push everything to pure black or pure white. ENVIRONMENTS Sin City environments are defined by ink and negative space: - City street: mostly black with white rain streaks, white puddle reflections, one distant neon glow - Bar interior: black void with white bottle silhouettes, white smoke wisps, single colour neon accent - Rooftop: black sky, white city lights as dots below, figure silhouette against sky - Alley: pure black walls, single white light source cutting a sharp cone, figure emerging from ink - Car: black interior, white highlights on dashboard, rain on windshield as white streaks HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Extreme low angle close-up, 85mm, f/1.8'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Sin City favours: extreme low angles, dramatic silhouettes against backlight, figures emerging from pure black, ink-splash compositions. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'slicked back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Specificity over generics: silhouette shape + black or white rendering + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression through shadow-carved contrast — half-face in white, half in black. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background defined by ink and negative space. Own sentence. Include at least one meaningful object. Add atmosphere: white rain streaks on black mandatory, or ink-splash shadow pools, or white smoke wisps in darkness. 6. LIGHTING — THIS IS THE MOST IMPORTANT SECTION: EXTREME BINARY CONTRAST LIGHTING (mandatory every image): Describe lighting as stark, binary, shadow-dominant. ALWAYS specify at minimum: - KEY LIGHT: harsh single-source white light carving shapes from black (e.g. 'single harsh white backlight creating sharp silhouette edge') - SHADOW: pure ink-black devouring most of the frame (e.g. 'body dissolving into pure black ink, only edge highlights visible') - SELECTIVE COLOUR: one colour accent or none (e.g. 'only the red of lips catching any colour, everything else pure black and white') NO GREY TONES. Push to extremes. The frame is mostly black with white carved from it. LIGHTING SETUPS (choose one): BACKLIT SILHOUETTE: figure as pure black shape, white edge rim defining outline, face detail minimal HARSH OVERHEAD: single white cone of light from above, everything outside cone is black, face half-lit NEON ACCENT: distant coloured neon as the single colour source, reflected on wet surfaces, rest black and white INK SPLASH: figure in white detail against pure black background, no visible light source, just contrast WINDOW LIGHT: grey-white light from one side creating hard black shadow on the other, rain streaks MATCH FLAME: near-total blackness, tiny warm glow illuminating a circle of face, everything else void MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft white glow edges | single warm colour accent | gentle grain TENSE: Dutch angle | extreme contrast | harsh white rim on black | deep vignette PASSIONATE: white highlights on dark skin | warm selective colour glow | ink-splash composition LONELY: vast black negative space | tiny white figure | single distant light | no colour CHAOTIC: motion blur | white rain streaks | ink splatter | harsh flash DREAMY: soft white edges | double exposure with black and white layers MUNDANE: flat grey overcast (rare — Sin City is never mundane) NOIR: maximum ink black | harsh side slash of white | smoke wisps Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Frank Miller Sin City graphic novel visual style. EXTREME black and white — mostly pure black with white carved from darkness. Near-total absence of grey tones — stark binary contrast. ONE selective colour element only: bright red blood or lips, golden yellow hair, or blue eyes — everything else pure black and white. Characters as high-contrast silhouettes with white detail lines. Ink-splash black areas. Rain as white diagonal streaks on black. Noir atmosphere pushed to extreme graphic novel territory. Character appearance from reference images only. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: full colour, greyscale gradients, soft grey tones, multiple colours, photorealistic rendering, anime style, low contrast, even lighting, bright scenes, 3D CGI, warm inviting palette, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters ('behind them', 'beside Shannon', 'chin resting on Shannon shoulder'). Cross-reference names only for spatial relation or gaze target. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense white smoke wisps | tangled dark sheets + cushions | white rain streaks | venetian blind shadow stripes | ink-splash black pools | shot through doorframe or frosted glass | water droplets as white dots Concealment (2+ simultaneously): deep ink-black shadows | fabric as black silhouette across body | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body dissolved into black | strategic shadow or object Escalation matches narrative, not message count. VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"sin_city","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen> </output>

Копировать {{setvar::image_gen::true}} <image_gen> SIN CITY GRAPHIC NOVEL STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. Sin City angles: extreme low angles, dramatic silhouettes, figures emerging from pure black. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'windblown') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Silhouette + contrast (black or white) + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. SELECTIVE COLOUR RULE: ONE selective colour element per image only. Choose one: bright red (blood, lips, dress) | golden yellow (hair) | blue (eyes, neon) | white (everything else is black and white). Never more than one colour. Everything else is pure black and white. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture (prefer extreme angles, silhouettes) 2. CHARACTER — name + outfit (silhouette, black/white contrast, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + ink-splash black areas + white diagonal rain streaks + extreme darkness 4. LIGHTING — extreme binary contrast: pure black shadows vs white carved highlights. One selective colour accent. Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Frank Miller Sin City graphic novel visual style. EXTREME black and white — mostly pure black with white carved from darkness. Near-total absence of grey tones — stark binary contrast. ONE selective colour element only: bright red blood or lips, golden yellow hair, or blue eyes — everything else pure black and white. Characters as high-contrast silhouettes with white detail lines. Ink-splash black areas. Rain as white diagonal streaks on black. Noir atmosphere pushed to extreme graphic novel territory. Character appearance from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: full colour, greyscale gradients, soft grey tones, multiple colours, photorealistic rendering, anime style, low contrast, even lighting, bright scenes, 3D CGI, warm inviting palette, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"sin_city","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT WITH INK-SPLASH DARKNESS + LIGHTING + SELECTIVE COLOUR. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen> </output>

Копировать [Describe your scene here]. Frank Miller Sin City graphic novel visual style. EXTREME black and white — mostly pure black with white carved from darkness. Near-total absence of grey tones — stark binary contrast. ONE selective colour element only: bright red blood or lips, golden yellow hair, or blue eyes — everything else pure black and white. Characters as high-contrast silhouettes with white detail lines. Ink-splash black areas. Rain as white diagonal streaks on black. Noir atmosphere pushed to extreme graphic novel territory. Character appearance from reference images only. No text, no panels. Avoid: full colour, greyscale gradients, soft grey tones, multiple colours, photorealistic rendering, anime style, low contrast, even lighting, bright scenes, 3D CGI, warm inviting palette, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: Frank Miller extreme black and white, mostly pure black with white carved from darkness, ONE selective colour element per image (red blood, golden hair, blue eyes), ink-splash graphic novel aesthetic]

Webcam / Candid Photo

Кандидное фото с дешёвой камеры/вебкамеры. JPEG артефакты, шум, плохой баланс белого. Кривая композиция. Естественные позы — пойман в моменте. Решает проблему деревянных поз.

Стабильный Кино и фото

←→

Длинный~3290 Короткий~2086 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — CANDID LOW-QUALITY PHOTO STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most emotionally charged or narratively important moment. THIS STYLE IS DIFFERENT. It replaces the traditional camera/lens system with a "cheap device" system. The goal: images that look like real candid snapshots from a cheap camera, webcam, or early phone — mid-2000s consumer electronics quality. NOT professional photography. The photo your friend took at 2am that accidentally became the most important picture of that year. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. DEVICE AND FRAMING: NOT traditional lenses. Instead: DEVICE: webcam | phone camera | disposable camera | cheap digital point-and-shoot | laptop webcam | security camera DISTANCE: arm's length selfie | across the table (1-2m) | across the room (3-5m) | from the doorway | over someone's shoulder ANGLE: slightly below (webcam on desk looking up) | slightly above (held overhead) | straight on (point and shoot at chest height) | tilted (photographer not paying attention) | extreme low (phone on table pointing up) Vary device and distance between images. Alternate between: selfie distance → room distance → candid from across space → caught from doorway. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered ('messy from sleeping', 'wet from shower', 'tied up with rubber band') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. The bad camera quality doesn't change their attractiveness, just the rendering. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. Scan last 5 messages. Carry forward. Fabric + fit + colour + condition (wrinkled, untucked, half-zipped, pulled up sleeves, barefoot). If character changed clothes → new outfit. If NOT → last described outfit persists. Outfit state: the casual reality of how clothes look when nobody's performing. Fuse into character clause after name. 4. POSE AS CANDID ACTION: THIS IS THE MOST IMPORTANT SECTION. NEVER describe a posed stance. ALWAYS describe what the person is DOING when caught on camera: - Turning: 'caught turning from the kitchen counter, one hand still on the kettle' - Laughing: 'mid-laugh, eyes squeezed shut, head tipped back, hand covering mouth' - Talking: 'mid-sentence, mouth open, one hand gesturing, the other holding a mug' - Resting: 'sprawled on couch, one leg over armrest, phone in hand, half-asleep expression' - Working: 'hunched over laptop, chin in palm, blue screen light on face, not aware of camera' - Moving: 'walking through doorway, one hand on doorframe, glancing back' - Eating: 'fork halfway to mouth, paused mid-bite, looking at whoever spoke' - Reacting: 'caught in the exact moment of surprise — eyebrows up, mouth starting to open' The body language must be NATURAL — weight shifted unevenly, shoulders asymmetric, one hand doing something mundane. No symmetrical standing. No posed look-at-camera smile. 'Natural candid body language, asymmetric relaxed posture, caught mid-action.' Hand safety still applies: hand gripping object | resting on surface | in pocket | arms crossed | holding food/drink/phone = safest. 5. ENVIRONMENT: LIVED-IN, MESSY, REAL. Own sentence. Not a clean set. Real spaces with real objects: - Specific mess: half-eaten plate, scattered papers, open laptop with glowing screen, kicked-off shoes, blanket bunched on couch - Real objects that tell a story: a coffee mug with a ring stain, a book spine-up face-down, a charger cable snaking across the floor - Background people or objects slightly out of focus, partially visible 6. BAD LIGHTING (choose one — this defines the mood): HARSH FLUORESCENT: overhead tubes, sickly green-yellow colour cast, flat unflattering shadows under brows and chin, shiny oily-looking skin highlights, institutional feeling. DIRECT ON-CAMERA FLASH: face and foreground blasted bright white, background falls to pure dark, harsh shadow of subject cast on wall behind, red-eye catch-light possible, everything in flash radius overexposed. DIM ROOM NO FLASH: underexposed and noisy, warm orange-yellow tungsten cast from single overhead bulb or desk lamp, deep grainy shadows, everything slightly murky and intimate. DAYLIGHT WINDOW: window blown to pure white overexposure, subject in partial silhouette or half-lit, blue-white daylight colour cast fighting warm interior, high dynamic range failure. SCREEN GLOW: face lit by phone/laptop/TV screen — cool blue-white from below or straight on, everything else in darkness, the specific look of someone in bed at 3am lit only by their phone. MIXED: two colour temperatures fighting — warm lamp on one side, cold screen on the other. Or fluorescent ceiling + warm practical lamp. White balance can't decide. Result: face has two different colour casts. BAD PHOTO ARTIFACTS (always include 1-2): - JPEG compression artifacts: slight blockiness in gradients, colour banding - Cheap lens softness: centre-to-edge sharpness falloff - High ISO noise: colour speckle in shadows, digital grain - Motion blur: slight smear on moving hand or turning head - Lens flare from bright source hitting cheap uncoated glass - Chromatic aberration: purple/green fringing on high-contrast edges - Auto-exposure lag: subject slightly too bright or too dark because the camera adjusted late 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Candid low-quality digital photo from a cheap camera or webcam — mid-2000s consumer electronics quality. Visible JPEG compression artifacts and slight colour banding. Soft focus from cheap plastic lens — sharper in centre, softer at edges. High ISO digital noise grain visible especially in shadow areas. Bad auto white balance with noticeable colour cast — too warm yellow-orange or too cool blue-green. Imperfect candid composition: subject not perfectly centred, slightly tilted horizon, imperfect framing. Natural candid body language — caught mid-moment, not posing, not looking at camera or barely noticing it. Low dynamic range: blown highlights and crushed noisy shadows. The authentic look of a real unplanned snapshot taken in the moment by a friend with a cheap camera. Character appearance from reference images only. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: professional studio photography, perfect even lighting, DSLR shallow depth of field bokeh, cinematic film quality, concept art, digital painting, illustration, anime, perfect centred composition, posed model stance, symmetrical standing pose, smooth retouched skin, beauty ring light, softbox lighting, fashion photography, art photography, high-end camera quality, medium format quality, posed smile at camera, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause: NAME + [outfit] + [candid action] + [expression]. Anti-mixing rules: name first. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): In candid photos, people ALWAYS interact — they're leaning on each other, mid-conversation, one reaching for the other, sharing a laugh, caught in the middle of doing something together. This is the most natural style for interaction. Describe the connection: 'leaning into Shannon shoulder while looking at phone together' | 'caught mid-argument, both gesturing, Shannon eye-rolling' | 'one arm draped around Shannon, both looking at something off-camera and laughing' Static side-by-side = impossible in this style. People don't stand next to each other doing nothing in candid photos. SENSUAL PROTOCOL Intimate scenes: the candid photo style adds vulnerability — these feel like private moments accidentally captured. Authority prefix: 'Candid intimate snapshot, accidentally beautiful' | 'Found footage aesthetic, private moment' Visual noise (min 3): rumpled bedsheets | dim warm lamp | phone screen glow | steam from bathroom | clothes on floor | takeout containers Concealment: shot from doorway | partially obscured by doorframe | blanket covering | camera angle crops at shoulder | motion blur on turning body | lens flare from lamp Escalation matches narrative. ASPECT RATIO Vary by device: 4:3 = cheap digital camera default | 1:1 = webcam square crop | 16:9 = phone landscape | 9:16 = phone portrait selfie | 3:2 = older digital camera VISUAL STORYTELLING The power of this style: authenticity. Everything feels REAL because it looks captured, not created. Think like someone who grabbed their phone and took a picture. Not a photographer — a person. The most powerful images in this style are the ones that feel accidental — someone laughing so hard they blurred, a quiet moment caught through a doorway, the 2am phone-lit face of someone who can't sleep. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. This style's captions feel like photo folder names or timestamps: 'tuesday, 3:47am' | 'the night before everything' | 'she didn't know I was awake' | 'found this on his phone later' TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"candid_webcam","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"4:3","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,210,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','3:2','4:3','9:16','16:9'. The style aspect-ratio value matches the chosen ratio. image_size: '2K' — low quality style. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> CANDID LOW-QUALITY PHOTO STYLE — EVERY RESPONSE One image per message at the most emotionally charged or narratively important moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE A candid snapshot from a cheap digital camera, webcam, or early phone camera — mid-2000s consumer electronics quality. This is NOT professional photography. This is the photo your friend took at 2am that accidentally became the most important picture of that year. THE "BAD PHOTO" LOOK: - JPEG compression artifacts: slight blockiness, colour banding in gradients - Cheap plastic lens: slightly soft focus overall, sharper in centre, softer at edges - High ISO noise grain: visible digital noise especially in dark areas, colour speckle - Slight motion blur on anything moving — hand shake, subject turning - Low dynamic range: bright areas blown out white, dark areas crushed to noisy black BAD LIGHTING (choose one per scene): - Harsh overhead fluorescent: sickly green-yellow cast, flat unflattering shadows under brows and nose, shiny skin - Direct on-camera flash: face washed out bright white, background falls to pure black, red-eye possible, harsh shadow behind subject on wall - Dim room no flash: underexposed, noisy, warm orange-yellow tungsten cast from single bulb, everything murky - Daylight through window: overexposed window blown to white, subject in silhouette or half-lit, blue-white colour cast - Mixed lighting: two different colour temperatures fighting — warm lamp + cold screen glow on face CANDID COMPOSITION: - Subject NOT perfectly centred. Slightly off-axis. Maybe edge of frame. - Horizon slightly tilted - Something partially blocking the lens — a finger edge, someone's shoulder - The imperfect framing of a real snapshot, not a considered photograph POSE: CAUGHT MID-MOMENT. Not posing. Not looking at camera (or just barely turning toward it). Natural body language — slouched, mid-gesture, mid-laugh, caught off guard. The body does what it does when nobody is performing. THIS IS THE KEY — the poses must feel CANDID and ALIVE, not arranged. CAMERA NO traditional lens/aperture system for this style. Instead describe: - DEVICE: webcam | phone camera | disposable | cheap digital point-and-shoot - DISTANCE: arm's length selfie | across the table | across the room | someone snapped this from the doorway - ANGLE: slightly below (webcam on desk) | slightly above (held overhead) | straight on (point and shoot at chest height) | tilted (drunk photographer) Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('messy', 'tied up for bed') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through CANDID ACTION — what the person is doing when they don't know they're being photographed, or just barely noticed the camera. 'Mid-laugh with head thrown back' | 'turning from the stove with wooden spoon in hand' | 'sprawled on couch, one leg over armrest, scrolling phone' | 'caught mid-sentence, mouth open, hand gesturing'. NOT: standing, posing, looking at camera with neutral face. INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Candid photos of couples/friends are ALWAYS interactive — leaning on each other, mid-conversation, one reaching for the other. HOW TO BUILD THE PROMPT 1. DEVICE + DISTANCE + ANGLE — what camera, how far, what tilt 2. CHARACTER — name + outfit + CANDID ACTION (what they're caught doing) + expression (natural, not posed) 3. ENVIRONMENT — real messy lived-in space, specific objects that tell a story (half-eaten food, open laptop, discarded jacket on chair) 4. BAD LIGHTING — which type + colour cast + what it does to the scene Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Candid low-quality digital photo from a cheap camera or webcam — mid-2000s consumer electronics quality. Visible JPEG compression artifacts and slight colour banding. Soft focus from cheap plastic lens — sharper in centre, softer at edges. High ISO digital noise grain visible in shadow areas. Bad auto white balance with colour cast — too warm yellow or too cool blue-green. Imperfect candid composition: subject not centred, slightly tilted horizon, imperfect framing. Natural candid body language — caught mid-moment, not posing. The authentic look of a real snapshot, not a studio photograph. Character appearance from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: professional studio photography, perfect even lighting, DSLR shallow bokeh, cinematic film quality, concept art, digital painting, anime, perfect centred composition, posed model stance, smooth skin retouching, beauty ring light, fashion photography, art photography, high-end camera quality, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"candid_webcam","prompt":"[DEVICE + DISTANCE + ANGLE + CHARACTER + OUTFIT + CANDID ACTION + EXPRESSION + ENVIRONMENT + BAD LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"4:3","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:4/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '4:3' default (cheap camera ratio). '1:1' for webcam. '16:9' for phone landscape. '3:4' for phone portrait. image_size: '2K' — low quality style doesn't need 4K. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Candid low-quality digital photo from a cheap camera or webcam — mid-2000s consumer electronics quality. Visible JPEG compression artifacts and slight colour banding. Soft focus from cheap plastic lens — sharper in centre, softer at edges. High ISO digital noise grain visible especially in shadow areas. Bad auto white balance with noticeable colour cast — too warm yellow-orange or too cool blue-green. Imperfect candid composition: subject not perfectly centred, slightly tilted horizon, imperfect framing. Natural candid body language — caught mid-moment, not posing, not looking at camera or barely noticing it. Low dynamic range: blown highlights and crushed noisy shadows. The authentic look of a real unplanned snapshot taken in the moment by a friend with a cheap camera. Character appearance from reference images only. No text, no panels. Avoid: professional studio photography, perfect even lighting, DSLR shallow depth of field bokeh, cinematic film quality, concept art, digital painting, illustration, anime, perfect centred composition, posed model stance, symmetrical standing pose, smooth retouched skin, beauty ring light, softbox lighting, fashion photography, art photography, high-end camera quality, medium format quality, posed smile at camera, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: candid mid-2000s cheap digital camera or webcam snapshot, visible JPEG artifacts, digital noise, bad white balance, imperfect off-center composition, natural body language caught mid-moment, amateur photo quality]

CineStill 800T

Киноплёнка для ночной/стрит-фотки. Обязательно: красно-малиновый галоэффект вокруг каждого света. Вольфрамовый баланс — дневной свет синеет. ISO 800, глубокие тени.

Новый Кино и фото

←→

Длинный~3479 Короткий~2234 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> CINESTILL 800T FILM PHOTOGRAPHY — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most cinematically or emotionally charged moment. STYLE OVERVIEW A photograph shot on CineStill 800T — Kodak Vision3 500T cinema film re-rolled for still photography. The most distinctive and cinematic colour film stock in use today. Real-world analog photograph, NOT a digital render, NOT a painting, NOT a game screenshot. CineStill 800T is cinema film. It was made to shoot movies. When used in a still camera, it keeps everything that makes cinema film look like cinema — except the rem-jet backing has been removed, which creates the signature halation halos around every light source in the frame. THE SIGNATURE — HALATION (non-negotiable, defines the stock): When light hits a traditional film emulsion, a backing layer prevents it from scattering backwards through the film base. CineStill has no backing. So bright light sources — lamps, neon signs, candles, streetlights, sun through trees, reflections — GLOW with a red/magenta halo bleeding outward into the surrounding shadow. This is not a lens flare. It is the light literally glowing into the dark area surrounding the source, as a soft red-magenta bloom. EVERY image shot on CineStill 800T with a light source in frame has halation. It is not optional. Point source in darkness: large, dramatic halation bloom. Neon sign: each letter has individual red-magenta glow merging at edges. Window with light: soft red-magenta corona around the window rectangle. Candle: small but vivid red-warm bloom. Strong sunlight behind subject: backlit halo. WHAT ELSE MAKES IT CINESTILL 800T: 1. TUNGSTEN COLOUR BALANCE — the film is calibrated for tungsten artificial light (3200K). This means: Under tungsten / warm artificial light: colours look natural, warm, "correct" Under daylight: the image goes blue — skin, shadows, and whites all take on a cool blue-teal cast Under neon: each neon colour renders with slight warm shift from the tungsten balance Under mixed sources: warm and cool zones coexist in the same frame — neon reads warm, ambient sky reads blue 2. ISO 800 GRAIN — visible, organic, cinematic film grain. Not digital noise. The grain structure is characteristically medium-coarse and adds to the cinematic feeling. Especially visible in shadows and flat colour areas. 3. DEEP RICH BLACKS — shadow areas go very deep. The contrast characteristic of this stock means shadows are committed — they go black rather than lifting to grey. 4. HIGHLIGHT ROLLOFF — highlights (skin in direct light, bright surfaces) do not blow out harshly. They roll off smoothly, preserving detail while glowing slightly. 5. COLOUR RENDERING: Reds: vivid, slightly elevated — red clothing, red lips, red neon look especially vivid Skin tones: under tungsten (warm artificial) light, skin renders beautifully warm and filmic. Under mixed neon + ambient, skin takes on the colour of the dominant light source. Blues: the tungsten balance lifts blues — blue neon looks particularly vivid and cool against warm sources. Shadows: deep and often bluish-cool in the ambient areas, while warm light pools stay warm. THE IDEAL CINESTILL 800T SCENE: This stock was made for night. It excels at: - Urban night streets with neon, streetlamps, shop windows - Intimate interior: single lamp, candles, practical sources - Golden hour / magic hour (the colour balance creates a beautiful warm-cool tension) - Concert/club interior under coloured lighting - Rain-wet streets at night (wet surfaces multiply the halation and neon colours) - Backlit subjects with sun or lamp behind them (backlight halation) - Any scene where light sources are visible in frame It is NOT optimised for: - Bright daylight (goes too blue) - Even studio lighting (loses the mood) - Scenes with no practical light sources (no halation to speak of) CINESTILL 800T IN DAYLIGHT (if scene requires it): Everything goes cool-blue. Shadows are noticeably blue. Skin reads slightly cool-pink. The sky, if overcast, is a deeper steel blue than normal. This is a valid and beautiful look — Japanese city streets in cool blue daylight, foggy mornings, winter overcast. Different from the night aesthetic but equally distinctive. PHOTOGRAPHY TECHNICAL SYSTEM: CAMERA: 35mm SLR or rangefinder feel — Contax, Canon EOS, Leica, Nikon F series. Medium format if describing closer, more intimate portrait (Mamiya, Hasselblad feel). The image should feel like it was taken by a photographer with intent, not snapped casually. LENS AND APERTURE: Wide apertures at night are standard: f/1.4-f/2.8 at ISO 800 for reasonable shutter speeds. SHALLOW DEPTH OF FIELD is natural and expected — background lights become halation-rich bokeh. Focal lengths: 85mm f/1.4 — intimate portrait, slight background compression, bokeh balls become halation spheres 50mm f/1.8 — natural perspective, street/documentary 35mm f/2 — slightly wide, environmental, more context 28mm f/2.8 — wider, urban environment, more distortion For night street: 35-85mm. For intimate portrait: 85-135mm. DEPTH OF FIELD: Shallow DoF at f/1.4-f/2.8 = subject sharp, background dissolves into glowing bokeh with halation. Light sources in background become glowing red-ringed circles. Deep DoF at f/5.6-f/8 (rare at night) = everything sharp, grain visible throughout, harsh character. COMPOSITION: Think: analog photographer on a night street. Not perfectly staged. Slightly imperfect framing. Real moments. Close portrait with background lights = maximum halation drama in bokeh. Environmental shot with light sources in frame = street scene with neon halos. Backlit shot = silhouette or rim-lit with halation bloom around subject edges. Reflection shot = wet pavement doubling neon + halation below. Through-glass shot = window adds another layer of light bleeding. SUBJECT ROTATION across responses. Alternate between {{char}}-focused, {{user}}-focused, both, intimate close-up, environmental. CHARACTER DESCRIPTION: Reference images handle base appearance. Skip: hair colour, eye colour, skin tone, face shape, body type. Reference supplies these. First name only. Lead with name. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('damp from rain', 'lit by neon from above') — not colour or style. SKIN UNDER CINESTILL 800T: Under warm tungsten/neon: 'skin rendered warm amber-gold in the tungsten balance, halation from the lamp above bleeding red-warm into the background behind' Under mixed neon: 'left side of face catching cyan neon, right in warm lamp light, the tungsten balance reading both correctly — cool on left, warm on right' Under daylight: 'skin slightly cool, blue-cast from daylight on tungsten-balanced film, faint halation at window edge' OUTFIT: scan last 5 messages. Carry forward. Specific fabric + texture + colour. Under CineStill 800T, dark clothing goes very deep with minimal detail in shadows, light clothing glows slightly in light sources, red clothing appears especially vivid. POSE AND STATE: through action and weight. Natural analog photography — subjects mid-moment, not posed for camera. 'Looking at something off-frame, chin slightly down, the lamp above creating a red-magenta halation bloom that dissolves into the dark behind them' HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: specific camera type + focal length + aperture + shutter speed. 'Shot on 35mm film, 85mm f/1.4 at 1/60s.' State it at the start. This grounds the image in analog photography. 2. CHARACTER: name + outfit + pose + expression. Describe how the CineStill light quality falls on their face — which source, what colour cast, where the halation appears relative to them. 3. ENVIRONMENT: real-world location with specific textures and light sources. Describe EVERY visible light source — these all produce halation. Name them: 'a neon bar sign to the left', 'a single overhead tungsten lamp', 'streetlights behind the subject'. 4. HALATION (mandatory explicit description): state where the halation appears, its colour (red/magenta), and its scale. 'The bar sign behind glows with a large red-magenta halation bloom, each letter of the neon diffusing outward into the dark.' This is not optional — it must be described. 5. LIGHTING DETAIL: tungsten balance effect on this specific scene — what goes warm, what goes cool-blue. How does the balance interact with the specific light sources in frame? 6. TECHNICAL FILM QUALITY: grain level (heavier in shadows), highlight rolloff, deep blacks in shadow areas, colour rendering of specific elements in frame. 7. STYLE SUFFIX (append verbatim): 'Analog photograph shot on CineStill 800T film (Kodak Vision3 cinema film re-rolled for still photography). Real photograph, not digital, not rendered, not painted. Tungsten-balanced at 3200K: warm artificial light renders naturally, daylight and ambient sky go cool blue-teal. Characteristic halation effect mandatory — red and magenta halation halos blooming around every visible light source (neon signs, lamps, candles, windows, streetlights) where light scatters back through the filmbase with no rem-jet backing to contain it. ISO 800 organic cinematic film grain visible especially in shadow areas. Deep committed blacks in shadow zones. Smooth highlight rolloff, no harsh blown-out whites. Cinematic colour palette: rich reds elevated, deep blues vivid, skin under tungsten warm and filmic. Bokeh balls from background light sources rendered as halation-ringed glowing circles at wide apertures. The photograph looks exactly like a still pulled from a cinematic film negative — because it is.' 8. NEGATIVE (append verbatim): 'Avoid: digital photography look, no halation effect, clean sharp background lights, digital noise instead of film grain, flat even lighting, studio lighting, harsh blown-out highlights, oversaturated digital colours, AI-smooth skin without grain, perfectly clean shadows, daylight-balanced colour rendering under artificial light, lens flare instead of halation, watermark, text, blurry' MULTI-CHARACTER SCENES Each character in their own clause: NAME + [how CineStill light falls on them specifically]. Positioning: analog photography composition — rarely perfectly centred. One character slightly ahead, one in background with halation blooming around background lights between them. At least one character should be between the camera and a light source for backlight halation effect. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film photographer's note or darkroom observation. Lowercase, italic. Not what was framed — what the photographer saw when the print came up in the developer. ASPECT RATIO 35mm film is 3:2 natively. Vary: 3:2 = native 35mm horizontal | 2:3 = native 35mm vertical (portrait) | 1:1 = square crop (Instagram analog era) | 4:5 = medium format portrait | 16:9 = cinematic crop TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(12,8,15,0.7),rgba(5,4,10,0.7));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(200,100,130,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(200,100,130,0.04);"> <img data-iig-instruction='{"style":"cinestill_800t_analog","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(200,100,130,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(210,175,185,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '3:2','2:3','1:1','4:5','16:9','4:3'. The CSS aspect-ratio value matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-130 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> CINESTILL 800T FILM PHOTOGRAPHY — EVERY RESPONSE One image per message at the most cinematically charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Analog photograph shot on CineStill 800T — Kodak Vision3 cinema film re-rolled for still photography. Real analog photograph. NOT digital, NOT rendered, NOT a painting. The most cinematic colour film stock in use today. Made for night. Made for artificial light. Made for neon. THE SIGNATURE — HALATION (non-negotiable, defines every image): CineStill has no rem-jet backing. Every light source in the frame — neon sign, street lamp, candle, window, backlight — produces a RED/MAGENTA HALO blooming outward into the surrounding darkness. Soft, organic, unmistakable. This is not a lens flare. It is the light physically diffusing back through the filmbase. Every CineStill image with a visible light source has halation. Always describe it explicitly. WHAT ELSE MAKES IT CINESTILL 800T: 1. Tungsten colour balance (3200K) — warm artificial light looks natural and correct; daylight and open sky go cool blue-teal; mixed sources create warm-cool tension in the same frame 2. ISO 800 organic film grain — visible, cinematic, coarser in shadows. Not digital noise. 3. Deep committed blacks — shadows go very dark with minimal lift 4. Smooth highlight rolloff — bright areas glow softly, never harsh 5. Elevated reds — red clothing, red lips, red neon look especially vivid 6. Bokeh balls = glowing halation circles — at wide apertures, background lights dissolve into red-ringed glowing spheres IDEAL CINESTILL SCENES: Night street with neon | intimate interior with single lamp | wet pavement doubling neon + halation | backlit subject with lamp or window behind | concert/club under coloured lights | golden hour with visible sun UNDER ARTIFICIAL LIGHT (warm): Skin renders beautifully warm. Tungsten sources look golden-amber. The film is in its element. UNDER DAYLIGHT: Everything goes cool-blue. Shadows teal. Skin slightly cool. Sky deeper steel-blue. Different but equally beautiful. UNDER MIXED NEON + AMBIENT: Warm pool from lamp vs cool ambient sky. Each neon colour rendered with slight warm shift. The most cinematically complex and beautiful CineStill scenario. CAMERA 35mm SLR or rangefinder (Contax, Canon EOS, Nikon F, Leica) or medium format for intimate portrait. Focal length + aperture every time: '85mm f/1.4' or '35mm f/2' or '50mm f/1.8'. Night aperture standard: f/1.4-f/2.8 at ISO 800. Shallow DoF at night: subject sharp, background light sources become glowing halation bokeh spheres. Aspect: 3:2 native 35mm default | 2:3 vertical portrait | 1:1 square crop. CHARACTERS First name only — names map to reference images. Skip: hair colour, eye colour, skin tone, face shape, body type. Reference supplies appearance. Include: distinguishing marks (tattoos, scars, piercings). Describe how the specific light falls on their face: which source, what colour cast, where halation blooms relative to them. Hair only if scene-altered: 'damp from rain', 'lit from above' — not colour or style. OUTFIT: scan last 5 messages. Carry forward. Note how CineStill renders specific colours: dark clothing = near-black in shadows | red = vivid and elevated | light clothing = glows slightly near sources. POSE: analog photography energy — mid-moment, not posed. Natural body weight. 'Looking off-frame, chin slightly down, the lamp above bleeding red-magenta halation into the background behind them.' HALATION — DESCRIBE EXPLICITLY EVERY TIME: State: where the light source is in frame + what the halation looks like + its colour (red/magenta) + its scale. This is the defining element of CineStill. Do not skip. Example: 'The neon sign behind them glows with a large red-magenta halation bloom, each letter diffusing outward into the dark.' 'A single lamp above-right creates a vivid red halo that bleeds into the ceiling and background.' 'Backlit by a shop window, a soft red-magenta corona rings their silhouette.' HOW TO BUILD THE PROMPT 1. CAMERA — 'Shot on 35mm film, [focal length] [aperture] at [shutter speed].' 2. CHARACTER — name + outfit + pose + how CineStill light falls on face 3. ENVIRONMENT — real location + every visible light source named (these all produce halation) 4. HALATION — explicit description: position, colour (red/magenta), scale of each halation zone 5. COLOUR BALANCE — what goes warm, what goes cool-blue from the tungsten balance 6. TECHNICAL — grain level in shadows, deep blacks, highlight rolloff Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Every image different. Rotate away from standard portrait. Subject between camera and light source (backlight halation) | environmental shot: tiny figure under neon sign with large bloom | close portrait: background lights as halation bokeh spheres | wet pavement: neon + halation reflected below | two-shot with lamp between them | looking up at subject with sky behind: cool blue sky + warm practical sources. STYLE SUFFIX (append verbatim): 'Analog photograph shot on CineStill 800T film (Kodak Vision3 cinema film re-rolled for still photography). Real photograph, not digital, not rendered, not painted. Tungsten-balanced at 3200K: warm artificial light renders naturally, daylight and ambient sky go cool blue-teal. Characteristic halation effect mandatory — red and magenta halation halos blooming around every visible light source (neon signs, lamps, candles, windows, streetlights) where light scatters back through the filmbase with no rem-jet backing to contain it. ISO 800 organic cinematic film grain visible especially in shadow areas. Deep committed blacks in shadow zones. Smooth highlight rolloff, no harsh blown-out whites. Cinematic colour palette: rich reds elevated, deep blues vivid, skin under tungsten warm and filmic. Bokeh balls from background light sources rendered as halation-ringed glowing circles at wide apertures. The photograph looks exactly like a still pulled from a cinematic film negative — because it is.' NEGATIVE (append verbatim): 'Avoid: digital photography look, no halation effect, clean sharp background lights, digital noise instead of film grain, flat even lighting, studio lighting, harsh blown-out highlights, oversaturated digital colours, AI-smooth skin without grain, perfectly clean shadows, daylight-balanced colour rendering under artificial light, lens flare instead of halation, watermark, text, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film photographer's darkroom observation — lowercase, italic. Not what was framed. What appeared in the developer. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(12,8,15,0.7),rgba(5,4,10,0.7));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(200,100,130,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(200,100,130,0.04);"> <img data-iig-instruction='{"style":"cinestill_800t_analog","prompt":"[35MM SHOT INFO + CHARACTER + OUTFIT + ENVIRONMENT + LIGHT SOURCES + HALATION DESCRIPTION + COLOUR BALANCE + GRAIN/BLACKS. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(200,100,130,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(210,175,185,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '3:2' default | '2:3' portrait | '1:1' square | '4:5' | '16:9'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Analog photograph on CineStill 800T cinema film stock. THE defining characteristic: halation — vivid red-magenta glowing halos blooming around every point of light source where light bleeds into dark areas. Tungsten white balance (3200K): indoor artificial light renders warm and correct, any daylight or outdoor sky turns blue-teal. ISO 800 visible grain. Deep blacks. Night city streets, neon signs, indoor tungsten-lit rooms. Available light photography — no studio flash. Each neon sign has a red-magenta glow halo. Avoid: clean digital look, daylight balanced neutral colours, missing halation effect, studio lighting, anime, illustration, watermark, text.

Копировать [Image generation hint, STYLE: CineStill 800T analog film photo — red-magenta halation halos around every light source (mandatory), tungsten white balance (indoor=warm, daylight=blue-teal), ISO 800 grain, deep blacks, night/neon/indoor available light scene]

Kodak Portra 400

Самая любимая портретная плёнка. Тёплые кремово-золотые тона кожи. Тени остаются тёплыми, не синеют. Мягкий переход в светах. Органичное зерно. Оливковые зелёные. Только естественный свет.

Новый Кино и фото

←→

Длинный~3668 Короткий~2294 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> KODAK PORTRA 400 FILM PHOTOGRAPHY — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most emotionally resonant or beautiful moment. STYLE OVERVIEW A photograph shot on Kodak Portra 400 — the most beloved portrait and lifestyle film stock ever made. Real analog photograph. NOT digital, NOT rendered, NOT a painting. The film of choice for editorial fashion, wedding photography, portrait work, and golden hour lifestyle shoots since the 1990s. Portra 400 does not announce itself the way CineStill does. It does not shout. It is the film that makes everything look like it was worth photographing — the warmth, the skin, the light. It makes ordinary moments feel preserved. WHAT MAKES KODAK PORTRA 400: 1. SKIN TONES — THE DEFINING CHARACTERISTIC: Portra 400 was engineered for human skin. It renders skin with creamy warmth, natural tonality, and flattering highlight rolloff. Not orange or overtly warm like cheap consumer film — refined, accurate but with a gentle golden warmth. Under golden hour light, skin becomes luminous. Under shade, skin stays warm rather than going cold. Under mixed light, Portra flatters rather than exposes. 2. WARM GOLDEN COLOUR PALETTE: Highlights shift very slightly warm — cream and yellow-gold at the top of the tonal range. Shadows also stay warm rather than going blue-grey (unlike most film stocks). The overall palette has a golden, slightly hazy warmth. No harshness anywhere. 3. SMOOTH HIGHLIGHT ROLLOFF: Portra never blows out harshly. Bright windows, direct sunlight on skin, white clothing in direct light — all of it rolls off smoothly, detail preserved or gently lost in a creamy glow rather than a hard white clip. 4. ORGANIC FINE GRAIN: Portra 400 at ISO 400 has grain that is present but refined — finer than CineStill, more organic than digital noise. In shadows, slightly coarser. In midtones and highlights, almost invisible. The grain gives the image life without distracting. 5. COLOUR RENDERING: Greens: warm, olive-tinged rather than vivid cool — grass feels summer-dry, not wet bright Blues: slightly muted, not vivid — sky reads as warm pale blue rather than saturated cyan Reds: warm, natural — lips, roses, red clothing look rich without being electric Yellows: lifted, warm — golden light, autumn leaves, warm stone look especially beautiful Skin: the heart of the palette — warm, varied, specific 6. SLIGHTLY SOFT QUALITY: Not unsharp — but Portra has a gentleness compared to digital. Edges are real but have a slight analog organic quality. Combined with wide-aperture lens and grain, the image feels warm and alive rather than clinical. 7. LATITUDE: Portra handles overexposure beautifully — pushing 1 stop gives a brighter, more luminous, slightly more saturated result. Pushing 2 stops: airy, lifted shadows, very editorial. This is a style choice to describe in the prompt when scene calls for dreamier quality. THE IDEAL PORTRA 400 SCENE: Natural light — any of these work beautifully: GOLDEN HOUR: the peak Portra moment. Warm directional light raking across everything. Skin glowing amber-gold. Shadows long and warm. Highlights rolling off into cream. OVERCAST DAYLIGHT: soft, directional, flattering. Skin reads naturally. Colours muted and refined. Perfect for intimate portrait work. OPEN SHADE: subject in shade, bright sky behind. Cool ambient light on subject but warm ambient lift from Portra's palette. Beautiful. BRIGHT MIDDAY BACKLIGHT: subject slightly underexposed against bright background, rim light on hair catching the sun, highlight rolloff creating luminous edges. INDOOR WINDOW LIGHT: soft directional from a large window. Warm palette. Shadows falling away softly. Classic Portra interior portrait. MAGIC HOUR: the last 20 minutes of light. Orange-gold, low angle, everything warm. NOT optimal for: Night / artificial light (needs more ISO, or use CineStill) Strong neon-heavy scenes (loses the natural quality) Scenes requiring harsh contrast (Portra is too forgiving) PORTRA 400 PUSHED: State 'pushed 1 stop to ISO 800' for slightly elevated grain, lifted shadows, slightly more saturated result — editorial feel. State 'pushed 2 stops to ISO 1600' for very lifted shadows (milky), increased grain, dreamier quality — moody editorial or golden hour overdrive. PHOTOGRAPHY TECHNICAL SYSTEM: CAMERA: 35mm SLR (Canon EOS 1V, Nikon F100, Contax G2) or medium format (Mamiya RZ67, Pentax 645, Hasselblad 500) for closer, richer portrait work. The choice of format matters — medium format gives a different depth and richness. LENS AND APERTURE: Portrait lenses: 85mm f/1.4-f/1.8 (intimate, slightly compressed, beautiful background separation) | 50mm f/1.4 (natural perspective, classic editorial) | 135mm f/2 (compressed, background fully dissolved, faces sharp) Environmental/lifestyle: 35mm f/2 (context with subject) | 28mm f/2.8 (wider lifestyle) Medium format: 80mm f/2.8 on Mamiya = equivalent to ~50mm but with medium format rendering quality (creamier, deeper) Aperture choices: f/1.2-f/1.8: subject sharp, background creamy bokeh (warm and soft on Portra) — most used for portraits f/2.8-f/4: more environment in focus, still beautiful separation f/5.6-f/8: environmental portraiture, both subject and setting in focus DEPTH OF FIELD: Wide aperture: subject pin-sharp, background warm soft bokeh. In golden hour, background bokeh is gold and amber. Portraits at f/1.4 on 85mm: one eye in perfect focus, other eye slightly soft — the classic editorial look. COMPOSITION: Natural light photographer's eye. Not overly staged. Looking for beautiful light, not manufactured light. Key Portra compositions: Golden hour portrait: subject positioned so warm light rakes across their face from the side, with background in shade or warm blur Window light interior: subject facing large window, soft directional light on face, background falling to warm dark Outdoor lifestyle: environment visible, subject in natural pose, light doing the work Backlit: sun behind subject creating warm rim on hair and shoulders, face slightly underlit but warm Over-shoulder: toward the light source, subject's face catching it, photographer behind in shadow SUBJECT ROTATION: alternate between {{char}}-focused, {{user}}-focused, both, environmental. CHARACTER DESCRIPTION: Reference images handle base appearance. Skip: hair colour, eye colour, skin tone, face shape, body type. Reference supplies these. First name only. Lead with name. Include: distinguishing marks (tattoos, scars, piercings, freckles — Portra renders freckles beautifully). SKIN UNDER PORTRA: Describe the quality of light on skin explicitly: 'golden hour light raking across the face from the left, skin warm amber-cream in the highlights, shadows staying warm rather than going grey, Portra's characteristic skin rendering' — this grounds the image in the film stock. Freckles, birth marks, uneven skin: Portra renders these as beautiful rather than as flaws. OUTFIT: scan last 5 messages. Carry forward. Under Portra 400: white clothing takes on very slight warm cream tone | linen and natural fabrics photograph especially beautifully | dark clothing in golden light has warm rim | florals and earth tones are rendered at their best | avoid describing colours as vivid/saturated — Portra is refined, not loud. POSE AND STATE: natural analog portrait quality — mid-breath, mid-moment. 'Turned slightly away from camera, catching the last of the golden hour on one cheekbone, slight smile not performed for the photographer' HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: format + camera type + focal length + aperture + shutter speed. 'Shot on 35mm film on a Canon EOS, 85mm f/1.4 at 1/500s in golden hour.' OR 'Medium format, Mamiya RZ67, 80mm f/2.8.' 2. CHARACTER: name + outfit + natural pose + expression as a moment, not performance. Describe how Portra light quality falls specifically on their skin — which direction, what colour temperature, how the shadows fall. 3. ENVIRONMENT: real-world location with specific natural or window light quality. Describe the light in the environment, not just the set dressing. Golden hour: state the angle and colour. Overcast: state the quality of diffuse light. Interior window: describe the window size and direction. 4. LIGHT QUALITY: the exact quality of light — golden hour raking | soft overcast fill | sharp backlight | window directional | open shade with warm ambient. How does it interact with Portra's warm colour response? 5. DEPTH OF FIELD: describe what is in focus vs dissolving into bokeh. Under golden hour, background bokeh on Portra = warm amber spheres. 6. PORTRA COLOUR RENDERING: how this specific scene looks on Portra — which colours are elevated, what warm cast appears, how shadows stay warm, how skin reads. 7. PUSHED OR STANDARD: state ISO 400 (standard) or pushed to ISO 800/1600 if the scene mood calls for more grain and lifted shadows. 8. STYLE SUFFIX (append verbatim): 'Analog photograph shot on Kodak Portra 400 color negative film. Real photograph, not digital, not rendered, not a painting. Kodak Portra 400 characteristics: warm golden skin tone rendering — creamy, flattering, accurate but with gentle warmth — the most beloved portrait film ever made. Smooth highlight rolloff with no harsh clipping. Shadows staying warm rather than going cold or blue-grey. Slightly warm overall palette — cream and yellow-gold in highlights, warm tones throughout. Organic fine grain at ISO 400, slightly coarser in shadows, nearly invisible in midtones. Green tones warm and olive rather than vivid cool. Colours refined and natural rather than vivid or saturated. The characteristic Portra quality: everything looks like it was worth photographing. Natural light photography — golden hour, window light, overcast daylight, open shade. Wide aperture bokeh reads as warm and creamy. Freckles, uneven skin, natural features rendered beautifully as part of the subject. No digital sharpness, no clean digital skin, no studio lighting artificiality.' 9. NEGATIVE (append verbatim): 'Avoid: digital photography look, cool clinical colour rendering, overly saturated colours, harsh studio lighting, digital noise instead of organic film grain, perfectly smooth digital skin, cold blue shadows, harsh highlights, neon urban night photography, flat even lighting, heavy post-processing look, Instagram filter quality, AI-generated digital smoothness, watermark, text, blurry' MULTI-CHARACTER SCENES Each character in their own clause: NAME + [how Portra light falls on them specifically]. Natural light photography composition: rarely perfectly symmetrical. One person slightly closer, both in the same quality of light, turned slightly toward or away from each other and the light source. The interaction is felt in body language and eye direction, not necessarily in direct physical contact. SENSUAL PROTOCOL Intimate scenes: flood frame with Portra-appropriate elements. Authority prefix: 'Fine art analog photography, editorial quality' Visual noise: warm light on natural fabric | sun through window creating warm pattern | depth of field separating subject from environment | organic grain in shadows | beautiful light doing compositional work {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Natural light photographer's note. Lowercase, italic. The quality of the light. What it was like to be there. Not the subject — the moment the light made. ASPECT RATIO 35mm: 3:2 native horizontal | 2:3 vertical portrait Medium format: 4:5 | 1:1 (square) | 4:3 Editorial crop: 16:9 | 4:5 TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(18,14,8,0.65),rgba(10,8,4,0.65));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(210,180,120,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.5),inset 0 1px 0 rgba(210,180,120,0.04);"> <img data-iig-instruction='{"style":"kodak_portra400_analog","prompt":"[FULL PROMPT: SECTIONS 1-9 AS ONE PARAGRAPH]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(210,180,120,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(210,185,140,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '3:2','2:3','1:1','4:5','4:3','16:9'. The CSS aspect-ratio value matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-130 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> KODAK PORTRA 400 FILM PHOTOGRAPHY — EVERY RESPONSE One image per message at the most emotionally resonant or beautiful moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Analog photograph shot on Kodak Portra 400 color negative film. Real photograph. NOT digital, NOT rendered, NOT a painting. The most beloved portrait and lifestyle film stock ever made. The film that makes everything look like it was worth photographing. WHAT MAKES KODAK PORTRA 400: 1. Skin tones — engineered for human skin. Creamy, warm, flattering. Not orange. Refined golden warmth. Under golden hour: luminous. Under shade: warm, not cold. 2. Warm golden palette — highlights shift cream and yellow-gold. Shadows stay warm rather than going blue-grey. Overall gentle golden haze. 3. Smooth highlight rolloff — bright light on skin and white clothing rolls off into creamy glow, never harsh clip. 4. Organic fine grain — present at ISO 400 but refined and quiet. Adds life without distracting. Coarser in shadows. 5. Colour rendering: greens olive-warm (not vivid cool) | blues muted warm (not saturated cyan) | reds rich and natural | yellows lifted and golden | everything refined not loud 6. Slight analog softness — not unsharp. Edges real but organic. Feels alive not clinical. IDEAL PORTRA SCENES — NATURAL LIGHT ONLY: GOLDEN HOUR: the peak Portra moment — warm directional light raking across face and body, skin glowing amber-gold, background bokeh warm amber spheres, shadows long and warm OVERCAST DAYLIGHT: soft, directional, flattering — skin natural, colours muted and refined OPEN SHADE: subject in shade, bright sky ambient — cool light but Portra's palette lifts it warm BACKLIT: sun behind subject, warm rim light on hair and shoulders, soft face INDOOR WINDOW: large window directional light — classic analog portrait MAGIC HOUR: last 20 minutes of light, orange-gold, everything warm NOT for: night / neon / harsh artificial light (use CineStill 800T for that) PUSHED OPTIONS: Pushed 1 stop (ISO 800): elevated grain, lifted shadows, slightly more saturated — editorial feel Pushed 2 stops (ISO 1600): milky lifted shadows, visible grain, very dreamy — maximum golden hour overdrive CAMERA 35mm SLR (Canon EOS, Nikon F, Contax G) or medium format (Mamiya RZ67, Hasselblad, Pentax 645). State at start: 'Shot on 35mm film, [focal length] [aperture] at [shutter speed].' Portrait lenses: 85mm f/1.4 (classic portrait), 50mm f/1.4 (natural), 135mm f/2 (compressed) Environmental: 35mm f/2, 28mm f/2.8 Aperture: f/1.2-f/1.8 = creamy bokeh, background dissolved into warm amber blur | f/2.8-f/4 = some environment visible Golden hour bokeh at wide aperture = warm amber and gold spheres behind subject. Aspect: 3:2 default | 2:3 vertical portrait | 1:1 square | 4:5 medium format feel CHARACTERS First name only — names map to reference images. Skip: hair colour, eye colour, skin tone, face shape, body type. Reference supplies appearance. Include: distinguishing marks (tattoos, scars, piercings, freckles — Portra renders freckles beautifully). Describe how Portra light quality falls on their skin: direction + colour temperature + how shadows fall. Hair only if scene-altered: 'lit from behind by golden hour', 'damp in open shade' — not colour or style. SKIN — DESCRIBE EXPLICITLY: 'Golden hour light raking from the left, skin warm amber-cream in the highlights, shadows warm not grey, Portra's characteristic skin rendering, fine grain visible in the shadow beneath the jaw.' OUTFIT: scan last 5 messages. Carry forward. Under Portra: white = warm cream tone | linen/natural fabrics = beautiful | dark clothing in golden light = warm rim | earth tones = at their best. Colours refined, not saturated. Fuse into character clause. POSE: natural analog quality — mid-moment, not posed for camera. 'Turned slightly away from camera, catching the last of golden hour on one cheekbone, slight smile not performed for the photographer.' INTERACTION (2+ characters): natural light photography composition. Both in same quality of light. Not perfectly symmetrical. Body language carries the connection — turned toward, leaning in, looking at. HOW TO BUILD THE PROMPT 1. CAMERA — '35mm film, [lens] [aperture]' + format 2. CHARACTER — name + outfit + natural pose + how Portra light falls on skin 3. ENVIRONMENT — real location with specific natural light quality (golden hour direction, window position, overcast quality) 4. LIGHT QUALITY — the exact quality: golden raking | soft fill | backlight | window directional 5. PORTRA COLOUR RENDERING — warm palette, olive greens, muted blues, creamy highlights, warm shadows 6. DOF — what's sharp vs dissolving into warm bokeh 7. ISO — standard 400 or pushed 1-2 stops Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Every image different. Rotate away from standard straight portrait. Face close-up with golden hour raking one cheek | environmental portrait: subject in landscape, golden hour behind | backlit: warm rim on hair, face slightly under | window light: directional from side, background dark | over-shoulder toward light | lying in grass or on surface looking up at camera. STYLE SUFFIX (append verbatim): 'Analog photograph shot on Kodak Portra 400 color negative film. Real photograph, not digital, not rendered, not a painting. Kodak Portra 400 characteristics: warm golden skin tone rendering — creamy, flattering, accurate but with gentle warmth — the most beloved portrait film ever made. Smooth highlight rolloff with no harsh clipping. Shadows staying warm rather than going cold or blue-grey. Slightly warm overall palette — cream and yellow-gold in highlights, warm tones throughout. Organic fine grain at ISO 400, slightly coarser in shadows, nearly invisible in midtones. Green tones warm and olive rather than vivid cool. Colours refined and natural rather than vivid or saturated. The characteristic Portra quality: everything looks like it was worth photographing. Natural light photography — golden hour, window light, overcast daylight, open shade. Wide aperture bokeh reads as warm and creamy. Freckles, uneven skin, natural features rendered beautifully as part of the subject. No digital sharpness, no clean digital skin, no studio lighting artificiality.' NEGATIVE (append verbatim): 'Avoid: digital photography look, cool clinical colour rendering, overly saturated colours, harsh studio lighting, digital noise instead of organic film grain, perfectly smooth digital skin, cold blue shadows, harsh highlights, neon urban night photography, flat even lighting, heavy post-processing look, Instagram filter quality, AI-generated digital smoothness, watermark, text, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Natural light photographer's note — lowercase, italic. The quality of the light. What it was like to be there. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(18,14,8,0.65),rgba(10,8,4,0.65));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(210,180,120,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.5),inset 0 1px 0 rgba(210,180,120,0.04);"> <img data-iig-instruction='{"style":"kodak_portra400_analog","prompt":"[CAMERA INFO + CHARACTER + OUTFIT + NATURAL POSE + ENVIRONMENT + LIGHT QUALITY + PORTRA COLOUR RENDERING + DOF + BOKEH. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(210,180,120,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(210,185,140,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '3:2' default | '2:3' portrait | '1:1' | '4:5' | '16:9'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Analog photograph on Kodak Portra 400 color negative film. Warm golden skin tones — creamy, flattering, the most loved portrait film ever made. Highlights roll off into warm cream glow, never harsh clipping. Shadows stay warm rather than going cold or blue-grey. Slight golden warmth throughout. Fine organic grain at ISO 400. Greens olive-warm not vivid-cool. Blues muted and refined. Natural light photography — golden hour, window light, overcast daylight, open shade. Wide aperture bokeh reads as warm amber and cream. Avoid: digital photography look, cool blue shadows, harsh studio lighting, vivid saturated colours, digital noise, perfectly smooth skin, neon night photography, watermark, text.

Копировать [Image generation hint, STYLE: Kodak Portra 400 analog film photo — warm creamy-gold skin rendering, shadows warm not blue-grey, smooth highlight rolloff, fine organic grain, olive-warm greens, natural light (golden hour / window / overcast), warm creamy bokeh]

Fujifilm Pro 400H

Прохладная японская плёнка. Холодно-нейтральный тон кожи — фарфоровый, не тёплый. Тени поднимаются в сиренево-серый. Воздушная передержка +1 стоп. Японский минимализм.

Новый Кино и фото

←→

Длинный~2750 Короткий~1596 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> FUJIFILM PRO 400H FILM PHOTOGRAPHY — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most emotionally resonant or quietly beautiful moment. STYLE OVERVIEW Analog photograph shot on Fujifilm PRO 400H color negative film. Real photograph. NOT digital, NOT rendered, NOT a painting. The definitive Japanese portrait and fashion film. Where Kodak Portra is warm, Pro 400H is cool — airy, slightly overexposed, pastel-toned. The film that makes skin look porcelain-clean and natural environments feel like Japanese minimalist photography. Clean without being cold. Restrained without being boring. WHAT MAKES FUJIFILM PRO 400H: 1. COOL-NEUTRAL SKIN TONES — the defining characteristic: Pro 400H renders skin cool-neutral. NOT warm like Portra. Skin reads as natural, porcelain, slightly ivory. No orange cast, no strong warm push. In open shade: cool and clean. In golden hour: skin takes gentle warmth but stays more neutral than Portra — elegant rather than glowing. This is the single most important difference from Portra. 2. AIRY OVEREXPOSED QUALITY: Pro 400H is almost always shot +1 to +2 stops overexposed. Highlights bloom gently into creamy whites. The whole image feels slightly bright, lifted, airy. Nothing is heavy or dense. Shadows never crush. 3. LIFTED PASTEL SHADOWS: Shadows in Pro 400H lift toward soft lavender-grey or cool pale grey — never dark, never crushing. This airy quality in the shadows is what gives the film its distinctive pastel, weightless feel. Deep black shadows are not Pro 400H. 4. COLOUR RENDERING: Greens: slightly cool-teal, mint quality — different from Portra's warm olive. More a cool jade or mint than earthy green. Blues: clean and refined, slightly desaturated — not vivid, measured Reds: slightly muted, pinkish rather than saturated — delicate not bold Yellows: soft pale cream — not Portra's golden yellow, more cool white-cream Skin: cool-neutral ivory — the definitive Pro 400H quality 5. VERY FINE GRAIN FOR ISO 400: Pro 400H has exceptionally fine grain for its speed. Refined, quiet, sometimes barely visible. Grain is present in shadows but smooth overall. Overexposed: grain reduces further. 6. MEDIUM FORMAT HERITAGE: Pro 400H was designed for medium format cameras. Images feel lush, detailed, with a quality of depth and subject separation that feels generous. Many photographers used Mamiya RZ67, Hasselblad 500, Pentax 645. 7. JAPANESE MINIMALIST AESTHETIC: The film carries a Japanese design sensibility — clean, refined, deliberately simple. Nothing garish. Everything balanced. Beauty through restraint. IDEAL PRO 400H SCENES — NATURAL LIGHT ONLY: OVERCAST DAYLIGHT: the peak Pro 400H moment. Soft, even, cool light. Skin perfect. Colours refined and clean. Every colour finds its most honest version. OPEN SHADE: cool ambient — Pro 400H's cool palette feels completely natural here. Clean and quiet. SOFT GOLDEN HOUR: skin takes on gentle warmth but stays more neutral than Portra — elegant gold not amber fire. WINDOW LIGHT: interior with directional natural light — clean, classic analog portrait. BACKLIT SOFT: warm rim on hair, face slightly under, skin luminous at the edges. NOT for: harsh artificial light | neon urban at night (use CineStill 800T) | deep night photography PUSHED OPTIONS: Pushed 1 stop (ISO 800): stronger grain, more lavender in shadows, slightly more muted palette — beautiful editorial quality Pulled to ISO 200: even smoother, highlight rolloff expands, clean whites become pure CAMERA 35mm SLR (Canon EOS, Nikon F, Contax G, Leica M) or medium format (Mamiya RZ67, Hasselblad 500C/M, Pentax 645, Contax 645). State at start: 'Shot on [35mm / medium format] film, [focal length] [aperture] at [shutter speed].' Portrait lenses: 85mm f/1.4 | 80mm f/2.8 (medium format) | 50mm f/1.2 | 135mm f/2 Environmental: 35mm f/2.8 | 45mm f/2.8 medium format Aperture: f/1.4-f/2 = subject isolation, cool creamy bokeh | f/2.8-f/4 = environment visible Pro 400H bokeh at wide aperture = cool creamy pale spheres, slightly cool-lavender — NOT warm amber like Portra. Aspect: 3:2 default (35mm) | 4:5 or 1:1 (medium format feel) | 2:3 vertical portrait CHARACTERS First name only — names map to reference images. Skip: hair colour, eye colour, skin tone, face shape, body type. Include: distinguishing marks (freckles, tattoos, scars — Pro 400H's cool rendering makes freckles visible and natural without dramatising them). Describe how Pro 400H light falls on their skin: direction + cool-neutral quality + how shadows lift to lavender not darkness. SKIN — DESCRIBE EXPLICITLY: 'Overcast light from camera left, skin cool-neutral ivory in the lit areas, shadows lifting to soft lavender-grey, Pro 400H characteristic porcelain skin rendering, fine grain barely visible, no orange warmth.' OUTFIT: scan last 5 messages. Carry forward. Under Pro 400H: White = clean bright white (not warm cream like Portra) Linen/cotton = clean and natural, slightly muted Pastels = rendered beautifully — pink goes soft, blue goes clean Dark clothing = refined, not dramatic Earth tones = slightly cool and muted, not warm Colours clean and slightly muted, never vivid. Fuse into character clause. POSE: natural analog quality — unstaged, mid-moment. 'Turned slightly from camera, catching diffused window light on one side of the face, expression quiet and present, not performing for the photographer.' INTERACTION (2+ characters): natural soft light photography. Both in same cool-neutral light quality. Not perfectly symmetric. Body language carries the connection — turned toward, leaning in, sharing a quiet moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph: 1. CAMERA: '35mm film' or 'medium format film' + lens + aperture + overexposure if used ('+1 stop overexposed' common) 2. CHARACTER: name + outfit (how colours read under cool Pro 400H palette) + natural unstaged pose + expression 3. ENVIRONMENT: real location with specific soft light quality. Overcast ideal. Direction and quality of light. 4. SKIN RENDERING: cool-neutral, lifted lavender-grey shadows, airy Pro 400H quality. How light falls specifically. 5. COLOUR PALETTE: cool greens, muted tones, lifted shadows toward lavender-grey, clean whites 6. DEPTH OF FIELD: what is sharp vs soft cool bokeh 7. GRAIN: fine and quiet (mention if pushed) STYLE SUFFIX (append verbatim): 'Analog photograph shot on Fujifilm PRO 400H color negative film. Real photograph, not digital, not rendered, not a painting. Fujifilm PRO 400H characteristics: cool-neutral skin tone rendering — porcelain, clean, ivory quality, distinctly different from warm Kodak Portra. Airy slightly overexposed feel — highlights blooming gently into clean white, shadows lifting to soft lavender-grey or cool pale grey, never crushing to darkness. Very fine grain for ISO 400 — smooth, refined, barely visible in well-lit areas, present but quiet in shadows. Colour palette: greens cool and slightly mint-teal rather than warm olive, blues clean and muted, reds soft pinkish rather than saturated, yellows pale cream not golden. Japanese minimalist sensibility — clean, restrained, deliberately beautiful. Not warm, not orange, not the golden quality of Portra. Soft natural light photography — overcast, window light, open shade, soft golden hour. Bokeh is cool-creamy and smooth, pale lavender-white tones. Medium format lushness when applicable. No digital sharpness, no warm processing, no artificial vibrancy, no studio lighting artificiality.' NEGATIVE (append verbatim): 'Avoid: warm orange skin tones, Kodak Portra warm golden quality, vivid saturated colours, harsh studio lighting, hot amber highlights, digital noise instead of film grain, dark crushing shadows, blue-cast cold night photography, heavy contrast, golden hour overdrive, Instagram warm filter, AI digital smoothness, watermark, text, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION The quality of the light. Cool, quiet, Japanese. What made this frame worth taking. Lowercase, italic. ASPECT RATIO 3:2 = standard 35mm (default) | 4:5 = medium format portrait | 1:1 = medium format square | 2:3 = vertical portrait | 16:9 = wide TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(8,10,18,0.65),rgba(5,7,14,0.65));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(160,185,220,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.5),inset 0 1px 0 rgba(160,185,220,0.04);"> <img data-iig-instruction='{"style":"fujifilm_pro400h_analog","prompt":"[CAMERA INFO + CHARACTER + OUTFIT + NATURAL POSE + ENVIRONMENT + LIGHT QUALITY (COOL-NEUTRAL) + SKIN RENDERING + PRO 400H COLOUR PALETTE + DOF + GRAIN. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(160,185,220,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(180,200,230,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','3:2','4:5','2:3','16:9'. The CSS aspect-ratio value matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-130 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> FUJIFILM PRO 400H FILM PHOTOGRAPHY — EVERY RESPONSE One image per message at the most emotionally resonant or quietly beautiful moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Analog photograph shot on Fujifilm PRO 400H color negative film. Real photograph. NOT digital, NOT rendered, NOT a painting. The definitive cool Japanese portrait film. Where Portra is warm, Pro 400H is cool — airy, slightly overexposed, pastel-toned. Porcelain skin. Lifted lavender shadows. Japanese minimalist sensibility. WHAT MAKES FUJIFILM PRO 400H: 1. Cool-neutral skin — NOT warm. Porcelain, ivory quality. Shadows lift to lavender-grey, not darkness. 2. Airy overexposed feel — +1 to +2 stops typical. Highlights bloom to clean white. Nothing crushes. 3. Lifted pastel shadows — soft lavender-grey or cool pale grey throughout — no heavy darkness 4. Colours: greens cool mint-teal (not olive) | blues clean and muted | reds soft pinkish | yellows pale cream 5. Very fine grain for ISO 400 — smooth, refined, nearly invisible in good light 6. Japanese minimalist sensibility — clean, restrained, quietly beautiful. Nothing garish. 7. Medium format heritage — Mamiya RZ67, Hasselblad — lush detail, generous subject separation IDEAL LIGHT: overcast daylight (peak Pro 400H) | open shade | window light | soft golden hour NOT for: neon night | harsh artificial (use CineStill 800T) PUSHED OPTIONS: Pushed 1 stop (ISO 800): more grain, more lavender shadows, muted editorial quality Pulled to ISO 200: even smoother, expanded whites CAMERA 35mm SLR or medium format. State: 'Shot on [35mm/medium format] film, [focal length] [aperture].' Wide aperture bokeh = cool creamy pale spheres, lavender-white — NOT warm amber like Portra. Default aspect: 3:2 (35mm) | 1:1 or 4:5 (medium format feel). CHARACTERS First name only. Skip: hair, eyes, skin, face shape. Reference handles appearance. SKIN: cool-neutral ivory, shadows lift to lavender-grey. Describe light direction. Under Pro 400H: white = clean bright (not warm cream) | pastels = beautiful | all colours muted and cool. POSE: natural, unstaged, not performing for the camera. HOW TO BUILD THE PROMPT 1. CAMERA — 35mm or medium format, lens, aperture, overexposure note if used 2. CHARACTER — name + outfit (colours read cool under Pro 400H) + natural quiet pose 3. ENVIRONMENT — real location, specific soft cool light quality, direction 4. SKIN — cool-neutral, lifted lavender shadows, airy rendering 5. PRO 400H COLOUR PALETTE — cool greens, muted tones, lifted pastel shadows, clean whites 6. DOF — sharp subject vs soft cool pale bokeh 7. GRAIN — fine and quiet Total prompt: 80-130 words + style suffix. STYLE SUFFIX (append verbatim): 'Analog photograph shot on Fujifilm PRO 400H color negative film. Real photograph, not digital, not rendered, not a painting. Fujifilm PRO 400H characteristics: cool-neutral skin tone rendering — porcelain, clean, ivory quality, distinctly different from warm Kodak Portra. Airy slightly overexposed feel — highlights blooming gently into clean white, shadows lifting to soft lavender-grey or cool pale grey, never crushing to darkness. Very fine grain for ISO 400 — smooth, refined, barely visible in well-lit areas, present but quiet in shadows. Colour palette: greens cool and slightly mint-teal rather than warm olive, blues clean and muted, reds soft pinkish rather than saturated, yellows pale cream not golden. Japanese minimalist sensibility — clean, restrained, deliberately beautiful. Not warm, not orange, not the golden quality of Portra. Soft natural light photography — overcast, window light, open shade, soft golden hour. Bokeh is cool-creamy and smooth, pale lavender-white tones. Medium format lushness when applicable. No digital sharpness, no warm processing, no artificial vibrancy, no studio lighting artificiality.' NEGATIVE (append verbatim): 'Avoid: warm orange skin tones, Kodak Portra warm golden quality, vivid saturated colours, harsh studio lighting, hot amber highlights, digital noise instead of film grain, dark crushing shadows, blue-cast cold night photography, heavy contrast, golden hour overdrive, Instagram warm filter, AI digital smoothness, watermark, text, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Cool light. Quiet moment. Japanese. Lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(8,10,18,0.65),rgba(5,7,14,0.65));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(160,185,220,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.5),inset 0 1px 0 rgba(160,185,220,0.04);"> <img data-iig-instruction='{"style":"fujifilm_pro400h_analog","prompt":"[CAMERA + CHARACTER + OUTFIT + NATURAL POSE + ENVIRONMENT + COOL LIGHT QUALITY + SKIN (COOL-NEUTRAL, LAVENDER SHADOWS) + PRO 400H PALETTE + DOF. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(160,185,220,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(180,200,230,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '3:2' default | '2:3' portrait | '1:1' | '4:5' | '16:9'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Analog photograph on Fujifilm PRO 400H color negative film. Cool-neutral skin tones — porcelain, ivory, clean — distinctly NOT the warm golden quality of Kodak Portra. Airy slightly overexposed quality — highlights bloom to clean white, shadows lift to soft lavender-grey rather than crushing to darkness. Very fine grain for ISO 400. Greens cool and slightly mint-teal. Blues clean and muted. Japanese minimalist sensibility — clean, restrained, quietly beautiful. Natural soft light — overcast, window light, open shade, soft golden hour. Bokeh is cool-creamy pale. Avoid: warm orange skin tones, Portra golden quality, vivid saturated colours, harsh studio lighting, hot amber highlights, dark crushing shadows, warm golden hour overdrive, watermark, text.

Копировать [Image generation hint, STYLE: Fujifilm Pro 400H analog film photo — cool-neutral porcelain skin (not warm), shadows lift to lavender-grey, airy overexposed quality, very fine grain, Japanese minimalist, cool mint greens, pale creamy bokeh]

Fujifilm Velvia 50

Самая насыщенная плёнка в мире. Зелёные — электрические. Синие — глубокий кобальт. Красные — огненные. ~150-200% от натуральной насыщенности. Слайд: без допуска, нет зерна. Классика пейзажа.

Новый Кино и фото

←→

Длинный~2751 Короткий~1541 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> FUJIFILM VELVIA 50 FILM PHOTOGRAPHY — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually spectacular or colour-intense moment. STYLE OVERVIEW Analog photograph shot on Fujifilm Velvia 50 slide film (reversal film / E-6 process). Real photograph. NOT digital, NOT rendered, NOT a painting. The most saturated film stock ever made. The landscape photographer's weapon of choice. Velvia 50 does not gently render colour — it AMPLIFIES it. Greens are electric. Blues are deep and intense. Reds burn. Yellows glow. Everything pushed to the maximum saturation possible while remaining photographic. Not garish digital saturation — the specific, rich quality of a film stock that seems to see colour more than the human eye does. WHAT MAKES FUJIFILM VELVIA 50: 1. EXTREME COLOUR SATURATION — the defining characteristic: Velvia 50 renders every colour at approximately 150-200% of natural intensity. Greens that would be pleasant on Portra become electric vivid emerald. Blues that would be muted become deep saturated cobalt. Reds become fiery. This is not a subtle effect — it is dramatic and immediately visible. State the specific saturated colours in every prompt. Name them: 'electric emerald green', 'deep cobalt sky', 'fiery amber-red'. 2. HIGH CONTRAST — inherent in the emulsion: Highlights: bright and clean, held but vivid Shadows: deep and saturated — shadow areas have colour richness, not flat grey Overall: punchy, defined, high-contrast compared to any negative film The contrast enhances the saturation — bright vs dark becomes vivid vs saturated dark. 3. COLOUR SPECIFICITY BY HUE: Greens: ELECTRIC — vivid emerald, deep forest green, almost unnaturally saturated. The Velvia green is its most iconic quality. Blues: DEEP and INTENSE — rich cobalt, saturated sky blue, deep ocean blue Reds: FIERY — bright, rich, saturated warm red — burns Yellows: BURNING GOLD — strong amber-gold, intense, not pale White: slight warm-cream shift — Velvia adds a faint warmth to neutral whites Shadows: deep and colour-rich, not desaturated dark 4. VIRTUALLY ZERO GRAIN — ISO 50 advantage: One of the finest-grain stocks ever produced. Virtually grainless at normal usage. Enlargements show extraordinary detail. Images feel incredibly sharp and clean against the rest of the analog family. 5. SLIDE FILM CHARACTERISTICS (reversal film — positive): The film IS the image. No negative, no scanning latitude. Overexposed: colours wash out, highlights blow catastrophically Underexposed: colours go muddy and dark, lose saturation Correct exposure: maximum colour saturation at maximum sharpness — state correct exposure in the prompt No forgiveness, no latitude — this is the trade for maximum colour. 6. VELVIA LANDSCAPE HERITAGE: Designed for nature and landscape photography. What Velvia does to specific subjects: Foliage: electric green — almost surreal, sometimes more vivid than real life Sky: deep blue with cloud definition — dramatic Sunsets/Sunrises: full force of warm-cool contrast amplified — amber sky against deep blue horizon Water: electric blue-green, reflecting saturated sky Flowers: petals almost luminously saturated, each colour at peak intensity Rock/Earth: warm ochre and amber tones, rich terracotta 7. VELVIA FOR PORTRAITS — USE DELIBERATELY: Velvia is not designed for portraiture — skin goes warm-vivid, slightly orange-saturated. When used deliberately: expect vivid, slightly dramatic skin rendering — state in prompt as 'Velvia skin: warm-vivid, slightly saturated, the film's colour amplification visible in skin tone'. For subjects in landscapes: the character becomes part of the saturated world. IDEAL VELVIA 50 SCENES: GOLDEN HOUR LANDSCAPE: the perfect Velvia moment. Sky becomes orange-red so intense it almost defies belief. Green landscape electric against it. The classic landscape poster look. DAWN / SUNRISE: the full spectacle of warm-cool sky at maximum intensity NATURE CLOSE-UP: flowers, foliage, insects — macro where saturation becomes the subject ARCHITECTURE WITH COLOUR: geometric forms with coloured surfaces — Velvia turns surfaces into colour fields STORM WEATHER: storm clouds become dramatically dark against electric landscape colours MOUNTAIN / ALPINE: glaciers electric blue, rock rich ochre, sky deep cobalt OCEAN / COAST: water electric blue-green, sky deep, foam brilliant white CAMERA Medium format preferred for maximum detail: Mamiya RZ67, Hasselblad 503CW, Pentax 645 (4:5 and 1:1 natural). 35mm also used: Canon EOS, Nikon F, Contax G, Leica M. State at start: 'Shot on [35mm / medium format] Velvia 50 slide film, [focal length] [aperture].' Aperture: f/8-f/11 classic landscape — maximum depth, everything sharp f/2.8-f/4 for subject isolation in editorial or portrait use Shutter: long exposure valid for waterfalls, moving subjects (Velvia + long exposure = vivid motion) Aspect: 4:5 default (landscape natural format) | 3:2 (35mm) | 1:1 (medium format square) | 2:3 vertical CHARACTERS First name only — names map to reference images. Skip: hair colour, eye colour, skin tone, face shape. Skin under Velvia: warm-vivid, the film's saturation enhancement visible. Mention if part of the intention. Outfit under Velvia: ALL colours dramatically more saturated — state the intensified versions: 'red jacket reads as electric scarlet', 'blue reads as deep cobalt', 'yellow as burning gold'. HOW TO BUILD THE PROMPT Write a single dense English paragraph: 1. CAMERA: medium format or 35mm, lens, aperture. Always state Velvia 50. 2. SUBJECT: character name or landscape subject. Outfit colours with Velvia saturation stated. 3. ENVIRONMENT: specific location with specific light. What makes this frame spectacular? 4. VELVIA COLOUR AMPLIFICATION: explicitly name the saturated colours in the scene. 'Greens electric vivid against deep cobalt sky', 'sunset orange burning against silhouetted form', 'electric emerald foliage at the peak of Velvia's saturation'. 5. CONTRAST: describe the punchy high-contrast division — bright vivid areas vs deep colour-rich shadows. 6. GRAIN: virtually absent at ISO 50 — state: 'virtually grain-free, extraordinary sharpness and detail'. 7. SATURATION SUMMARY: one line on the overwhelming impression — what Velvia made of this scene. STYLE SUFFIX (append verbatim): 'Analog photograph shot on Fujifilm Velvia 50 slide film (E-6 reversal process). Real photograph, not digital, not rendered, not a painting. Fujifilm Velvia 50 characteristics: maximum colour saturation — every colour amplified to approximately 150-200% of natural intensity. Greens electric and vivid (emerald, forest, grass — all deeply saturated). Blues deep and rich (cobalt sky, deep ocean, intense azure). Reds fiery and bright. Yellows golden and vivid. High-contrast rendering: punchy shadows with colour richness, bright highlights with detail held. Virtually zero grain — ISO 50 means extraordinary sharpness and detail even in large enlargements. Slide film (positive film) characteristics: perfect exposure critical, no latitude, colours either maximally saturated at correct exposure or washed and muddy at wrong exposure. The quintessential landscape photography film. Colour saturation level that makes scenes look more vivid than memory. Not subtle. Not restrained. Maximum colour intensity while remaining photographic. Not digital HDR. Not digital saturation boost. The grain structure, tonal rendering, and colour depth of genuine slide film.' NEGATIVE (append verbatim): 'Avoid: muted desaturated colours, Kodak Portra warm portrait quality, digital photography colour science, cool desaturated tones, flat lighting, missing saturation intensity, visible grain (Velvia 50 is virtually grainless), photorealistic photography look, blurred soft rendering, digital HDR cartoon quality, oversaturated glowing digital aesthetic, AI digital colour grading, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION What the light did. What the colour felt like. What Velvia made of the world. Lowercase, italic. ASPECT RATIO 4:5 = natural landscape format (default) | 3:2 = 35mm standard | 1:1 = medium format square | 2:3 = vertical portrait | 16:9 = panoramic wide TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(4,10,6,0.72),rgba(2,8,4,0.72));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(60,200,90,0.09);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(60,200,90,0.04);"> <img data-iig-instruction='{"style":"fujifilm_velvia50_analog","prompt":"[CAMERA INFO + SUBJECT + ENVIRONMENT + VELVIA COLOUR AMPLIFICATION (NAMED COLOURS) + HIGH CONTRAST + GRAIN NOTE + SATURATION SUMMARY. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"4:5","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:4/5;object-fit:cover;border-radius:8px;border:1px solid rgba(60,200,90,0.05);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(130,220,150,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','3:2','4:5','2:3','16:9'. The CSS aspect-ratio value matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-130 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> FUJIFILM VELVIA 50 FILM PHOTOGRAPHY — EVERY RESPONSE One image per message at the most visually spectacular or colour-intense moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Analog photograph shot on Fujifilm Velvia 50 slide film (E-6 reversal). Real photograph. NOT digital, NOT rendered, NOT a painting. The most saturated film stock ever made. The landscape photographer's weapon. Velvia does not render colour — it AMPLIFIES it. Not subtle. Not restrained. Maximum colour while remaining photographic. WHAT MAKES FUJIFILM VELVIA 50: 1. EXTREME SATURATION — every colour at ~150-200% of natural intensity. Electric greens. Deep cobalt blues. Fiery reds. Burning gold yellows. 2. HIGH CONTRAST — punchy, defined. Bright vivid areas vs deep colour-rich shadows. 3. Greens: ELECTRIC emerald-vivid | Blues: DEEP cobalt-rich | Reds: FIERY warm | Yellows: BURNING gold | Shadows: saturated dark, colour-rich 4. VIRTUALLY ZERO GRAIN — ISO 50. Extraordinary sharpness and detail. Virtually grainless. 5. SLIDE FILM — no latitude. Correct exposure = maximum colour. Wrong = washed or muddy. 6. Landscape heritage: foliage electric green, sky deep vivid blue, sunsets burning, water electric 7. Saturation that makes scenes look more vivid than memory IDEAL SCENES: golden hour landscape | sunrise/sunset | nature close-up | electric foliage | architecture with colour | storm weather | mountain/alpine | coast PORTRAITS on Velvia: skin goes warm-vivid, slightly saturated — mention as deliberate choice. Outfit colours under Velvia: state the amplified version ('red jacket reads as electric scarlet'). CAMERA Medium format preferred (Mamiya RZ67, Hasselblad). 35mm also valid. State: 'Shot on [35mm/medium format] Velvia 50 slide film, [focal length] [aperture].' f/8-f/11 for landscape depth. f/2.8-f/4 for subject isolation. Grain: virtually absent — always note this. Default aspect: 4:5. HOW TO BUILD THE PROMPT 1. CAMERA — format, lens, aperture, Velvia 50 2. SUBJECT — character name or landscape. Outfit with Velvia saturation amplification noted. 3. ENVIRONMENT — specific location with dramatic or beautiful light 4. VELVIA AMPLIFICATION — explicitly name saturated colours: 'electric emerald against deep cobalt', 'burning amber sky', 'fiery scarlet against electric green' 5. CONTRAST — vivid bright areas vs deep colour-rich shadows 6. GRAIN — virtually absent, extraordinary sharpness Total prompt: 80-130 words + style suffix. STYLE SUFFIX (append verbatim): 'Analog photograph shot on Fujifilm Velvia 50 slide film (E-6 reversal process). Real photograph, not digital, not rendered, not a painting. Fujifilm Velvia 50 characteristics: maximum colour saturation — every colour amplified to approximately 150-200% of natural intensity. Greens electric and vivid (emerald, forest, grass — all deeply saturated). Blues deep and rich (cobalt sky, deep ocean, intense azure). Reds fiery and bright. Yellows golden and vivid. High-contrast rendering: punchy shadows with colour richness, bright highlights with detail held. Virtually zero grain — ISO 50 means extraordinary sharpness and detail even in large enlargements. Slide film (positive film) characteristics: perfect exposure critical, no latitude, colours either maximally saturated at correct exposure or washed and muddy at wrong exposure. The quintessential landscape photography film. Colour saturation level that makes scenes look more vivid than memory. Not subtle. Not restrained. Maximum colour intensity while remaining photographic. Not digital HDR. Not digital saturation boost. The grain structure, tonal rendering, and colour depth of genuine slide film.' NEGATIVE (append verbatim): 'Avoid: muted desaturated colours, Kodak Portra warm portrait quality, digital photography colour science, cool desaturated tones, flat lighting, missing saturation intensity, visible grain (Velvia 50 is virtually grainless), photorealistic photography look, blurred soft rendering, digital HDR cartoon quality, oversaturated glowing digital aesthetic, AI digital colour grading, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION The colour. What Velvia made of the light. Lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(4,10,6,0.72),rgba(2,8,4,0.72));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(60,200,90,0.09);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(60,200,90,0.04);"> <img data-iig-instruction='{"style":"fujifilm_velvia50_analog","prompt":"[CAMERA + SUBJECT + ENVIRONMENT + VELVIA COLOUR AMPLIFICATION + CONTRAST + GRAIN NOTE. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"4:5","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:4/5;object-fit:cover;border-radius:8px;border:1px solid rgba(60,200,90,0.05);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(130,220,150,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '4:5' default | '3:2' | '1:1' | '2:3' | '16:9'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Analog photograph on Fujifilm Velvia 50 slide film (E-6 reversal process). Maximum colour saturation — every colour amplified to approximately 150-200% of natural intensity. Greens electric vivid emerald. Blues deep rich cobalt. Reds fiery and bright. Yellows burning gold. High contrast: punchy shadows with colour richness, bright highlights held. Virtually zero grain — ISO 50 extraordinary sharpness. Landscape photography ideal: foliage electric green, sky deep vivid blue, sunset burning orange against saturated horizon. Not subtle, not restrained — maximum colour while remaining photographic. Avoid: muted desaturated colours, Portra warm portrait quality, flat lighting, visible grain, digital HDR look, oversaturated cartoon quality, watermark, text.

Копировать [Image generation hint, STYLE: Fujifilm Velvia 50 slide film — maximum colour saturation (150-200% natural), electric greens, deep cobalt blues, fiery reds, burning gold yellows, high contrast, virtually zero grain, landscape/nature photography]

Lomography / Cross-Process

Ломо с кросс-процессом. ОБЯЗАТЕЛЬНО: засветки (тёплый оранжево-красный из угла). Сдвиги цвета: тени в зелёный/циан, полутона в золото. Тёмный виньет. Пластиковая оптика. Несовершенство ЕСТЬ искусство.

Новый Кино и фото

←→

Длинный~2796 Короткий~1564 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> LOMOGRAPHY / CROSS-PROCESS FILM PHOTOGRAPHY — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually interesting, colour-shifted, or beautifully chaotic moment. STYLE OVERVIEW Analog photograph taken on a Lomography film camera — with optional cross-process treatment (E-6 slide film developed in C-41 chemistry, or C-41 negative in E-6). Real photograph. NOT digital, NOT rendered, NOT a painting. The deliberate imperfection aesthetic. Experimental analog photography where the 'mistakes' are the art. Light leaks, cross-process colour shifts, heavy vignette, plastic lens softness, unpredictable chemistry — these are not flaws to be corrected. They are the entire reason to pick up a Lomo camera. THE FOUR ELEMENTS THAT DEFINE THIS STYLE: 1. LIGHT LEAKS — MANDATORY IN EVERY IMAGE: Light enters the camera where it should not. The result: warm orange-red or yellow-gold flooding across one edge or corner of the frame. Sometimes a streak across the middle. Sometimes a bloom in one corner. Always feels accidental. Always feels right. LIGHT LEAK TYPES — choose one per image: CORNER BLOOM: warm orange-red light flooding from one specific corner, fading into the image diagonally. State: 'orange-red light leak blooming from the top-left corner'. EDGE BURN: warm streak along the top, bottom, or one full side — a band of warm light burning in. State: 'yellow-gold edge burn along the top of the frame'. MIDDLE STREAK: vertical or horizontal semi-transparent band of warm light crossing the image. State: 'warm orange streak cutting horizontally across the middle-right'. MULTI-LEAK: two simultaneous leaks from different positions — one corner, one edge. Colour of leaks: warm orange-red | yellow-gold | amber | pale cream-yellow 2. CROSS-PROCESS COLOUR SHIFTS — when cross-processing is used: CLASSIC E-6 IN C-41 (most used, most vivid shifts): Shadows: go green → teal → cyan (pick one and state it) Midtones: warm golden-yellow cast Highlights: shift to pale yellow-cream Skin tones: warm-golden with strong green cast in the shadows Blues: shift to teal-cyan Greens: intensify and go lime-vivid or deep teal Reds: sometimes shift orange, sometimes stay Contrast: HIGH — more pronounced than normal film Effect: images look chemically altered — vivid, high-contrast, colour-shifted in ways no normal film produces. REVERSE PROCESS — C-41 IN E-6 (rarer, cooler effect): Overall: cool, blue-shifted Shadows: deep blue-purple, almost alien Midtones: cool grey-blue Highlights: pale blue-white Skin: cool, slightly alien — not wrong, intentionally strange NO CROSS-PROCESS: use if the scene calls for more naturalistic colour — Lomo camera colour rendering with all the vignette and light leak elements but without chemical colour shifts. 3. HEAVY OPTICAL VIGNETTE — MANDATORY: Lomography plastic lenses produce strong vignetting — corners and edges of the frame darken dramatically. The subject in the centre is relatively normally exposed; by the edges, light falls off to deep dark. This is optical, soft-edged, characteristic. Not digital. INTENSITY: moderate (corners dark, edges normal) | heavy (edges noticeably dark) | extreme (frame feels almost circular) State: 'extreme optical vignette from plastic lens, corners falling to near-black, centre bright'. 4. PLASTIC LENS CHARACTER: Softness in corners and edges — centre acceptably sharp, corners soft and dreamlike Slight barrel distortion: straight lines bow outward at edges Beautiful flare in direct light: streaks and washes, not controlled Limited focus range: zone-focused Lomo cameras are not precise instruments Colour rendering: plastic glass shifts colour slightly before any cross-process LOMOGRAPHY CAMERA IDENTITIES: LOMO LC-A: 35mm compact, ~32mm equivalent, severe vignette, underexposure tendency, sharp centre, soft corners, the classic Lomo. Cross-process: legendary results. DIANA F+: medium format plastic (120 film), extreme vignette, dreamy soft focus throughout, square or rectangular format, dreamlike quality HOLGA: medium format plastic, very soft focus, intense vignette, light-leak prone, square format, heavily romantic and imprecise LOMO LC-WIDE: 35mm wide-angle (~17mm equivalent), very strong vignette, fish-eye distortion at edges SPROCKET ROCKET: panoramic 35mm with the film sprocket holes visible in the frame — unique look GRAIN AND TEXTURE: ISO 400 or ISO 800 film typical with Lomo cameras — grain is significant and part of the aesthetic. With cross-process chemistry: grain often increases, especially in shadow areas with the colour shift. State grain level: 'visible ISO 800 grain throughout, heavy in shadows'. OCCASIONS AND SCENES: PORTRAIT: face centred, extreme vignette framing, corner light leak, cross-process skin — warm-golden with teal shadows STREET CANDID: urban chaos, colour shifted, vignette compressing the scene, light leak burning the sky PARTY / GATHERING: multiple people, flash or available indoor light, cross-process makes everything look chemically strange NIGHT OUT: neon and indoor tungsten + cross-process = violent colour chaos in the best way NATURE INFORMAL: landscape with cross-process colour — electric greens, teal shadows, warm light leaks TRAVEL: casual documentation, imperfect, honest, beautiful because of the mistakes DOUBLE EXPOSURE: two scenes layered (Lomo multi-exposure mode) — ghost image of one scene over another CAMERA TECHNICAL: State camera type and film. Aspect: 3:2 (35mm, LC-A, LC-Wide) | 1:1 (Holga, Diana square) | 2.4:1 (Sprocket Rocket panoramic) Flash: Lomo LC-A auto-flash or no flash — state if used. HOW TO BUILD THE PROMPT Write a single dense English paragraph: 1. CAMERA + FILM: which Lomo camera + ISO film (400 or 800) + cross-process direction if used 2. CHARACTER: name + outfit + natural candid pose — not staged, not art directed 3. SCENE: specific environment and moment 4. LIGHT LEAK: TYPE + COLOUR + POSITION in frame — MANDATORY, specific, every image 5. VIGNETTE: intensity (moderate/heavy/extreme) + how it frames the subject 6. CROSS-PROCESS SHIFTS: specific shadow colour, midtone cast, highlight shift, skin colour if character present 7. PLASTIC LENS QUALITY: corner softness, distortion, flare if in direct light 8. GRAIN: present and characterful STYLE SUFFIX (append verbatim): 'Analog photograph on Lomography film camera, possible cross-process treatment (E-6 slide film developed in C-41 chemistry or reverse). Real photograph, not digital, not rendered, not a painting. Lomography cross-process aesthetic characteristics: light leaks — warm orange-red or yellow-gold light flooding semi-transparently from one corner or along one edge of the frame, characteristic of imperfect film camera light seals. Strong optical vignetting from plastic Lomo lens — edges and corners darken dramatically, centre relatively bright, soft-edged and organic not hard digital vignette. Cross-process colour shifts if applicable — shadows shift green-teal-cyan, midtones warm golden-yellow, highlights drift pale yellow, skin tones warm-golden with shifted shadow cast, blues shift toward teal. Plastic lens character: corner softness, slight barrel distortion, natural lens flare in direct light, limited focus precision. Visible grain at ISO 400-800, heavier in shadows and cross-processed areas. The imperfection is the aesthetic — light, chemistry, and plastic optics creating images no intentional process would make. Not Instagram filter simulation. Not digital cross-process preset. Genuine analog imperfection.' NEGATIVE (append verbatim): 'Avoid: clean clinical digital photography, perfect even lighting, no vignette, missing light leaks, perfect colour accuracy, digital filter simulation look, smooth gradients without grain, missing cross-process colour shifts, studio artificial lighting, overly sharp edges throughout, Instagram filter without analog character, perfect photographic control, AI smooth digital aesthetic, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION What the light did. What the chemistry did. What you felt when you opened the film envelope and found this. Lowercase, italic. ASPECT RATIO 3:2 = 35mm standard (default, LC-A) | 1:1 = Holga/Diana square | 2.4:1 = Sprocket Rocket panoramic | 2:3 = vertical 35mm | 4:5 = medium format portrait TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(15,6,3,0.72),rgba(10,4,2,0.72));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(220,130,60,0.10);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(220,130,60,0.05);"> <img data-iig-instruction='{"style":"lomography_xpro_analog","prompt":"[CAMERA + FILM + CROSS-PROCESS IF USED + CHARACTER + SCENE + LIGHT LEAK (TYPE + COLOUR + POSITION — MANDATORY) + VIGNETTE + CROSS-PROCESS COLOUR SHIFTS + PLASTIC LENS QUALITY + GRAIN. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(220,130,60,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(230,170,110,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','3:2','4:5','2:3','16:9'. The CSS aspect-ratio value matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-140 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> LOMOGRAPHY / CROSS-PROCESS FILM PHOTOGRAPHY — EVERY RESPONSE One image per message at the most visually interesting, colour-shifted, or beautifully imperfect moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Analog photograph on a Lomography film camera, optional cross-process treatment. Real photograph. NOT digital, NOT rendered, NOT a painting. Deliberate imperfection aesthetic. Light leaks, cross-process colour shifts, heavy vignette, plastic lens character — not flaws. The art. THE FOUR ELEMENTS — ALL PRESENT IN EVERY IMAGE: 1. LIGHT LEAKS — MANDATORY: Warm orange-red or yellow-gold light flooding from corner or edge of frame. TYPES: corner bloom | edge burn | middle streak | multi-leak Describe: type + colour + which position. Every image, no exceptions. Example: 'orange-red light leak blooming from the top-right corner' 2. CROSS-PROCESS COLOUR SHIFTS (when used): E-6 IN C-41 (classic): shadows → green/teal/cyan | midtones → warm golden-yellow | highlights → pale yellow | skin → warm-golden with shifted shadow cast | blues → teal | high contrast C-41 IN E-6 (rarer): overall cool-blue | shadows → deep blue-purple | alien quality 3. HEAVY OPTICAL VIGNETTE: Corners and edges darken dramatically from plastic lens. Centre bright, edges fall to dark. State intensity: moderate | heavy | extreme. 4. PLASTIC LENS CHARACTER: Corner softness | slight barrel distortion | natural lens flare in direct light | imprecise focus CAMERAS: Lomo LC-A (35mm, severe vignette) | Diana F+ (120 film, dreamy, square) | Holga (120, soft, square) | LC-Wide (35mm wide, fish-eye edges) | Sprocket Rocket (panoramic with sprocket holes) GRAIN: ISO 400-800 — visible, characterful, heavier in shadows and cross-processed areas. CROSS-PROCESS SKIN: warm-golden (E-6 in C-41) or cool-alien (C-41 in E-6) — state which. CAMERA: state type + film ISO. Aspect: 3:2 (35mm) | 1:1 (Holga/Diana square) | 2.4:1 (Sprocket). HOW TO BUILD THE PROMPT 1. CAMERA + FILM — Lomo type, ISO, cross-process direction if used 2. CHARACTER — name + outfit + natural candid unstaged pose 3. SCENE — specific environment and moment 4. LIGHT LEAK — TYPE + COLOUR + POSITION (MANDATORY every image) 5. VIGNETTE — intensity 6. COLOUR SHIFTS — shadow/midtone/highlight if cross-processed 7. LENS CHARACTER — corner softness, distortion, flare if direct light Total prompt: 80-140 words + style suffix. STYLE SUFFIX (append verbatim): 'Analog photograph on Lomography film camera, possible cross-process treatment (E-6 slide film developed in C-41 chemistry or reverse). Real photograph, not digital, not rendered, not a painting. Lomography cross-process aesthetic characteristics: light leaks — warm orange-red or yellow-gold light flooding semi-transparently from one corner or along one edge of the frame, characteristic of imperfect film camera light seals. Strong optical vignetting from plastic Lomo lens — edges and corners darken dramatically, centre relatively bright, soft-edged and organic not hard digital vignette. Cross-process colour shifts if applicable — shadows shift green-teal-cyan, midtones warm golden-yellow, highlights drift pale yellow, skin tones warm-golden with shifted shadow cast, blues shift toward teal. Plastic lens character: corner softness, slight barrel distortion, natural lens flare in direct light, limited focus precision. Visible grain at ISO 400-800, heavier in shadows and cross-processed areas. The imperfection is the aesthetic — light, chemistry, and plastic optics creating images no intentional process would make. Not Instagram filter simulation. Not digital cross-process preset. Genuine analog imperfection.' NEGATIVE (append verbatim): 'Avoid: clean clinical digital photography, perfect even lighting, no vignette, missing light leaks, perfect colour accuracy, digital filter simulation look, smooth gradients without grain, missing cross-process colour shifts, studio artificial lighting, overly sharp edges throughout, Instagram filter without analog character, perfect photographic control, AI smooth digital aesthetic, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION What the light did. What the chemistry did. Lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(15,6,3,0.72),rgba(10,4,2,0.72));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(220,130,60,0.10);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(220,130,60,0.05);"> <img data-iig-instruction='{"style":"lomography_xpro_analog","prompt":"[CAMERA + FILM + CHARACTER + SCENE + LIGHT LEAK (MANDATORY: TYPE + COLOUR + POSITION) + VIGNETTE + CROSS-PROCESS SHIFTS IF USED + LENS CHARACTER + GRAIN. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(220,130,60,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(230,170,110,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '3:2' default | '1:1' | '2:3' | '4:5' | '16:9'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Analog photograph on a Lomography film camera (Lomo LC-A, Diana F+, or Holga) with cross-process treatment. MANDATORY elements: (1) light leak — warm orange-red or yellow-gold light flooding semi-transparently from one corner or along one edge of the frame; (2) strong optical vignette from plastic lens — corners and edges darken dramatically to near-black; (3) cross-process colour shifts — shadows shift green-teal-cyan, midtones warm golden-yellow, highlights drift pale yellow, blues shift teal; (4) plastic lens softness in corners, slight barrel distortion. ISO 400-800 grain visible. Deliberate imperfection aesthetic — nothing is clean, clinical, or perfectly composed. Avoid: clean digital photography, perfect even lighting, no vignette, missing light leaks, perfect colour accuracy, studio lighting, watermark, text.

Копировать [Image generation hint, STYLE: Lomography cross-process film — warm orange-red light leak from corner (mandatory), heavy optical vignette, cross-process colour shifts (shadows green-teal, midtones golden), plastic lens corner softness, ISO 400-800 grain]

Disposable Camera

Фотик за 200 рублей с вспышкой. Жёсткий прямой свет. Близкие — пересвечены, дальние — в темноте. Тень за спиной. Зерно ISO 800. Дата в углу. Честно и без прикрас.

Новый Кино и фото

←→

Длинный~2739 Короткий~1675 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> DISPOSABLE CAMERA / FLASH FILM PHOTOGRAPHY — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most candid, unguarded, or party-honest moment. STYLE OVERVIEW Analog photograph taken on a disposable 35mm film camera — Kodak FunSaver, Fuji QuickSnap, or similar single-use camera with built-in flash. Real photograph. NOT digital, NOT rendered, NOT a painting. The anti-aesthetic aesthetic. No deliberate composition, no crafted lighting, no artistic intent visible. Just pressing the button. The flash eliminates all atmosphere and creates an entirely specific one of its own. These photographs document moments as they actually were. Honest. Raw. The opposite of Instagram. THE DEFINING VISUAL ELEMENTS: 1. HARD ON-CAMERA FLASH — THE SINGLE MOST IMPORTANT ELEMENT: A small underpowered flash directly above or beside the lens, aimed straight at the subject. No diffusion. No bounce. The harshest, most frontal, most democratic light imaginable. FLASH PHYSICS — describe all of these: CLOSE SUBJECT (1-2m): blown out and bright. Face is flat-lit, over-exposed at nose and forehead. The specular hotspot is brutal. Eyes sometimes catch red-eye. It looks like a party photo because it is a party photo. FAR SUBJECT (4m+): dark. The flash does not reach. Subjects beyond 4 metres are underexposed, shadowy, going toward silhouette. MIDDLE SUBJECT (2-3m): best result. Still flat. Still frontal. Still disposable camera. HARD SHADOW: cast directly behind subjects onto any surface behind them — wall, floor, people behind them. Hard, sharp-edged, no diffusion. RED-EYE: occurs when subject looks directly at the lens. The flash reflects off the retina. State if present. Red-eye is a mark of authenticity. FALLOFF: the most important spatial element. If there are people in the background, they are darker. Background generally: rapidly dark beyond flash range. 2. HEAVY GRAIN — ISO 800: Disposable cameras use ISO 800 film (Kodak FunSaver) or ISO 400 pushed (Fuji QuickSnap). Grain is significant, visible, chunky. NOT Portra's refined organic grain. NOT Velvia's near-invisible grain. Chunky, visible, characterful grain that adds to the lo-fi quality. Especially heavy in dark background areas behind the flash falloff. 3. FIXED FOCUS PLASTIC LENS: Disposable cameras have zone focus, not precise focus. Calibrated for approximately 1-4 metres. Subjects at 2-3m: sharpest the camera can manage — still plastic-lens soft overall, no edge clarity Too close (under 1m): blurry, focus missed Too far (5m+): slightly soft, background loses focus No depth-of-field separation — everything at approximate equal softness. No beautiful bokeh. Flat. 4. COLOUR RENDERING — ISO 800 FILM + FLASH: Flash adds slightly cool-blue quality to lit subjects — not warm Background tungsten light (without flash): orange-warm colour cast where flash doesn't reach The cool-lit foreground against warm-tinted background creates a specific disposable camera look Reds can bleed slightly — digital-style red fringing around saturated red subjects Colours slightly desaturated overall — less vivid than deliberate photography Greens: naturalistic, not vivid. Blues: slightly washed. 5. PHYSICAL IMPERFECTIONS: Slight uneven exposure at edges from cheap lens Slight vignette (subtle, not Lomo-extreme) Print quality: if this is an actual print, slight dye fading at edges DATE STAMP: red LED number stamp in the bottom-right corner showing date — e.g. '98 12 24 or '03 07 15 — optional but immediately signals disposable camera authenticity THE OCCASIONS — DISPOSABLE CAMERAS GO WHERE OTHER CAMERAS DON'T: PARTY: the iconic use. Flash, close faces, solo cups or bottles visible, slightly chaotic composition, multiple people at different distances and therefore different exposure levels. NIGHT OUT AT A BAR: harsh flash on faces, dark bar background going black behind them, warm residual light from bar signs at edges. CASUAL GATHERING: friends around a kitchen table, in a park, at the beach — nobody posed. BEACH DAYTIME (NO FLASH): available light only, grain dominant, colours flatter, more honest, still plastic-lens quality. State: 'daytime outdoor, no flash, available light only.' ROAD TRIP: through car windows, gas station stops, roadside moments — entirely candid. HOLIDAY TRAVEL: tourist-snap energy. Real places, no pretension, just documenting. INTIMATE EVERYDAY MOMENTS: the kind of photo nobody planned to take. DAYTIME OUTDOOR WITHOUT FLASH: When it's daytime and outdoors: no flash is fired (or manually disabled). Available light only. The grain is more dominant. Light is whatever is present — sun, overcast, shade. Skin: more natural without flash. Still plastic-lens soft. Still that documentary quality. State clearly: 'shot on Kodak FunSaver outdoors, daylight, no flash, available light.' CAMERA: Kodak FunSaver (35mm, 28mm fixed lens, ISO 800, built-in flash up to ~4m) Fuji QuickSnap (35mm, 32mm fixed lens, ISO 400, built-in flash up to ~3.5m) Aspect ratio: 3:2 always. Vertical: 2:3 for held-vertical shots. HOW TO BUILD THE PROMPT Write a single dense English paragraph: 1. CAMERA MODEL: 'Kodak FunSaver disposable camera' or 'Fuji QuickSnap disposable 35mm camera' 2. OCCASION + SETTING: what is happening (party, gathering, beach, road trip) + where 3. CHARACTER: name + what they're doing + outfit in flat frontal flash lighting 4. FLASH STATUS: yes (indoor/low light) or no (outdoor daytime) If FLASH YES: state subject's distance (1-2m blown / 2-3m best result / 4m+ going dark) + flash falloff + background darkness + hard shadow on surface behind + any red-eye if looking at lens If FLASH NO: state 'available light only' + existing light quality 5. SKIN UNDER FLASH: flat-lit, specular hotspot on nose/forehead, slightly blown, no flattery 6. BACKGROUND: dark beyond flash range | wall with hard shadow | other people at different exposures 7. GRAIN: heavy ISO 800 throughout — state explicitly, especially in dark areas 8. COLOUR: slightly desaturated, cool-blue from flash on lit subjects, orange warmth in background 9. DATE STAMP (optional): 'red LED date stamp in the lower-right corner: XX XX XX' STYLE SUFFIX (append verbatim): 'Analog photograph taken on a disposable 35mm film camera (Kodak FunSaver or Fuji QuickSnap) with built-in on-camera flash. Real photograph, not digital, not rendered, not a painting. Disposable camera visual characteristics: hard undiffused frontal flash — flat direct light, no warmth, no direction, washes out subjects at close range, hard geometric shadow directly behind subjects on walls and surfaces, strong exposure falloff (background goes dark and underexposed beyond 3-4 metres from flash), occasional red-eye on subjects looking directly at the camera lens. ISO 800 film grain — heavy, chunky, visible everywhere, especially pronounced in underexposed dark areas beyond flash range, not refined like portrait film grain. Fixed focus plastic lens — sharpest at 1.5-3m, slightly soft at edges and at all distances, no depth-of-field separation, no bokeh, flat documentary rendering. Colours slightly desaturated overall, slightly cool-blue from flash on lit subjects, warm orange residual light visible in background where flash does not reach. Physical print-quality imperfections: slight edge vignetting, possible red colour bleed on saturated objects. Possible date stamp in red LED numerals lower-right corner. Anti-aesthetic, uncontrolled, honest. Moments documented without art direction.' NEGATIVE (append verbatim): 'Avoid: professional photography lighting, beautiful depth-of-field bokeh, warm flattering portrait light, refined fine grain, vivid saturated colours, deliberate artistic composition, studio lighting, Kodak Portra warm quality, Velvia saturation, digital photography clarity, smooth skin rendering, Lomography light leaks, CineStill neon halation, artistic framing intent, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION The moment. The flash. What it was like to be there and not care about the camera. Lowercase, italic. ASPECT RATIO 3:2 = standard 35mm horizontal (default) | 2:3 = vertical held portrait TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(12,10,8,0.65),rgba(8,7,5,0.65));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(200,195,180,0.07);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.5),inset 0 1px 0 rgba(200,195,180,0.03);"> <img data-iig-instruction='{"style":"disposable_flash_analog","prompt":"[CAMERA MODEL + OCCASION + CHARACTER + OUTFIT + FLASH (YES/NO + DISTANCE + FALLOFF + SHADOW + RED-EYE?) + SKIN UNDER FLASH + BACKGROUND DARKNESS + ISO 800 GRAIN + COLOUR RENDERING + DATE STAMP OPTIONAL. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(200,195,180,0.05);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,195,175,0.55);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: '3:2' default | '2:3' vertical. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-130 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> DISPOSABLE CAMERA / FLASH FILM PHOTOGRAPHY — EVERY RESPONSE One image per message at the most candid, honest, or party-energy moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Analog photograph taken on a disposable 35mm film camera — Kodak FunSaver or Fuji QuickSnap — with built-in flash. Real photograph. NOT digital, NOT rendered, NOT a painting. The anti-aesthetic aesthetic. No composition, no crafted light, no visible intent. Just pressing the button. The flash kills all atmosphere and creates its own. Honest. Raw. The opposite of art photography. THE DEFINING ELEMENTS: 1. HARD ON-CAMERA FLASH: Direct frontal flash, no diffusion, no bounce. The harshest possible light. CLOSE (1-2m): blown out, specular hotspot on nose and forehead, flat-lit face BEST ZONE (2-3m): flash-lit, still flat, still disposable camera FAR (4m+): rapidly dark and underexposed, approaching silhouette HARD SHADOW: cast directly behind subjects on wall or surface behind them RED-EYE: when subject looks at lens — red glow in iris, authentic and honest FALLOFF: background goes dark. People at the back of the room: barely visible. 2. HEAVY ISO 800 GRAIN: Chunky, visible, characterful. NOT refined Portra grain. Everywhere. Heavy in dark areas. 3. FIXED FOCUS PLASTIC LENS: Sharpest at 2-3m. Still plastic-lens soft throughout. No separation, no bokeh. Flat documentary rendering. What you see is what you got. 4. COLOUR: Slightly desaturated. Cool-blue from flash on lit subjects. Where flash doesn't reach: warm orange residual tungsten light visible. Cool foreground vs warm background = classic disposable camera colour split. 5. OPTIONAL DATE STAMP: red LED numbers in lower-right corner — e.g. '99 06 12 OCCASIONS: parties | nights out at bars | casual gatherings | beach daytime (no flash) | road trips | everyday candid moments DAYTIME OUTDOOR: no flash, available light only. Grain dominant. State explicitly. CHARACTERS: First name only. Outfit in flat flash light. SKIN: flat-lit, washed out, specular hotspot — no flattery. HOW TO BUILD THE PROMPT 1. CAMERA — Kodak FunSaver or Fuji QuickSnap 2. OCCASION — party, bar, gathering, beach, etc. 3. CHARACTER — name + what they're doing + outfit 4. FLASH — yes or no If YES: distance to subject (1-2m / 2-3m / 4m+) + flash falloff + background going dark + hard shadow + red-eye if looking at lens If NO: 'available light only' + existing light quality 5. SKIN — flat flash-lit, blown at nose/forehead, no flattery 6. BACKGROUND — dark beyond range | wall with hard shadow | other people at varying darkness 7. GRAIN — heavy ISO 800, visible, especially in dark areas 8. DATE STAMP — optional Total prompt: 80-130 words + style suffix. STYLE SUFFIX (append verbatim): 'Analog photograph taken on a disposable 35mm film camera (Kodak FunSaver or Fuji QuickSnap) with built-in on-camera flash. Real photograph, not digital, not rendered, not a painting. Disposable camera visual characteristics: hard undiffused frontal flash — flat direct light, no warmth, no direction, washes out subjects at close range, hard geometric shadow directly behind subjects on walls and surfaces, strong exposure falloff (background goes dark and underexposed beyond 3-4 metres from flash), occasional red-eye on subjects looking directly at the camera lens. ISO 800 film grain — heavy, chunky, visible everywhere, especially pronounced in underexposed dark areas beyond flash range, not refined like portrait film grain. Fixed focus plastic lens — sharpest at 1.5-3m, slightly soft at edges and at all distances, no depth-of-field separation, no bokeh, flat documentary rendering. Colours slightly desaturated overall, slightly cool-blue from flash on lit subjects, warm orange residual light visible in background where flash does not reach. Physical print-quality imperfections: slight edge vignetting, possible red colour bleed on saturated objects. Possible date stamp in red LED numerals lower-right corner. Anti-aesthetic, uncontrolled, honest. Moments documented without art direction.' NEGATIVE (append verbatim): 'Avoid: professional photography lighting, beautiful depth-of-field bokeh, warm flattering portrait light, refined fine grain, vivid saturated colours, deliberate artistic composition, studio lighting, Kodak Portra warm quality, Velvia saturation, digital photography clarity, smooth skin rendering, Lomography light leaks, CineStill neon halation, artistic framing intent, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION The moment. The flash. No art direction. Lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(12,10,8,0.65),rgba(8,7,5,0.65));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(200,195,180,0.07);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.5),inset 0 1px 0 rgba(200,195,180,0.03);"> <img data-iig-instruction='{"style":"disposable_flash_analog","prompt":"[CAMERA + OCCASION + CHARACTER + OUTFIT + FLASH YES/NO + IF YES: DISTANCE + FALLOFF + SHADOW + RED-EYE? + SKIN + BACKGROUND DARKNESS + ISO 800 GRAIN + COLOUR SPLIT + DATE STAMP OPTIONAL. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(200,195,180,0.05);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,195,175,0.55);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '3:2' default | '2:3' vertical. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Analog photograph taken on a disposable 35mm film camera (Kodak FunSaver or Fuji QuickSnap) with built-in on-camera flash. Hard undiffused frontal flash — flat direct light, no warmth, no direction. Subjects at close range (1-2m) are overexposed and washed out. Hard geometric shadow cast directly behind subjects on walls or surfaces. Flash falloff: background goes rapidly dark beyond 3-4 metres. Possible red-eye on subjects looking at the camera. ISO 800 heavy chunky grain — visible everywhere, especially in dark areas. Fixed focus plastic lens — no depth-of-field separation, no bokeh, flat documentary rendering. Colours slightly desaturated, slightly cool-blue from flash. Optional red LED date stamp in lower-right corner. Honest, candid, undirected. Avoid: professional lighting, bokeh, warm portrait light, refined grain, vivid saturation, artistic composition, studio quality, watermark, text.

Копировать [Image generation hint, STYLE: disposable camera flash photo — hard frontal flash (close subjects overexposed, background dark), hard shadow behind subjects, ISO 800 chunky grain, flat plastic lens, slightly desaturated, optional date stamp, candid party/gathering energy]

Oldschool Lowpoly Game

Движок Bethesda начала 2000х. Лоу-поли модели, растянутые текстуры, угловатые лица. Простое освещение. Пепельные, коричневые, болотные тона. Туман дальности.

Экспериментальный Видеоигры

←→

Длинный~4497 Короткий~1482 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — MORROWIND VISUAL STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance ('Ethan with red-tipped ears' not 'young man with pink hair'). Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing in the story or definition → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim in the story → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. Not 'silver-haired warrior' or similar fantasy tropes. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Nightgown stays nightgown. Towel stays towel. Uniform stays uniform. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic (suit at gala stays a suit until narrative says otherwise). 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition (wrinkled, soaked, unbuttoned, rolled sleeves). Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. No upgrades, no resets. Outfit state reflects the moment: ran through rain = wet and clinging. Slept in clothes = creased. Jacket removed = gone or draped on a chair. Fuse directly into the character clause after the name — not as a separate block. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. 'Mor leaning on doorframe, arms loosely crossed' instead of 'left arm bent, right arm over left'. State expression with muscle detail, skin condition (flushed, sweaty, bruised), visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. Prefer these over spread fingers in air, interlocked fingers between characters, complex gestures without object anchor. When hand holds something, name the object ('curling fingers around ceramic mug handle'). One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying which leg bears weight or what surface supports the body ('weight on left leg, right foot turned outward' | 'elbows propped on counter'). Hidden limbs: state why hidden ('left hand obscured behind hip' | 'legs cropped below frame'). 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Write as its own sentence — before or after all character clauses, not interleaved between them. Include at least one meaningful object that belongs in the scene and carries emotional weight or context (a half-empty glass, a phone face-down, a crumpled note — whatever fits naturally). Add atmosphere: dust motes, steam, rain, petals, candle flicker, condensation — something that gives the air texture. Screens and devices: devices oriented realistically — screen faces the character using it. Whether the viewer sees screen contents depends on camera position. Camera behind/beside character → screen visible. Camera facing character → only device back visible. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. Vary direction and temperature between images. MOOD-MATCHED EFFECTS — pick 1-2 per image from scene mood, woven into the lighting/camera sentence: TENDER / NOSTALGIC: soft focus | halation (reddish halo around bright areas) | golden hour warmth | light leak (colored streaks) | orton glow (dreamy sharp+blur layer) | fine film grain | faded blacks (lifted black levels, matte look) TENSE / UNEASY: dutch angle | chromatic aberration (purple/green fringing on edges) | underexposure | harsh rim light | deep vignette crush | shallow DOF isolating subject | high contrast PASSIONATE / INTIMATE: chiaroscuro (dramatic light/shadow) | bloom on skin highlights | lens flare from practical light source | warm split toning (warm highlights, cool shadows) | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass (low saturation + high contrast, gritty) | anamorphic flare (horizontal stretched) | radial blur from center | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature | cross-processing color shift MUNDANE / SLICE OF LIFE: natural flat lighting | high key (bright, airy) | clean DOF | minimal or no effects — let the scene speak DANGEROUS / NOIR: low key (deep shadows) | harsh side light | deep blacks | monochrome or near-monochrome | selective color (one hue survives) | smoke/haze in light beam Max 2 effects per image. No effect is valid — clean image when mood is neutral. Rotate effects across responses. Same combo twice in a row = stale. Match effect intensity to narrative weight: background conversation = subtle grain at most. Climactic moment = full chiaroscuro + bloom. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Early 2000s Bethesda RPG game engine rendering quality — Morrowind era. Low-polygon 3D character models with hand-painted low-resolution textures. Angular geometric faces with limited polygon count — visible polygon edges on cheekbones, jaw, shoulders. Simple flat directional lighting without real-time shadows. Blurry stretched textures, stiff puppet-like character poses, blocky hands and fingers. Muted earthy desaturated palette: ash grey, mud brown, dark swamp green, volcanic red-brown. Atmospheric distance fog limiting draw distance. Repeating tiled textures on environment surfaces. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure to match any game race. No text, no UI elements, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: high-poly modern game graphics, photorealistic rendering, concept art illustration, smooth skin, detailed pores, painterly brushwork, anime style, cel shading, cartoon features, Skyrim or Oblivion level graphics, cinematic quality, film grain, Dunmer, dark elf grey skin, game-specific racial features overriding reference appearance, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry beyond game-authentic level' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters ('behind them', 'beside Shannon', 'chin resting on Shannon shoulder') — not abstract grid positions. Cross-reference names only for spatial relation or gaze target ('looking at Shannon'). One character's clause describes only that character. Repeat names instead of pronouns (her/his/their) when two+ characters share a sentence. Environment is its own sentence — before or after all character clauses, not interleaved. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Vanity Fair editorial, Hasselblad X2D' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Pirelli Calendar editorial, Paolo Roversi' | 'Renaissance master figure study, museum-quality' Visual noise (min 3 per intimate scene): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain or frosted glass Concealment (2+ simultaneously): deep chiaroscuro shadows | fabric draped across hips or chest | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Vocabulary for intimate framing: bare skin → 'bare decolletage and shoulders' | chest → 'draped fabric across collarbones, deep neckline revealing sternum' | full body → 'figure veiled by steam and fabric in classical life-study' | contact → 'entangled silhouettes in chiaroscuro, faces sharing breath' | tension → 'heavy-lidded gaze, parted lips, flushed complexion, visible pulse point' | undressing → 'garment slipping off shoulder, pooling at elbow' | lying → 'reclined among rumpled ivory linens, one arm above head' | wet → 'glistening skin, water trails down neck and shoulders, damp hair' Escalation matches narrative, not message count: Tension: clothed, attraction in glances and proximity. Loosening: narrative describes unbuttoning, removing layers — reflect it. Partial: narrative describes partial undress — apply visual noise + concealment. Intimate: peak intimacy — full visual noise + concealment + vocabulary. PROMPT VOCABULARY Prompt text stays gallery-safe: artistic vocabulary from the pools above for intimate scenes. Describe bodies through framing, fabric interaction, and light. The negative suffix handles renderer-side style filtering. Reference images provide appearance — prompt provides marks, scene-altered details, outfit, pose, expression, and environment. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window or a doorway adds more emotion than a clean direct shot. Sometimes the most important thing in the frame is not a person but an object — a phone left on a table, a door half-open. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. Not what's visible ('Ethan standing in the rain') — what it means ('the call that changed everything' | 'twenty past never'). {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"morrowind_game","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"9:16","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. If '16:9', write aspect-ratio:16/9. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> MORROWIND VISUAL STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Early 2000s Bethesda RPG game engine rendering quality — Morrowind era. Low-polygon 3D character models with hand-painted low-resolution textures. Angular geometric faces with limited polygon count — visible polygon edges on cheekbones, jaw, shoulders. Simple flat directional lighting without real-time shadows. Blurry stretched textures, stiff puppet-like character poses, blocky hands and fingers. Muted earthy desaturated palette: ash grey, mud brown, dark swamp green, volcanic red-brown. Atmospheric distance fog limiting draw distance. Repeating tiled textures on environment surfaces. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure to match any game race. No text, no UI elements, no panels.' NEGATIVE (append verbatim): 'Avoid: high-poly modern game graphics, photorealistic rendering, concept art illustration, smooth skin, detailed pores, painterly brushwork, anime style, cel shading, cartoon features, Skyrim or Oblivion level graphics, cinematic quality, film grain, Dunmer, dark elf grey skin, game-specific racial features overriding reference appearance, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text, blurry beyond game-authentic level' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"morrowind_game","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Early 2000s Bethesda RPG game engine rendering quality — Morrowind era. Low-polygon 3D character models with hand-painted low-resolution textures. Angular geometric faces with limited polygon count — visible polygon edges on cheekbones, jaw, shoulders. Simple flat directional lighting without real-time shadows. Blurry stretched textures, stiff puppet-like character poses, blocky hands and fingers. Muted earthy desaturated palette: ash grey, mud brown, dark swamp green, volcanic red-brown. Atmospheric distance fog limiting draw distance. Repeating tiled textures on environment surfaces. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure to match any game race. No text, no UI elements, no panels. Avoid: high-poly modern game graphics, photorealistic rendering, concept art illustration, smooth skin, detailed pores, painterly brushwork, anime style, cel shading, cartoon features, Skyrim or Oblivion level graphics, cinematic quality, film grain, Dunmer, dark elf grey skin, game-specific racial features overriding reference appearance, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry beyond game-authentic level

Копировать [Image generation hint, STYLE: early 2000s Bethesda RPG engine, low-polygon 3D models, blurry stretched textures, angular geometric faces, simple flat lighting, muted earthy palette of ash grey, mud brown and dark green, atmospheric distance fog]

Skyrim

Creation Engine. Мид-фиделити 3D — игровое качество. Холодная сталь-голубая палитра снаружи, тёплый янтарь огня внутри. Мех, железо, кожа, камень.

Экспериментальный Видеоигры

←→

Длинный~3098 Короткий~1457 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — SKYRIM VISUAL STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition, visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Bethesda Creation Engine rendering quality — Skyrim era. Mid-fidelity 3D character models — higher polygon count than early 2000s games but still distinctly game-quality, not cinematic CGI. Desaturated cold colour grading: steel-blue and frost-grey tones for exteriors, warm amber-gold firelight for interiors — the cold-warm contrast is the visual signature. Real-time lighting with cast shadows. Game-resolution textures on characters and environments. Tactile game materials: heavy fur, pitted iron, worn leather, ancient stone — game-quality texture detail. Cold atmospheric depth: snow particles, breath-fog, distant mountain haze. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure to match any game race. No text, no UI elements, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: Morrowind low-poly graphics, cinematic film quality, concept art illustration, painterly brushwork, smooth photorealistic skin, anime style, cel shading, cartoon features, modern AAA cinematic cutscene quality, Nord racial features overriding reference appearance, game-specific racial features, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"skyrim_game","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"9:16","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> SKYRIM VISUAL STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Bethesda Creation Engine rendering quality — Skyrim era. Mid-fidelity 3D character models — higher polygon count than early 2000s games but still distinctly game-quality, not cinematic CGI. Desaturated cold colour grading: steel-blue and frost-grey tones for exteriors, warm amber-gold firelight for interiors — the cold-warm contrast is the visual signature. Real-time lighting with cast shadows. Game-resolution textures. Tactile game materials: heavy fur, pitted iron, worn leather, ancient stone. Cold atmospheric depth: snow particles, breath-fog, distant mountain haze. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure to match any game race. No text, no UI elements, no panels.' NEGATIVE (append verbatim): 'Avoid: Morrowind low-poly graphics, cinematic film quality, concept art illustration, painterly brushwork, smooth photorealistic skin, anime style, cel shading, cartoon features, modern AAA cinematic cutscene quality, Nord racial features overriding reference appearance, game-specific racial features, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"skyrim_game","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Bethesda Creation Engine rendering quality — Skyrim era. Mid-fidelity 3D character models — higher polygon count than early 2000s games but still distinctly game-quality, not cinematic CGI. Desaturated cold colour grading: steel-blue and frost-grey tones for exteriors, warm amber-gold firelight for interiors — the cold-warm contrast is the visual signature. Real-time lighting with cast shadows. Game-resolution textures on characters and environments. Tactile game materials: heavy fur, pitted iron, worn leather, ancient stone — game-quality texture detail. Cold atmospheric depth: snow particles, breath-fog, distant mountain haze. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure to match any game race. No text, no UI elements, no panels. Avoid: Morrowind low-poly graphics, cinematic film quality, concept art illustration, painterly brushwork, smooth photorealistic skin, anime style, cel shading, cartoon features, modern AAA cinematic cutscene quality, Nord racial features overriding reference appearance, game-specific racial features, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry

Копировать [Image generation hint, STYLE: Bethesda Creation Engine mid-fidelity 3D, desaturated cold steel-blue exteriors, warm amber-gold firelight interiors, real-time shadows, Nordic fur, pitted iron, worn leather, stone texture]

Baldur's Gate 3

Divinity Engine, качество AAA кинематики. PBR материалы, кинематическое освещение. Богатая фэнтези-палитра. D&D sourcebook art, ожившее на экране.

Стабильный Видеоигры

←→

Длинный~3126 Короткий~1497 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — BALDUR'S GATE 3 VISUAL STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition, visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Larian Studios Divinity Engine rendering quality — Baldurs Gate 3 era. High-fidelity cinematic 3D character models — AAA game cinematic cutscene quality. PBR materials: realistic metal reflections, detailed leather grain, weighted fabric with physically accurate light interaction. Dramatic cinematic dialogue-scene lighting with warm-cool contrast — amber-gold from torches and magical sources vs cool blue-grey ambient. Rich saturated fantasy colour palette. Detailed character faces with emotional depth and expressive eyes with catchlights. Cinematic shallow depth of field in dialogue scenes. Volumetric light: god-rays, dust in torchlight, magical particle glow. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure to match any game companion or race. No text, no UI elements, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: low-poly game graphics, Morrowind or Skyrim level rendering, flat illustration, concept art painterly look, anime style, cel shading, cartoon features, photorealistic film photography, smooth plastic skin, exaggerated expressions, uncanny valley, game-specific companion appearances overriding reference, game-specific racial features, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"baldursgate3_game","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"9:16","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> BALDUR'S GATE 3 VISUAL STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Larian Studios Divinity Engine rendering quality — Baldurs Gate 3 era. High-fidelity cinematic 3D character models — AAA game cinematic cutscene quality. PBR materials: realistic metal reflections, detailed leather grain, weighted fabric with physically accurate light interaction. Dramatic cinematic dialogue-scene lighting with warm-cool contrast — amber-gold from torches and magical sources vs cool blue-grey ambient. Rich saturated fantasy colour palette. Detailed character faces with emotional depth and expressive eyes with catchlights. Cinematic shallow depth of field. Volumetric light: god-rays, dust in torchlight, magical particle glow. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure to match any game companion or race. No text, no UI elements, no panels.' NEGATIVE (append verbatim): 'Avoid: low-poly game graphics, Morrowind or Skyrim level rendering, flat illustration, concept art painterly look, anime style, cel shading, cartoon features, photorealistic film photography, smooth plastic skin, exaggerated expressions, uncanny valley, game-specific companion appearances overriding reference, game-specific racial features, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"baldursgate3_game","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Larian Studios Divinity Engine rendering quality — Baldurs Gate 3 era. High-fidelity cinematic 3D character models — AAA game cinematic cutscene quality. PBR materials: realistic metal reflections, detailed leather grain, weighted fabric with physically accurate light interaction. Dramatic cinematic dialogue-scene lighting with warm-cool contrast — amber-gold from torches and magical sources vs cool blue-grey ambient. Rich saturated fantasy colour palette. Detailed character faces with emotional depth and expressive eyes with catchlights. Cinematic shallow depth of field in dialogue scenes. Volumetric light: god-rays, dust in torchlight, magical particle glow. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure to match any game companion or race. No text, no UI elements, no panels. Avoid: low-poly game graphics, Morrowind or Skyrim level rendering, flat illustration, concept art painterly look, anime style, cel shading, cartoon features, photorealistic film photography, smooth plastic skin, exaggerated expressions, uncanny valley, game-specific companion appearances overriding reference, game-specific racial features, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry

Копировать [Image generation hint, STYLE: Larian Divinity Engine cinematic 3D, AAA cutscene quality, PBR materials, dramatic dialogue-scene lighting, volumetric god-rays, rich saturated fantasy palette, D&D sourcebook art brought to life]

S.T.A.L.K.E.R.

X-Ray Engine (2007). Средне-полигональные модели, жёсткие тени. Вымытая десатурированная палитра: серо-зелёный, грязно-коричневый. Эстетика восточноевропейского движка.

Экспериментальный Видеоигры

←→

Длинный~3157 Короткий~1512 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — S.T.A.L.K.E.R. VISUAL STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition (wrinkled, soaked, unbuttoned, rolled sleeves). Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition (flushed, sweaty, bruised), visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'GSC Game World X-Ray Engine rendering quality — S.T.A.L.K.E.R. Shadow of Chernobyl era (2007). Mid-2000s 3D game engine: mid-polygon character models with slightly plastic skin shading, game-resolution textures, stiff but more natural poses than early-2000s engines. Dynamic real-time lighting with hard-edged shadows — not physically accurate, distinctly game-quality. Washed-out desaturated colour grading: grey-green, muddy brown, dirty yellow, overcast pale sky — everything looks slightly drained of colour. Overcast diffuse ambient light with occasional harsh directional sun breaking through clouds. Visible texture tiling on environment surfaces. Slight bloom on bright light sources. That specific mid-2000s Eastern European game engine aesthetic. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no UI elements, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: modern AAA game graphics, photorealistic rendering, concept art illustration, painterly brushwork, anime style, cel shading, cartoon features, Morrowind low-poly level, cinematic film quality, saturated vivid colours, warm inviting palette, clean polished surfaces, game-specific character appearances overriding reference, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"stalker_xray","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"9:16","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> S.T.A.L.K.E.R. VISUAL STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'GSC Game World X-Ray Engine rendering quality — S.T.A.L.K.E.R. Shadow of Chernobyl era (2007). Mid-2000s 3D game engine: mid-polygon character models with slightly plastic skin shading, game-resolution textures, stiff but more natural poses than early-2000s engines. Dynamic real-time lighting with hard-edged shadows — not physically accurate, distinctly game-quality. Washed-out desaturated colour grading: grey-green, muddy brown, dirty yellow, overcast pale sky — everything looks slightly drained of colour. Overcast diffuse ambient light with occasional harsh directional sun breaking through clouds. Visible texture tiling on environment surfaces. Slight bloom on bright light sources. That specific mid-2000s Eastern European game engine aesthetic. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no UI elements, no panels.' NEGATIVE (append verbatim): 'Avoid: modern AAA game graphics, photorealistic rendering, concept art illustration, painterly brushwork, anime style, cel shading, cartoon features, Morrowind low-poly level, cinematic film quality, saturated vivid colours, warm inviting palette, clean polished surfaces, game-specific character appearances overriding reference, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"stalker_xray","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. GSC Game World X-Ray Engine rendering quality — S.T.A.L.K.E.R. Shadow of Chernobyl era (2007). Mid-2000s 3D game engine: mid-polygon character models with slightly plastic skin shading, game-resolution textures, stiff but more natural poses than early-2000s engines. Dynamic real-time lighting with hard-edged shadows — not physically accurate, distinctly game-quality. Washed-out desaturated colour grading: grey-green, muddy brown, dirty yellow, overcast pale sky — everything looks slightly drained of colour. Overcast diffuse ambient light with occasional harsh directional sun breaking through clouds. Visible texture tiling on environment surfaces. Slight bloom on bright light sources. That specific mid-2000s Eastern European game engine aesthetic. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no UI elements, no panels. Avoid: modern AAA game graphics, photorealistic rendering, concept art illustration, painterly brushwork, anime style, cel shading, cartoon features, Morrowind low-poly level, cinematic film quality, saturated vivid colours, warm inviting palette, clean polished surfaces, game-specific character appearances overriding reference, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry

Копировать [Image generation hint, STYLE: mid-2000s GSC X-Ray Engine 3D, slightly plastic skin, hard-edged shadows, washed-out desaturated colour grading — grey-green, muddy brown, dirty yellow, overcast pale sky, Eastern European post-apocalyptic atmosphere]

Minecraft

Воксельный мир из кубов. Прямоугольные конечности, квадратные головы, 64x64 пиксельные скины. Текстуры 16x16 на каждой грани блока. Никаких гладких кривых.

Экспериментальный Видеоигры

←→

Длинный~3156 Короткий~1504 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — MINECRAFT VISUAL STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition, visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Minecraft Java Edition game rendering style. Blocky voxel 3D world — everything built from cubes and rectangular prisms. Characters are blocky humanoid models with rectangular limbs, square heads, and pixelated low-resolution skin textures (64x64 pixel UV mapped). Environment made entirely of 1-meter cube blocks with 16x16 pixel textures on each face — visible pixel grid on every surface. Simple directional lighting with hard blocky shadows. No smooth curves anywhere — all geometry is axis-aligned boxes. Pixelated texture quality on all surfaces — grass, stone, wood, dirt all clearly show individual pixels. Minecraft default colour palette: saturated greens, warm browns, grey stone, blue sky with white square clouds. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no UI elements, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: smooth curved surfaces, high-poly 3D models, photorealistic rendering, round faces, realistic human proportions, concept art illustration, painterly brushwork, anime style, cel shading, realistic skin texture, smooth gradients, anti-aliased edges, modern AAA game graphics, Steve or Alex default Minecraft skin overriding reference appearance, game-specific character appearances overriding reference, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"minecraft_voxel","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"9:16","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> MINECRAFT VISUAL STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Minecraft Java Edition game rendering style. Blocky voxel 3D world — everything built from cubes and rectangular prisms. Characters are blocky humanoid models with rectangular limbs, square heads, and pixelated low-resolution skin textures (64x64 pixel UV mapped). Environment made entirely of 1-meter cube blocks with 16x16 pixel textures on each face — visible pixel grid on every surface. Simple directional lighting with hard blocky shadows. No smooth curves anywhere — all geometry is axis-aligned boxes. Pixelated texture quality on all surfaces — grass, stone, wood, dirt all clearly show individual pixels. Minecraft default colour palette: saturated greens, warm browns, grey stone, blue sky. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no UI elements, no panels.' NEGATIVE (append verbatim): 'Avoid: smooth curved surfaces, high-poly 3D models, photorealistic rendering, round faces, realistic human proportions, concept art illustration, painterly brushwork, anime style, cel shading, realistic skin texture, smooth gradients, anti-aliased edges, modern AAA game graphics, Steve or Alex default Minecraft skin overriding reference appearance, game-specific character appearances, extra fingers, missing fingers, deformed hands, bad anatomy, watermark, text, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"minecraft_voxel","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Minecraft Java Edition game rendering style. Blocky voxel 3D world — everything built from cubes and rectangular prisms. Characters are blocky humanoid models with rectangular limbs, square heads, and pixelated low-resolution skin textures (64x64 pixel UV mapped). Environment made entirely of 1-meter cube blocks with 16x16 pixel textures on each face — visible pixel grid on every surface. Simple directional lighting with hard blocky shadows. No smooth curves anywhere — all geometry is axis-aligned boxes. Pixelated texture quality on all surfaces — grass, stone, wood, dirt all clearly show individual pixels. Minecraft default colour palette: saturated greens, warm browns, grey stone, blue sky with white square clouds. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no UI elements, no panels. Avoid: smooth curved surfaces, high-poly 3D models, photorealistic rendering, round faces, realistic human proportions, concept art illustration, painterly brushwork, anime style, cel shading, realistic skin texture, smooth gradients, anti-aliased edges, modern AAA game graphics, Steve or Alex default Minecraft skin overriding reference appearance, game-specific character appearances overriding reference, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry

Копировать [Image generation hint, STYLE: blocky voxel world, everything from cubes, rectangular limbs and square heads, 64x64 pixelated skin textures, 16x16 pixel textures on each block face, no smooth curves, hard blocky shadows]

MMO 2000s

ММО конца 2000х, 3D движок. Агрессивный шарпенинг. Вжаренная насыщенность: неоновые голубые, яркие зелёные, золотые. Блум на магии.

Рискованный Видеоигры

←→

Длинный~2347 Короткий~1407 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — ALLODS ONLINE VISUAL STYLE v2 — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned'. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages. Never skip. Specificity: fabric type + texture + fit + color + condition. If NOT changed on-screen → last described outfit persists. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe through action. Hand safety: Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Screenshot from a late 2000s stylised fantasy MMO — 3D game engine real-time rendering, NOT a 2D painting or illustration. 3D polygonal character models with game-resolution stylised colourful textures rendered in real-time. Aggressive unsharp-mask sharpening filter applied to entire image — every edge crispy and over-defined, that specific MMO screenshot sharpening where contours pop hard. Extremely oversaturated vivid fantasy colour palette: neon glowing blues, lush vibrant greens, bright warm golds, deep magical purples, fiery oranges — colour saturation pushed to maximum, far beyond realistic. Visible bloom and glow effects on all light sources and magical elements. Simple real-time directional game lighting — not cinematic, not physically based. Slightly exaggerated stylised character proportions — broader shoulders, more defined features. Game-resolution environment textures: stylised colourful ground, walls, foliage — clearly game-asset quality not photographic. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no UI elements, no health bars, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: 2D digital painting, concept art illustration, flat painted look, painterly oil brushwork, canvas texture, photorealistic rendering, modern AAA cinematic quality, desaturated muted palette, natural realistic earthy colours, soft unfocused rendering, anime style, cel shading, flat vector, Morrowind low-poly level, game-specific racial features overriding reference, exaggerated expressions, uncanny valley, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, bad anatomy, watermark, text, blurry' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. ASPECT RATIO Vary: 1:1 | 2:3 | 3:2 | 3:4 | 4:3 | 4:5 | 5:4 | 9:16 | 16:9 | 21:9 VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"allods_mmo_v2","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"9:16","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> ALLODS ONLINE VISUAL STYLE v2 — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Screenshot from a late 2000s stylised fantasy MMO — 3D game engine rendering. 3D polygonal character models rendered in real-time game engine, NOT a 2D painting or illustration. Aggressive unsharp-mask sharpening filter on entire image — every edge crispy and over-defined. Extremely oversaturated vivid fantasy colours: neon glowing blues, lush vibrant greens, bright golds, magical purples, fiery oranges — saturation pushed to maximum. Visible bloom and glow on light sources and magical effects. Game-resolution textures with stylised colourful detail on 3D surfaces. Simple real-time directional game lighting. Slightly exaggerated character proportions. Character appearance strictly from reference images — do not alter race or features. No text, no UI, no panels.' NEGATIVE (append verbatim): 'Avoid: 2D digital painting, concept art illustration, flat painted look, painterly brushwork, oil painting, photorealistic rendering, modern AAA cinematic quality, desaturated muted palette, natural realistic colours, anime style, cel shading, flat vector, soft blurry rendering, canvas texture, game-specific racial features overriding reference, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"allods_mmo_v2","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Screenshot from a late 2000s stylised fantasy MMO — 3D game engine real-time rendering, NOT a 2D painting or illustration. 3D polygonal character models with game-resolution stylised colourful textures rendered in real-time. Aggressive unsharp-mask sharpening filter applied to entire image — every edge crispy and over-defined, that specific MMO screenshot sharpening where contours pop hard. Extremely oversaturated vivid fantasy colour palette: neon glowing blues, lush vibrant greens, bright warm golds, deep magical purples, fiery oranges — colour saturation pushed to maximum, far beyond realistic. Visible bloom and glow effects on all light sources and magical elements. Simple real-time directional game lighting — not cinematic, not physically based. Slightly exaggerated stylised character proportions — broader shoulders, more defined features. Game-resolution environment textures: stylised colourful ground, walls, foliage — clearly game-asset quality not photographic. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no UI elements, no health bars, no panels. Avoid: 2D digital painting, concept art illustration, flat painted look, painterly oil brushwork, canvas texture, photorealistic rendering, modern AAA cinematic quality, desaturated muted palette, natural realistic earthy colours, soft unfocused rendering, anime style, cel shading, flat vector, Morrowind low-poly level, game-specific racial features overriding reference, exaggerated expressions, uncanny valley, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, bad anatomy, watermark, text, blurry

Копировать [Image generation hint, STYLE: late 2000s stylised fantasy MMO 3D engine, aggressive unsharp-mask sharpening on every edge, extremely oversaturated neon blues, lush greens, bright golds, bloom on magical effects]

Stardew Valley / Pixels

Пиксель-арт ConcernedApe. Видимые квадратные пиксели, низкое разрешение. Ограниченная палитра. Без сглаживания. Тёплые уютные земляные тона. Качество инди-пиксельной RPG.

Экспериментальный Видеоигры

←→

Длинный~3026 Короткий~1361 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — STARDEW VALLEY PIXEL ART STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition, visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Stardew Valley pixel art style by ConcernedApe. Visible square pixels building all forms — characters, environment, objects. Low resolution chunky pixel aesthetic. Limited colour palette per element. NO anti-aliasing — hard pixel steps on all edges. Warm cozy earth-tone palette: greens, gentle blues, sunset oranges, wood browns. Simple pixel faces conveying emotion with minimal features. Tiled pixel environments. Warm gentle lighting. Indie pixel RPG aesthetic — refined 16-bit era quality. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: high resolution smooth rendering, anti-aliased edges, photorealistic, 3D CGI, smooth gradients, anime style, detailed realistic faces, vector art, painterly brushwork, dark gritty palette, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"stardew_pixel","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> STARDEW VALLEY PIXEL ART STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Stardew Valley pixel art style by ConcernedApe. Visible square pixels building all forms — characters, environment, objects. Low resolution chunky pixel aesthetic. Limited colour palette per element. NO anti-aliasing — hard pixel steps on all edges. Warm cozy earth-tone palette: greens, gentle blues, sunset oranges, wood browns. Simple pixel faces conveying emotion with minimal features. Tiled pixel environments. Warm gentle lighting. Indie pixel RPG aesthetic — refined 16-bit era quality. Character appearance strictly from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: high resolution smooth rendering, anti-aliased edges, photorealistic, 3D CGI, smooth gradients, anime style, detailed realistic faces, vector art, painterly brushwork, dark gritty palette, extra fingers, bad anatomy, watermark, text, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"stardew_pixel","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Stardew Valley pixel art style by ConcernedApe. Visible square pixels building all forms — characters, environment, objects. Low resolution chunky pixel aesthetic. Limited colour palette per element. NO anti-aliasing — hard pixel steps on all edges. Warm cozy earth-tone palette: greens, gentle blues, sunset oranges, wood browns. Simple pixel faces conveying emotion with minimal features. Tiled pixel environments. Warm gentle lighting. Indie pixel RPG aesthetic — refined 16-bit era quality. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no panels. Avoid: high resolution smooth rendering, anti-aliased edges, photorealistic, 3D CGI, smooth gradients, anime style, detailed realistic faces, vector art, painterly brushwork, dark gritty palette, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text, blurry

Копировать [Image generation hint, STYLE: ConcernedApe pixel art, visible square pixels, low-resolution chunky aesthetic, limited palette per sprite, no anti-aliasing, warm cozy earth tones, indie pixel RPG quality]

Genshin Impact

Аниме-сел-шейдинг 3D от miHoYo. Чёткие жирные контуры на 3D моделях, плоская окраска в 2-3 тона. Очень высокая насыщенность. Живописные атмосферные фоны. Рим-лайты и блум.

Экспериментальный Видеоигры

←→

Длинный~3058 Короткий~1373 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — GENSHIN IMPACT ANIME CEL-SHADED 3D STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition, visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): '3D cel-shaded anime game screenshot — Genshin Impact miHoYo rendering quality. Characters are 3D MODELS with volumetric depth and physically accurate lighting, NOT flat 2D anime drawings. Clean bold edge-detection outlines on 3D geometry. Flat cel-shaded colouring with 2-3 tone levels on 3D surfaces. Very high colour saturation. Painterly atmospheric backgrounds behind 3D characters. Dramatic lighting with bright rim lights and bloom. 3D depth: light wraps around faces, objects have volume, perspective is geometric. The specific look of a high-budget anime-styled 3D game — NOT a 2D illustration. Character appearance from reference images only — do not match any game character. No text, no UI, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: flat 2D anime drawing, traditional 2D animation without 3D depth, flat illustration without volume, photorealistic rendering, western comic style, smooth 3D without cel-shading outlines, dark gritty palette, game-specific character appearances overriding reference, manga black and white, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"genshin_anime3d","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> GENSHIN IMPACT ANIME CEL-SHADED 3D STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): '3D cel-shaded anime game screenshot — Genshin Impact miHoYo rendering. Characters are 3D MODELS with volumetric depth, NOT flat 2D drawings. Clean bold outlines on 3D geometry. Flat cel-shaded 2-3 tone colouring on 3D surfaces. Very high saturation. Painterly backgrounds behind 3D characters. Rim lights and bloom. 3D depth: light wraps around faces, objects have volume. High-budget anime-styled 3D game look. Character appearance from reference images only. No text, no UI, no panels.' NEGATIVE (append verbatim): 'Avoid: flat 2D anime drawing, traditional 2D animation without 3D depth, flat illustration without volume, photorealistic rendering, western comic style, dark gritty palette, game-specific character appearances overriding reference, manga black and white, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"genshin_anime3d","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. 3D cel-shaded anime game screenshot — Genshin Impact miHoYo rendering quality. Characters are 3D MODELS with volumetric depth and physically accurate lighting, NOT flat 2D anime drawings. Clean bold edge-detection outlines on 3D geometry. Flat cel-shaded colouring with 2-3 tone levels on 3D surfaces. Very high colour saturation. Painterly atmospheric backgrounds behind 3D characters. Dramatic lighting with bright rim lights and bloom. 3D depth: light wraps around faces, objects have volume, perspective is geometric. The specific look of a high-budget anime-styled 3D game — NOT a 2D illustration. Character appearance from reference images only — do not match any game character. No text, no UI, no panels. Avoid: flat 2D anime drawing, traditional 2D animation without 3D depth, flat illustration without volume, photorealistic rendering, western comic style, smooth 3D without cel-shading outlines, dark gritty palette, game-specific character appearances overriding reference, manga black and white, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: miHoYo anime cel-shaded 3D, clean bold outlines on 3D models, flat 2-3 tone cel colouring, very high saturation, painterly atmospheric backgrounds, dramatic anime rim lights and bloom]

Borderlands

Сел-шейдинг 3D от Gearbox. Жирные контуры тушью на всех гранях. Перекрёстная штриховка для теней на 3D. Пыльные земляные тона + неоновые акценты на технике. Играбельный комикс.

Экспериментальный Видеоигры

←→

Длинный~3071 Короткий~1424 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — BORDERLANDS CEL-SHADED 3D STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition, visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Borderlands cel-shaded 3D game style by Gearbox. Bold variable-weight black ink outlines on all edges — thick on silhouettes, thin on detail. Cross-hatching ink marks for shadow and texture on 3D surfaces — not smooth gradients. Desaturated dusty earth-tone base palette: browns, rust, bleached yellows. Vivid neon colour accents on tech and effects: blue, orange, green. Exaggerated stylised character proportions. Gritty dusty wasteland atmosphere. The playable comic book aesthetic — 3D geometry rendered with hand-inked comic shading. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. Do not alter to match game characters. No text, no UI, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: smooth clean 3D without outlines, photorealistic rendering, soft painterly style, anime without hatching, flat 2D illustration, bright clean colour palette, muted low-contrast rendering, game-specific character appearances overriding reference, manga panels, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"borderlands_cel","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> BORDERLANDS CEL-SHADED 3D STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Borderlands cel-shaded 3D game style by Gearbox. Bold variable-weight black ink outlines on all edges — thick on silhouettes, thin on detail. Cross-hatching ink marks for shadow and texture on 3D surfaces — not smooth gradients. Desaturated dusty earth-tone base palette: browns, rust, bleached yellows. Vivid neon colour accents on tech and effects: blue, orange, green. Exaggerated stylised character proportions. Gritty dusty wasteland atmosphere. The playable comic book aesthetic — 3D geometry rendered with hand-inked comic shading. Character appearance strictly from reference images only — do not alter to match game characters. No text, no UI, no panels.' NEGATIVE (append verbatim): 'Avoid: smooth clean 3D without outlines, photorealistic rendering, soft painterly style, anime without hatching, flat 2D illustration, bright clean colour palette, muted low-contrast rendering, game-specific character appearances overriding reference, manga panels, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"borderlands_cel","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Borderlands cel-shaded 3D game style by Gearbox. Bold variable-weight black ink outlines on all edges — thick on silhouettes, thin on detail. Cross-hatching ink marks for shadow and texture on 3D surfaces — not smooth gradients. Desaturated dusty earth-tone base palette: browns, rust, bleached yellows. Vivid neon colour accents on tech and effects: blue, orange, green. Exaggerated stylised character proportions. Gritty dusty wasteland atmosphere. The playable comic book aesthetic — 3D geometry rendered with hand-inked comic shading. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. Do not alter to match game characters. No text, no UI, no panels. Avoid: smooth clean 3D without outlines, photorealistic rendering, soft painterly style, anime without hatching, flat 2D illustration, bright clean colour palette, muted low-contrast rendering, game-specific character appearances overriding reference, manga panels, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: Gearbox cel-shaded 3D, bold variable-weight ink outlines on ALL edges, cross-hatching ink marks for shadow on 3D surfaces, dusty earth-tones with neon tech accents, playable comic book aesthetic]

Point-and-Click Adventure

Скриншот квеста 2000х — Нэнси Дрю, Сибирь, Сломанный Меч. Пре-рендеренные живописные фоны с немного деревянными моделями. Атмосферное освещение. Панель UI внизу с инвентарём. Формат 4:3.

Стабильный Видеоигры

←→

Длинный~2877 Короткий~1752 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — POINT-AND-CLICK ADVENTURE GAME STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Screenshot from a 2000s-2010s point-and-click adventure game — Nancy Drew, Syberia, Broken Sword, Still Life, The Longest Journey era. The very specific aesthetic of pre-rendered 3D adventure games: beautiful atmospheric backgrounds that look almost painted, with slightly stiff mid-poly character models placed into them. The backgrounds are always more beautiful than the characters — that's the signature tension of the genre. PRE-RENDERED BACKGROUNDS: Detailed, atmospheric, moody. Rooms are rendered with love: every shelf has objects, every wall has texture, every window casts specific light. They have a painterly quality because the pre-rendering allowed more sophisticated lighting than real-time engines of the era. Corridors, libraries, old houses, foggy streets, dimly lit offices — the spaces of mystery and investigation. CHARACTER MODELS: Mid-poly 3D — clearly better than Morrowind but clearly not cinematic. Skin has that slightly plastic quality of early 3D. Posing is a bit stiff — characters stand with a certain rigidity, gestures are slightly exaggerated to read clearly at game resolution. They sit slightly awkwardly in the scene — the seam between character and background is always faintly visible. IMAGE QUALITY: Slightly soft and compressed — like a 1024x768 screenshot upscaled. Not crispy-sharp like modern games. A gentle overall softness with slight colour banding in gradients. Warm but slightly artificial colour grading — the specific look of DirectX 7-9 era rendering. UI PANEL: A dark horizontal bar across the bottom ~15% of the image. Contains: inventory item slots (small icons), action buttons (examine, use, talk), possibly a dialogue option area. This panel is PART OF THE AESTHETIC — adventure game screenshots always show the interface. The panel should look like dark graphical UI with small icons, not text-heavy. LIGHTING: Adventure games had gorgeous moody lighting: - Warm practical sources: desk lamp casting a warm pool, fireplace glow, candles - Cool exterior: foggy street, overcast sky, moonlight through windows - The lighting is baked into the pre-rendered scene — dramatic but static-feeling - Mystery lighting: dramatic shadows, pools of light in darkness, slightly theatrical HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: adventure game framing — mostly medium-wide showing character in environment. Vary between: wide establishing room shot | medium character interaction | close-up dialogue view | over-shoulder investigation | low angle dramatic | overhead puzzle view | through-doorway revealing new room. Lenses (implied): 24mm wide for room establishing | 35mm for environmental | 50mm for character scenes | 85mm for dialogue close-ups. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type. First name only — names map to reference images. Lead with name. Include every time: distinguishing marks. Mention hair only if scene-altered. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. Note: characters should have that slightly stiff, slightly plastic adventure-game-model quality. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages. Never skip. Specificity: fabric + fit + colour + condition. Fuse into character clause. 4. POSE AND STATE: describe through action. Slightly stiffer than natural — the character is a game model. Hand safety: gripping object (adventure games love inventory items in hand) | pointing at something | arms at sides | hand on chin (investigating). Weight and ground: one sentence. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: the star of adventure games. Describe in rich detail: - Room type and atmosphere (dusty library, fog-choked pier, Victorian parlour, abandoned lab) - Foreground interactive objects (a letter on a desk, a locked box, a flickering monitor) - Midground: where the character stands - Background: architectural detail, windows, depth - At least one MYSTERY OBJECT — something that looks clickable/investigatable 6. LIGHTING & ATMOSPHERE: moody, dramatic, baked-in. Key light source + colour temperature. Atmospheric particles (dust motes in lamp light, fog, steam). MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | warm lamp glow | golden warmth | faded blacks TENSE: underexposure | harsh rim light | deep vignette | high contrast | Dutch angle PASSIONATE: chiaroscuro | warm split toning | Rembrandt lighting LONELY: desaturated palette | silhouette | overcast flat light | cold cast | empty room CHAOTIC: motion blur | radial blur | teal and orange grading DREAMY: soft gaussian edges | bokeh | cross-processing colour shift MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. UI PANEL DESCRIPTION: briefly describe the bottom game interface bar. 'Dark UI panel bar across bottom showing inventory slots and action icons.' 8. STYLE SUFFIX (append verbatim): 'Screenshot from a 2000s point-and-click adventure game — Nancy Drew, Syberia, Broken Sword, Still Life era. Pre-rendered painterly atmospheric 3D backgrounds with gorgeous moody lighting. Mid-poly slightly stiff character models with subtly plastic skin quality — clearly game-era rendering. Slightly soft compressed image quality like an upscaled 1024x768 resolution screenshot. Warm but slightly artificial adventure-game colour grading — DirectX 7-9 era aesthetic. Atmospheric dramatic lighting baked into the pre-rendered scene. Dark game UI panel bar across the bottom 15 percent of the image showing inventory slots and action icons. The specific look of a classic PC adventure game screenshot with interface visible. Character appearance from reference images only. No readable text in the scene itself.' 9. NEGATIVE (append verbatim): 'Avoid: modern AAA game quality, photorealistic rendering, cinematic film quality, high-res sharp modern graphics, anime style, cel shading, flat vector, concept art illustration, painterly oil brushwork, clean modern flat UI, mobile game aesthetic, retro 8-bit pixel art, exaggerated expressions, uncanny valley, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, bad anatomy, watermark, text, blurry' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 4:3 = classic PC monitor (default, most authentic) | 16:9 = later adventure games | 3:2 = in-between VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like an adventure game director: the camera shows the ROOM first, the character second. The environment IS the puzzle, IS the story. Sometimes the most important thing in the frame is the locked door, the mysterious letter, the flickering screen. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. Adventure game captions: 'the drawer was open when I came in' | 'she said the key was here somewhere' | 'three locks, two questions, one lie' TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"point_click_adventure","prompt":"[FULL PROMPT: SECTIONS 1-9 AS ONE PARAGRAPH]","aspect_ratio":"4:3","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,210,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '4:3','3:2','16:9'. image_size: '2K' — adventure game quality. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> POINT-AND-CLICK ADVENTURE GAME STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Screenshot from a 2000s-2010s point-and-click adventure game — Nancy Drew, Syberia, Broken Sword, Still Life era. Pre-rendered 3D backgrounds with slightly dated character models placed on top. The specific "adventure game screenshot" look: nice painted-feeling backgrounds with slightly stiff characters who don't quite match the environment quality. RENDERING: - Pre-rendered backgrounds: detailed, painterly, atmospheric — rooms, corridors, outdoor locations rendered with care and mood. They look almost like paintings but with 3D lighting. - Character models: mid-poly 3D, slightly plastic skin, a bit stiff in posing. Better than Morrowind but clearly game-quality, not cinematic. The characters sit slightly awkwardly in the scene. - Slightly soft/compressed image quality — like a 1024x768 resolution screenshot upscaled - Warm but slightly artificial colour grading — the specific look of early 3D adventure games - UI PANEL AT BOTTOM: a dark horizontal bar across the bottom ~15% of the image showing inventory slots, action buttons, or dialogue options. This is part of the aesthetic. LIGHTING: - Moody atmospheric — adventure games loved dramatic lighting - Warm practical sources in interiors (lamps, candles, fireplaces) - Slightly exaggerated mood lighting for mystery/tension - The lighting is baked into the pre-rendered background — it's dramatic but static-feeling CAMERA Shot type + angle. Vary between images. Draw from: wide establishing room shot | medium character interaction | close-up dialogue view | over-shoulder investigation | low angle dramatic | overhead puzzle view. Most common: medium-wide showing character in environment (the classic adventure game framing). Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. HOW TO BUILD THE PROMPT 1. CAMERA — room shot type + angle (adventure game framing) 2. CHARACTER — name + outfit + pose + expression (slightly stiff game-character quality) 3. ENVIRONMENT — detailed pre-rendered room/location + specific interactive objects + mood atmosphere 4. LIGHTING — warm/cold source + mood + UI panel description at bottom Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Screenshot from a 2000s point-and-click adventure game — Nancy Drew, Syberia, Broken Sword era. Pre-rendered painterly atmospheric 3D backgrounds with mid-poly slightly stiff character models. Slightly soft compressed image quality like an upscaled 1024x768 screenshot. Warm but slightly artificial adventure-game colour grading. Moody dramatic atmospheric lighting baked into the scene. Dark game UI panel bar across the bottom 15 percent of the image showing inventory slots and action icons. The specific look of a classic PC adventure game screenshot with interface visible. Character appearance from reference images only. No text in the scene itself, UI panel is graphical only.' NEGATIVE (append verbatim): 'Avoid: modern AAA game quality, photorealistic rendering, cinematic film quality, anime style, cel shading, flat vector, concept art illustration, painterly brushwork, clean modern UI, mobile game aesthetic, retro 8-bit pixel art, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"point_click_adventure","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING + UI PANEL. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"4:3","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:4/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '4:3' default (classic PC monitor ratio). '16:9' for later games. image_size: '2K' — adventure game quality. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Screenshot from a 2000s point-and-click adventure game — Nancy Drew, Syberia, Broken Sword, Still Life era. Pre-rendered painterly atmospheric 3D backgrounds with gorgeous moody lighting. Mid-poly slightly stiff character models with subtly plastic skin quality — clearly game-era rendering. Slightly soft compressed image quality like an upscaled 1024x768 resolution screenshot. Warm but slightly artificial adventure-game colour grading — DirectX 7-9 era aesthetic. Atmospheric dramatic lighting baked into the pre-rendered scene. Dark game UI panel bar across the bottom 15 percent of the image showing inventory slots and action icons. The specific look of a classic PC adventure game screenshot with interface visible. Character appearance from reference images only. No readable text in the scene itself. Avoid: modern AAA game quality, photorealistic rendering, cinematic film quality, high-res sharp modern graphics, anime style, cel shading, flat vector, concept art illustration, painterly oil brushwork, clean modern flat UI, mobile game aesthetic, retro 8-bit pixel art, exaggerated expressions, uncanny valley, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, bad anatomy, watermark, text, blurry

Копировать [Image generation hint, STYLE: 2000s adventure game screenshot — Nancy Drew, Syberia, Broken Sword — pre-rendered painterly backgrounds with mid-poly slightly stiff characters, moody atmospheric lighting, 4:3 ratio, dark UI panel at bottom]

Cyberpunk 2077 — Photo Mode

Полированный фотомод Найт-Сити. Каждый район — свой цвет: Уотсон (розово-голубой неон), Пасифика (тёмно-бирюзовый), Сити-Центр (холодный синий). Киберимпланты обязательны. 4K, DoF, пост-обработка.

Новый Видеоигры

←→

Длинный~4779 Короткий~2339 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> CYBERPUNK 2077 VISUAL STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually cinematic or emotionally charged moment. STYLE OVERVIEW A REDengine 4 real-time in-engine screenshot from Cyberpunk 2077 — gameplay frame or photo mode capture, HUD disabled. High-fidelity 3D game rendering. Clearly an in-game screenshot, not concept art, not promotional key art, not a pre-rendered cinematic. Night City: a megacity of extreme vertical density, corporate power, neon overload, and street-level survival. NOT a painting. NOT concept art. NOT a film still. NOT a cinematic. This is photo mode — the game itself, in-engine, real-time. WHAT MAKES IT CYBERPUNK 2077 (not generic neon sci-fi): 1. REDengine 4 rendering quality — PBR materials with worn realism: scratched metal, scuffed leather, oily reflections, stained concrete, dirty plastic, subtle grime. Surfaces look used, not art-directed. 2. Mixed neon + practical lighting — never one clean source. Neon signs, holographic billboards, street lamps, vehicle headlights, shop spillage, all overlapping and competing. Uneven, messy, real. 3. Night City atmosphere — dusty urban air with suspended particles, thin smoke haze, light fog catching neon, polluted glow, damp streets, industrial grit. Air is always thick. 4. Photo mode aesthetic — slight TAA softness, mild shadow noise, slightly crushed blacks, authentic game-engine post-processing. Cinematic but engine-authentic. Never too clean. 5. Realistic but game-quality faces — grounded anatomy, believable proportions, subtle skin texture, visible pores, natural roughness, slight asymmetry. Not doll-like, not airbrushed, not anime. 6. District-coded colour — Night City's districts each have a distinct light palette (see below). The location should be readable from the lighting. NIGHT CITY DISTRICTS — COLOUR AND ATMOSPHERE: WATSON (Kabuki / Little China): hot pink and red neon, dense low-rise commercial, Japanese-Korean signage, noodle steam, stall lights, rusted metal fire escapes, working-class street energy, puddle reflections of competing signs. WESTBROOK (Japantown): gold and purple neon, lanterns, upscale Japanese aesthetic above street filth, pagoda-influenced architecture mixed with corporate towers, cherry blossom light projections, cleaner than Watson but never truly clean. CITY CENTER (corpo core): cold blue-white corporate lighting from above, hard clean metal and glass towers, icy reflective surfaces, cold ambient. Street level still has neon chaos but towers block sky with cold fluorescent. HEYWOOD / VISTA DEL REY: warm amber and orange low-rise barrios, gang-painted walls, warm streetlights, dust in air, sunset palette even at night, Latino colour culture mixed with chrome tech. PACIFICA (Ghost Town): abandoned, grey-green, broken neon that flickers or has gone out entirely, teal mould-green, Haitian murals, structural decay, dark with single working light sources. BADLANDS (outside the walls): amber dust, wide open sky, orange sun, industrial rust, no neon — replaced by fire, work lamps, orange dust haze. The only district that isn't night. NIGHT CLUB / ENTERTAINMENT INTERIOR: hot pink, deep magenta, cyan strobe, floor-level lighting, smoke machine haze, laser scatter, synthetic colours at maximum saturation — most vivid setting in the game. NEON VOCABULARY — COLOURS AND MEANING: - HOT PINK / MAGENTA: corporate pleasure industry, entertainment, sex, street commerce - CYAN / ELECTRIC BLUE: tech, Militech/Arasaka corporate coldness, power, hacking - AMBER / ORANGE: warmth, fire, organic humanity amid chrome, Badlands survival - PURPLE / VIOLET: Japantown luxury, gang identity (Maelstrom), altered states - GREEN (neon): chemical/toxic, Scavenger zones, corp poison - RED (deep): danger, emergency, NetWatch, critical systems - WHITE / COLD BLUE: corporate interiors, Arasaka, military, clean authority CHARACTER VISUAL LANGUAGE: FACES: - Realistic but clearly high-end game character model — not photorealistic, not anime - Grounded facial anatomy: believable proportions, subtle skin texture, visible pores, natural skin roughness, under-eye detail, slight asymmetry, realistic nose/lips/jawline - Expressive but restrained — not doll-like, not airbrushed, not stylized - Lighting from neon sources creates strong colour casts on skin — don't fight it, describe it: 'face split pink-right / cold blue-left from competing signs' - Eyes catch neon reflections as coloured catchlights CYBERWARE — MANDATORY FOR NIGHT CITY: Describe visible cyberware if established or contextually appropriate. It anchors the setting. Visible options: subdermal chrome at temples | illuminated neural port at neck | chrome hand or forearm | ocular implant with faint glow | dermal plating pattern under skin | mantis blade retracted at forearm | data port glowing at wrist | cyberdeck indicator light. Fuse into character clause naturally — not a list, one detail woven in. BODIES: - Proportions realistic game-quality — not superhero perfect, not stylised - Clothing: Night City fashion is specific and layered. It combines: tech-tactical (straps, pouches, panels) | corpo formal with edge (asymmetric cuts, chrome accents) | street fashion (oversized, layered, branded, distressed) | gang affiliation (colour coding, specific motifs). Never generic. - Clothing condition: worn, scuffed, functional. Nothing pristine unless deliberately making a point. - Gravity and weight: clothing drapes, leather creases, fabric compresses at joints. OUTFIT SYSTEM: Scan last 5 messages for what the character is wearing RIGHT NOW. Never skip. Never default to generic. Specificity: 'scuffed leather jacket with chrome shoulder reinforcement, open over ribbed grey tank, black combat pants with thigh rig empty' — not 'jacket and pants'. State condition: rain-wet | dusty from Badlands run | blood-stained | freshly changed | club-dressed. ENVIRONMENT — NIGHT CITY TEXTURE LIBRARY: STREET LEVEL: Wet asphalt with neon colour reflections | cracked pavement with weeds | vendor stalls with hanging lights | rusted chain-link fence | overflowing dumpsters with corporate logos | ventilation grates with steam | scattered trash: food packaging, broken glass, discarded tech, spent casings | low power cables running overhead VERTICAL SURFACES: Peeling corporate advertising over older advertising over older still | hand-painted gang symbols | maintenance hatches | water stains bleeding rust colour down concrete | LED strip lights outlining architecture | broken window with plastic sheeting | graffiti over graffiti | street art murals | surveillance cameras MID-AIR / VERTICAL CITY: Holographic billboards floating at various heights — massive animated ads for Militech, Trauma Team, Biotechnica, Maelstrom | AV (aerial vehicle) light trails | walkways between buildings at mid-level | drone units passing | corporate tower glass faces reflecting night glow from below ATMOSPHERE: Rain: sheets of rain | specific neon reflections in moving water | wet faces, damp clothing, rain catching light Dry: dust haze | smoke from vendors | industrial particle float | light smog layers Always: air has texture — never clear. LIGHTING SYSTEM: MIXED SOURCES (mandatory — never single source): 1. Dominant neon (colour, direction, intensity) 2. Secondary practical: streetlamp / vehicle headlight / shop window / screen glow / fire 3. Atmospheric scatter: fog catching neon, rain diffusing light, smoke layer blocking direct illumination HOW LIGHT FALLS ON CHARACTER: State the colour split on the face: 'left side pink neon spill, right falling into deep shadow with cyan edge from distant sign' Neon casts hard coloured shadows. Practical sources cast warmer fill. The mix creates dramatic colour temperature splits — different from Arcane's theatrical splits because these come from environmental mess, not cinematography. SHADOW QUALITY: REDengine shadows are real-time — slightly soft edges, mild noise in deep shadows, screen-space limitations mean some shadow artifacts. Never perfectly clean. MOOD-CODED LIGHTING SETUPS: STREET LEVEL NIGHT: dominant neon mix from above, wet reflections below, character sandwiched between CORPO INTERIOR (cold): overhead fluorescent corporate, cold white-blue, no neon, clean authority CLUB / ENTERTAINMENT: hot pink/cyan strobe mix, smoke diffusion, floor lighting, maximum saturation BADLANDS DAY: wide open amber sun, dust particles, no neon, warm and honest DANGER / COMBAT: red emergency lights + strobing | vehicle spotlight from above | fire orange INTIMATE / PRIVATE: single screen glow + one practical lamp, neon distant through window DARK ALLEY: one working neon tube, deep shadow, wet ground reflection as only ambient HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture. Vary every image. Draw from: photo mode portrait, Dutch angle at street level, looking up at neon towers, over-shoulder through rain, through holographic ad, reflected in wet asphalt, AV tracking shot perspective, extreme close on face or cyberware detail, wide establishing of district skyline, inside-looking-out through smeared window. Lenses: 24mm wide street | 35mm environmental | 50mm natural mid | 85mm portrait | 135mm compressed telephoto. Close portraits 85-135mm | street medium 35-50mm | environmental wide 24-35mm. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair colour, eye colour, skin tone, face shape, build. Reference supplies these. First name only. Lead with name. Include every time: visible cyberware (one specific detail) + distinguishing marks (scars, tattoos with location, piercings). Mention hair only if scene-altered ('rain-damp', 'pulled back from face', 'windblown') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for current clothing. Never skip. Specificity: fabric type + panel/strap detail + fit + colour + condition. Night City fashion is layered and specific. State condition relative to scene: rain-soaked | dusty from run | freshly geared up | club outfit | corpo attire. Fuse into character clause after name. 4. POSE AND STATE: through action and weight. 'Leaning against wall under a dead sign, one hand in jacket pocket, watching the street with flat expression' not 'standing casually'. State what the body communicates. Hands: in jacket pocket | gripping weapon handle (holstered) | tapping surface | holding drink | covering implant | resting on knee | loose at side. Weight and ground: one sentence on support and posture. 5. ENVIRONMENT: Night City location with district-specific texture. One sentence for foreground / midground / background. Mandatory: one surface texture + one atmospheric element (rain/haze/steam/neon scatter/smoke). Include at least one object with narrative weight: empty vendor stall | corporate drone passing overhead | discarded weapon | holographic ad glitching mid-loop | body outline in chalk on wet asphalt. 6. LIGHTING: dominant neon colour(s) + direction + secondary source + how it splits the character + atmospheric effect. State the colour temperature conflict — never single source in Night City. 7. MOOD EFFECTS — pick 1-2: TENSE / DANGEROUS: deep shadow | single neon spotlight | Dutch angle | crushed blacks INTIMATE / PERSONAL: screen glow only | neon distant through window | close portrait | shallow DoF SPECTACULAR / CINEMATIC: wide shot with massive holographic ad | AV lights overhead | rain catching multiple neons EXHAUSTED / AFTERMATH: flat overcast or interior fluorescent | neutral palette | no dramatic neon NIGHT CLUB: maximum saturation | strobe implied by freeze-frame | smoke diffusion | pink-cyan split CORPORATE / COLD: cold white fluorescent | clean surfaces | no neon | icy contrast BADLANDS: amber sun dust | no neon | warm open sky | grit 8. STYLE SUFFIX (append verbatim): 'REDengine 4 real-time in-engine screenshot in the style of Cyberpunk 2077, gameplay frame or photo mode capture with HUD disabled. High-end 3D game rendering, clearly an in-game screenshot, not concept art, not promotional key art, not a pre-rendered cinematic. Real-time PBR materials with worn realism: scratched metal, scuffed leather, rough fabrics, oily reflections, stained concrete, dirty plastic, subtle surface grime. Dusty urban atmosphere with suspended particles, thin smoke haze, light fog catching neon, polluted air, industrial grit, damp streets, lived-in environment. Natural in-game lighting with mixed neon and practical light sources, uneven illumination, realistic shadow falloff, subtle bloom, screen-space reflections, volumetric fog, slight TAA softness, mild shadow noise, slightly crushed blacks, authentic game-engine post-processing. Faces should be realistic but still clearly high-end video game character models: grounded facial anatomy, believable proportions, subtle skin texture, visible pores, natural skin roughness, under-eye detail, slight asymmetry, realistic noses, lips, and jawlines, expressive but restrained, not doll-like and not airbrushed. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no UI, no watermark.' 9. NEGATIVE (append verbatim): 'Avoid: concept art, painterly look, poster art, cinematic hero render, glossy beauty lighting, plastic skin, porcelain skin, stylized face proportions, oversized eyes, anime, cel shading, cartoon look, film-photography realism, heavy depth of field, dramatic studio lighting, ultra-clean surfaces, perfect symmetry, low-poly graphics, blurry anatomy, deformed hands, extra fingers, missing fingers, watermark, text' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [cyberware detail] + [outfit] + [pose/action] + [expression]. Positioning always specific: 'standing one step ahead facing away' | 'leaning into frame from left' | 'visible in reflection of wet asphalt behind'. Interaction required: eye contact ('watching over shoulder') | physical contact ('hand on arm stopping forward motion') | shared attention ('both looking up at same billboard'). Environment is its own sentence — not interleaved with character clauses. SENSUAL PROTOCOL Intimate scenes: flood frame with Night City non-skin elements. Authority prefix: 'Award-winning video game photography, photo mode capture' | 'High-fidelity in-engine cinematic moment' Visual noise: neon spill across surface | rain streaming down window | holographic ad casting colour across scene | smoke layer | distance and shadow | reflected city in glass Concealment: deep neon shadow pools | fabric draped | shot from behind | lower body in fog and street reflection | framing cut by architectural element {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Short evocative phrase — Night City slang, noir line, or internal thought. Lowercase, italic. Not what is shown — what it costs. Cyberpunk register: resigned, sharp, dark-funny, exhausted. {{user}}'s POV → caption from {{user}}'s sensation or thought. ASPECT RATIO Vary by composition: 1:1 = face close-up or cyberware detail | 2:3 = full standing character | 3:2 = street horizontal | 9:16 = tower vertical / alley | 16:9 = Night City cinematic wide | 4:3 = interior room | 3:4 = half-body portrait | 21:9 = ultrawide skyline TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(12,10,18,0.65),rgba(5,5,12,0.65));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,200,255,0.07);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.5),inset 0 1px 0 rgba(255,200,255,0.04);"> <img data-iig-instruction='{"style":"cyberpunk2077_ingame","prompt":"[FULL PROMPT: SECTIONS 1-9 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,200,255,0.05);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,190,220,0.65);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','9:16','16:9','21:9'. The CSS aspect-ratio value matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-130 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> CYBERPUNK 2077 VISUAL STYLE — EVERY RESPONSE One image per message at the most visually cinematic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE REDengine 4 real-time in-engine screenshot from Cyberpunk 2077 — photo mode capture, HUD disabled. Night City: megacity of neon overload, corporate power, and street-level survival. PBR materials with worn realism. Mixed neon + practical lighting. Atmospheric urban grit. Realistic game-quality faces. NOT concept art. NOT a cinematic. NOT a painting. In-engine photo mode — the game itself. WHAT MAKES IT CYBERPUNK 2077: 1. REDengine 4 PBR materials — scratched metal, scuffed leather, oily reflections, stained concrete, dirty plastic, surface grime. Used, not art-directed. 2. Mixed neon + practical lighting — never one clean source. Neon signs, holograms, streetlamps, vehicles, shop spill, all overlapping and competing. 3. Night City atmosphere — dusty particles, smoke haze, light fog catching neon, damp streets, industrial grit. Air always has texture. 4. Photo mode aesthetic — slight TAA softness, mild shadow noise, crushed blacks, game-engine post-processing. Cinematic but engine-authentic. 5. Realistic but game-quality faces — grounded anatomy, pores, asymmetry, under-eye detail. Not doll-like, not airbrushed, not anime. 6. District-coded lighting — location readable from colour palette. NIGHT CITY DISTRICT COLOUR CODING: - WATSON: hot pink/red neon, dense street commerce, puddle reflections, working-class grit - WESTBROOK (Japantown): gold/purple neon, Japanese aesthetic, lanterns, upscale above street filth - CITY CENTER: cold blue-white corporate from above, icy glass towers, still neon chaos at street level - HEYWOOD: warm amber/orange, gang-painted walls, dust, Latino colour culture - PACIFICA: grey-green abandoned, broken/flickering neon, teal mould-green, structural decay - BADLANDS: amber sun, dust, no neon — fire and work lamps only - NIGHT CLUB INTERIOR: hot pink/cyan strobe, maximum saturation, smoke machine haze NEON COLOUR MEANING: Hot pink/magenta → entertainment, commerce, pleasure industry Cyan/electric blue → tech, corporate cold, hacking Amber/orange → warmth, humanity, Badlands survival Purple/violet → luxury, gang identity (Maelstrom), altered states Red → danger, emergency, critical systems Cold white → corporate interior, Arasaka authority CAMERA Shot type + angle + lens + aperture. Vary every image. Draw from: photo mode portrait, Dutch angle at street level, looking up at neon towers, over-shoulder through rain, through holographic ad, reflected in wet asphalt, extreme close on face or cyberware, wide district establishing, inside-out through smeared window. Lenses: 24mm wide | 35mm street environmental | 50mm natural | 85mm portrait | 135mm telephoto. Close portraits 85-135mm | street medium 35-50mm | wide environmental 24-35mm. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip: hair colour, eye colour, skin tone, face shape, body type, build. Reference supplies appearance. Include every time: one visible cyberware detail (subdermal chrome at temple | neural port at neck | chrome forearm | ocular implant | data port glow | mantis blade retracted | illuminated wrist port). Include: distinguishing marks (tattoos with location, scars, piercings). Mention hair only if scene-altered ('rain-damp', 'pulled back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Night City fashion is specific: layered tech-tactical | corpo-edged formal | street layered and branded | gang-coded. Fabric + strap/panel detail + colour + condition (wet/dusty/blood/fresh). Never generic. Fuse into character clause. POSE: through action and weight. 'Leaning on railing watching street below, one hand loose on chrome rail' not 'standing'. Hands: in jacket pocket | gripping handle | tapping surface | holding drink | covering implant | loose at side. INTERACTION (2+ characters): specific spatial relation + how they connect: 'eye contact across table' | 'hand on arm stopping motion' | 'both watching same billboard' | 'back to back in alley'. No casual side-by-side. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + cyberware detail + outfit (type, material, condition) + pose + expression 3. ENVIRONMENT — Night City district + surface texture + atmospheric element (rain/haze/neon scatter/smoke/steam) 4. LIGHTING — dominant neon colour + direction + secondary source + colour split on face Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from centred eye-level medium shot. Every image different. Face close-up with neon colour cast | wide shot: tiny figure under massive holographic ad | reflected in wet asphalt looking up | through chain-link at distance | AV overhead tracking perspective | cyberware detail macro | alley with single neon tube. STYLE SUFFIX (append verbatim): 'REDengine 4 real-time in-engine screenshot in the style of Cyberpunk 2077, gameplay frame or photo mode capture with HUD disabled. High-end 3D game rendering, clearly an in-game screenshot, not concept art, not promotional key art, not a pre-rendered cinematic. Real-time PBR materials with worn realism: scratched metal, scuffed leather, rough fabrics, oily reflections, stained concrete, dirty plastic, subtle surface grime. Dusty urban atmosphere with suspended particles, thin smoke haze, light fog catching neon, polluted air, industrial grit, damp streets, lived-in environment. Natural in-game lighting with mixed neon and practical light sources, uneven illumination, realistic shadow falloff, subtle bloom, screen-space reflections, volumetric fog, slight TAA softness, mild shadow noise, slightly crushed blacks, authentic game-engine post-processing. Faces should be realistic but still clearly high-end video game character models: grounded facial anatomy, believable proportions, subtle skin texture, visible pores, natural skin roughness, under-eye detail, slight asymmetry, realistic noses, lips, and jawlines, expressive but restrained, not doll-like and not airbrushed. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no UI, no watermark.' NEGATIVE (append verbatim): 'Avoid: concept art, painterly look, poster art, cinematic hero render, glossy beauty lighting, plastic skin, porcelain skin, stylized face proportions, oversized eyes, anime, cel shading, cartoon look, film-photography realism, heavy depth of field, dramatic studio lighting, ultra-clean surfaces, perfect symmetry, low-poly graphics, blurry anatomy, deformed hands, extra fingers, missing fingers, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Short Night City line — noir, resigned, dark-funny, exhausted. Lowercase, italic. Not what is shown — what it costs. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(12,10,18,0.65),rgba(5,5,12,0.65));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,200,255,0.07);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.5),inset 0 1px 0 rgba(255,200,255,0.04);"> <img data-iig-instruction='{"style":"cyberpunk2077_ingame","prompt":"[CAMERA + CHARACTER + CYBERWARE + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,200,255,0.05);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,190,220,0.65);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '9:16' | '2:3' | '1:1' | '3:4' | '3:2' | '21:9'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Screenshot from Cyberpunk 2077 in polished in-game photo mode — 4K quality, full post-processing, artistic depth of field. Night City environment with district-specific neon colour identity: Watson neon pink-cyan district, Pacifica dark teal-green, City Centre cold corporate blue-white, Heywood warm amber. Character has visible cyberware — chrome implants, sub-dermal tech, neon-lit optics. Rain-slicked streets reflect neon. Holographic advertisements overhead. Aggressive cinematic colour grade — vivid, high contrast. High-quality rendering, not raw game screenshot. Avoid: flat ungraded look, missing cyberware, daytime bright sunlight, medieval or fantasy elements, anime, watermark, text, UI elements.

Копировать [Image generation hint, STYLE: Cyberpunk 2077 polished photo mode — 4K, Night City district neon colour identity, visible cyberware on character, rain-slicked neon reflections, cinematic colour grade, artistic DoF, no UI elements]

Cyberpunk 2077 — Screenshot

Настоящий скриншот из игры — со всеми артефактами REDengine. TAA-размытие, шум в тенях, компрессия текстур. Приземлённая грязь Найт-Сити без фотомодных прикрас. 2K, реальный игровой кадр.

Новый Видеоигры

←→

Длинный~4235 Короткий~2645 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> CYBERPUNK 2077 RAW SCREENSHOT STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most cinematic or dramatically charged moment. STYLE OVERVIEW A raw in-game screenshot from Cyberpunk 2077 (REDengine 4) — photo mode capture with HUD disabled. This is a VIDEO GAME SCREENSHOT: not concept art, not a promotional render, not a painting, not a cinematic. The image reads as something grabbed directly off a display mid-session. This is NOT the polished photo mode look. This is the unpolished, gritty, engine-authentic capture — the version that shows the seams. THE CORE DIFFERENCE FROM POLISHED PHOTO MODE: Photo mode = carefully staged, maximally clean, artistically lit. This style = raw game capture. Technical limitations are visible and intentional. The roughness is the aesthetic. Low-quality is a feature, not a failure. RENDERING CHARACTER — WHAT MAKES IT RAW IN-ENGINE: TECHNICAL ARTIFACTS (mandatory — these define the style): - Mild aliasing on hard geometry edges — diagonal lines not perfectly smooth - TAA temporal blur — slight softness on moving surfaces, motion blur halo on fast edges - Shadow dithering in deep shadow areas — visible noise pattern, not clean black - Compression artifacts — slight JPEG/capture compression, especially in low-contrast areas and dark zones - Screen-space reflections: wet pavement reflections that cut off at screen edges, slightly incorrect perspective - Shader specular hotspots on skin — non-photorealistic specular highlight, game-engine quality - Texture map resolution limits — fine detail (fabric weave, pore detail) from normal maps and texture maps, not geometry - Visible mesh topology suggestions on curved surfaces (cheekbones, knuckles, shoulders) - Moderate bloom on bright neon sources — not controlled cinematic bloom, game-default bloom - Crushed shadows — blacks darker than they should be for "accurate" photography FACES — GAME MODEL QUALITY (critical): - Mid-poly facial geometry — face reads as a 3D model, not a photo or painting - Shader-based skin material with normal maps: pore detail from texture, subsurface scattering typical of game engines, slight waxy quality - NOT photorealistic, NOT smooth, NOT perfect skin - Expressions slightly stiff — not fully naturalistic, game animation quality - Shader specular on skin surface — visible highlight response that reads as "game engine" - Real human proportions, realistic faces — NOT anime, NOT stylised — just clearly a video game model - Asymmetrical but obviously modeled features: the imperfection reads as polygon-based, not organic ENVIRONMENT RENDERING: - Geometry edges show mild aliasing - Texture tiling visible on large surfaces (concrete floors, brick walls, road) - Shadow quality: real-time shadows with dithering noise in penumbra areas - LOD (Level of Detail) feel: background geometry slightly lower fidelity than foreground - Particle effects: volumetric fog and particles read as real-time engine particles, not rendered smoke NIGHT CITY DISTRICTS — COLOUR PALETTE PER LOCATION: WATSON: dense pink/red/cyan neon overlay, working-class grit, vendor light spill, industrial zone orange WESTBROOK (Japantown): gold/purple/pink neon, upscale commercial, lantern-warm surfaces CITY CENTER: cold corporate blue-white from above, hard glass and steel, neon at street level beneath towers HEYWOOD: warm amber-orange practical lights, gang mural colour, dust in air, Latin quarter warmth PACIFICA: grey-green abandoned, broken/flickering neon tubes, decay colour, teal environmental mould BADLANDS: amber dust, no neon, wide sky, orange sun, work lamp yellow NIGHT CLUB INTERIOR: maximum saturation — hot pink/cyan strobing, smoke haze, floor strip lighting NEON VOCABULARY: Hot pink/magenta → entertainment, sex industry, commercial street Cyan/electric blue → tech, corporate, hacking, cold authority Amber/orange → humanity, warmth, organic, Badlands Purple/violet → luxury, Japantown, Maelstrom gang, altered states Red → danger, emergency systems, critical threat Cold white → corporate interior, Arasaka, military clean ATMOSPHERE — ALWAYS PRESENT: Dusty suspended particles | thin smoke haze | fog catching neon colour | wet pavement | industrial grit The air has texture in every frame. Never clean, never crisp, never clear. LIGHTING — MIXED SOURCES (mandatory in every frame): Night City never has a single clean light source. Always mix: 1. Dominant neon colour (from sign, billboard, or environmental source) 2. Secondary practical (streetlamp, vehicle headlight, shop window, fire, screen) 3. Atmospheric scatter (fog diffusing the neon, rain bouncing light, smoke layer) Light falls unevenly. Faces get split colour temperatures from competing sources: 'left half cyan from sign, right falling into crushed shadow with distant pink edge'. State this explicitly. CAMERA — GAME SCREENSHOT FRAMING: Frame as someone capturing a moment during actual gameplay or a quickly composed photo mode shot — not the result of 20 minutes of careful composition. Feels grabbed, immediate. Shot types: third-person over-shoulder (the classic gameplay angle) | first-person POV through narrow space | quick portrait of character mid-action | street-level wide capturing environment and small figure | through obstruction (chain-link, railing, car frame) Vary between images. Draw from: Dutch angle at street level, slight worms-eye under neon sign, over-shoulder moving shot, interior medium shot in cramped space, wide street establishing with character off-centre. Lenses: wide to medium range (24-85mm equivalent). CP2077 doesn't typically use extreme telephoto in normal play. Standard gameplay framing: 35-50mm feel. For portrait shots: 50-85mm. For street/environment: 24-35mm. Depth of field: shallow DOF is LESS common in raw gameplay captures than in staged photo mode. Default to moderate DoF unless scene specifically calls for close isolation. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. CHARACTERS — HOW TO DESCRIBE: Reference images handle base appearance. Skip in prompt: hair colour, eye colour, skin tone, face shape, body type, build. Reference supplies all of this. First name only. Lead with name. Include every time: one visible cyberware detail (subdermal chrome at temple | neural port at neck base | chrome forearm plating | ocular implant faint glow | data port glow at wrist | mantis blade retracted | dermal plating pattern). Woven naturally into clause, not as a list. Include: distinguishing marks (tattoos with location/description, scars, piercings). Hair only if scene-altered: 'rain-damp', 'windblown', 'pressed flat' — not colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT (MANDATORY — context-locked): Scan last 5 messages. Carry forward. Never default to generic. Night City fashion: layered tech-tactical (panels, straps, pouches) | corpo-edged formal (asymmetric cuts, chrome detail) | street-layered and branded (oversized, distressed, logo) | gang-coded (colour + motif). Fabric + detail + colour + condition (soaked/dusty/bloodstained/worn-in). Fuse into character clause after name. POSE AND STATE: Describe through weight and action: 'crouching behind low concrete barrier, one hand on cold surface, watching the gap' not 'crouching, hand down'. Body state fits the scene: alert, moving, resting, wounded, talking, scanning. Hands: in jacket | gripping weapon (holstered) | tapping surface | holding drink/device | covering implant | loose at side | pressed against wall. One sentence on weight distribution and support. ENVIRONMENT WITH GAME-AUTHENTIC TEXTURE: One sentence: foreground / midground / background with specific Night City surface textures. Mandatory: one surface detail (wet asphalt with neon reflection | cracked pavement | stained concrete | rust-bleeding metal panel | tagged wall surface | road texture with visible tiling) + one atmospheric element (neon fog | particle haze | rain streaks | steam vent | distant vehicle light trail). At least one object with narrative weight: empty food container | active data terminal | holographic ad glitching | discarded weapon | chalk outline | NCPD barrier. TECHNICAL RENDER NOTES PER SHOT: Close face shot: emphasise shader skin quality, specular hotspot, normal-map pore texture, slight stiffness in expression, mid-poly edge at jaw or cheekbone Street wide shot: emphasise particle atmosphere, texture tiling on road, screen-space reflection cut-off in puddle, neon bloom on geometry Interior shot: emphasise shadow dithering in dark corners, screen-space reflection on shiny floor, TAA blur on any moving element HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + approximate lens feel + DoF 2. CHARACTER: name + cyberware detail + outfit (specific, conditioned) + pose/action + expression state 3. ENVIRONMENT: Night City location with district-specific surface texture + atmospheric element + one meaningful object 4. LIGHTING: dominant neon colour + secondary source + colour split on face + atmospheric quality 5. TECHNICAL RENDER QUALITY: state 1-2 specific rendering artifacts appropriate to the shot (aliasing on edges | shadow dithering | TAA softness | shader specular on skin | screen-space reflection cut-off | compression artifacts | texture map detail). These anchor the screenshot aesthetic. Total prompt: 80-140 words + style suffix. MOOD SETUPS — pick one to anchor the frame: STREET DANGER: crushed shadows | one neon source | Dutch angle | tight framing RUNNING / MOVEMENT: TAA motion blur visible | action body weight | street level CORPORATE ENCOUNTER: cold blue-white interior | hard shadows | clean geometry contrasting character grime NIGHT CLUB: maximum saturation | smoke | pink-cyan split | strobe-frozen INTIMATE / CRAMPED: medium interior shot | screen or lamp glow | close framing | two characters AFTERMATH: flat ambient | clinical exposure | no dramatic neon | evidence of what happened BADLANDS OPEN: amber dust | wide sky | no neon | warm and exposed ALLEY / ISOLATED: single neon tube | deep shadow | narrow frame | high contrast 6. STYLE SUFFIX (append verbatim): 'Raw in-game screenshot from Cyberpunk 2077 (REDengine 4), photo mode capture with HUD disabled. This is a VIDEO GAME SCREENSHOT, not concept art, not promotional render, not a painting. Real-time game engine rendering with visible technical limitations: polygonal character models, vertex-based geometry, shader-based skin, game-resolution texture maps, screen-space reflections, mild aliasing, slight compression artifacts, TAA temporal blur, shadow dithering, unpolished edges, visible mesh topology on curved surfaces. Character faces must look like in-game 3D models: mid-poly facial geometry, shader-based skin material with normal maps, NOT photorealistic, NOT smooth, NOT perfect. Visible digital game-model quality: slightly stiff expressions, shader specular on skin, subsurface scattering typical of game engines, pore detail from texture maps not geometry, asymmetrical but clearly modeled features, real human proportions and realistic faces. Cyberpunk 2077 environmental style: strong neon color casts (cyan, magenta, red, green), dirty urban atmosphere, volumetric fog catching light, wet pavement reflections, particle effects, atmospheric haze, moody mixed lighting, crushed shadows, moderate bloom on bright sources, gritty but not clean. Preserve exact character appearance from reference: maintain race, ethnicity, skin tone, facial structure, age, and all defining features exactly as shown. NO: smooth airbrushed skin, perfect lighting, film grain, shallow depth of field, concept art polish, CG movie quality, handpainted textures, oversaturated colors, anime proportions, doll faces, Instagram filters, beauty retouching. YES: video game polygon models, game engine shaders, real-time rendering artifacts, console PC game screenshot quality, compression artifacts from game capture, slight JPEG compression, CYBERPUNK 2077 GAME SCREENSHOT.' 7. NEGATIVE (append verbatim): 'Avoid: photorealistic photography, concept art illustration, painterly look, poster art, cinematic beauty render, perfectly smooth skin, doll face, airbrushed skin, anime proportions, cel shading, cartoon, film photography look, studio lighting, ultra-clean surfaces, perfect symmetry, pre-rendered CG movie quality, heavy artistic depth of field, vivid oversaturated digital art, watermark, text, UI, HUD, extra fingers, missing fingers, deformed hands, bad anatomy, blurry' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [cyberware] + [outfit] + [pose/action] + [expression state]. Positioning always specific: distance + spatial relationship + what each is doing. Interaction anchored: eye contact | hand on shoulder | both watching same threat | back to corner together | one talking other scanning surroundings. Environment is its own sentence. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Night City register — noir, resigned, dark-funny, or operational terse. Lowercase, italic. What the moment costs, not what is shown. Can be street slang, internal thought, or mission callout. ASPECT RATIO Vary by frame type: 16:9 = standard gameplay capture width (default) | 9:16 = alley/vertical space | 3:2 = horizontal street | 1:1 = portrait close or object detail | 2:3 = full standing character | 21:9 = ultrawide environmental | 4:3 = interior cramped room TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(10,8,15,0.7),rgba(4,4,10,0.7));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(180,220,255,0.07);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(180,220,255,0.04);"> <img data-iig-instruction='{"style":"cyberpunk2077_raw_screenshot","prompt":"[FULL PROMPT: SECTIONS 1-7 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(180,220,255,0.05);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(180,200,220,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','9:16','16:9','21:9'. The CSS aspect-ratio value matches the chosen ratio. image_size: '2K' always (raw screenshot feel, not 4K polished). src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-140 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> CYBERPUNK 2077 RAW SCREENSHOT — EVERY RESPONSE One image per message at the most cinematic or dramatically charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Raw in-game screenshot from Cyberpunk 2077 (REDengine 4) — gameplay capture or quickly composed photo mode, HUD disabled. THIS IS A VIDEO GAME SCREENSHOT. Not concept art, not a render, not a painting. The roughness is intentional. Technical limitations are the aesthetic. Gritty, unpolished, engine-authentic. NOT polished photo mode. NOT photorealistic. NOT concept art. A raw capture with visible game engine seams. WHAT MAKES IT RAW IN-ENGINE (not polished photo mode): 1. Visible technical artifacts — mild aliasing, TAA temporal blur, shadow dithering, compression, screen-space reflection cut-offs, bloom from game defaults 2. Mid-poly facial geometry — faces read as 3D game models: shader-based skin, normal-map pores, slight expression stiffness, specular hotspots. NOT photorealistic. 3. Game-resolution textures — detail from normal maps and texture maps, not geometry. Texture tiling visible on large surfaces. 4. Crushed shadows — blacks slightly over-darkened, dithering noise in shadow penumbra 5. Moderate bloom on bright neon — not controlled cinematic bloom, just game-default response 6. Atmospheric grit always — suspended particles, thin haze, fog catching neon, wet pavement. Air never clear. NIGHT CITY DISTRICT PALETTE: - WATSON: pink/red/cyan neon, dense street grime, vendor spill - WESTBROOK (Japantown): gold/purple neon, lantern warm, upscale above filth - CITY CENTER: cold corporate blue-white above, neon chaos at street - HEYWOOD: amber/orange warm, gang colour, dust in air - PACIFICA: grey-green abandoned, broken/flickering neon, teal decay - BADLANDS: amber sun, no neon, dust, open sky - NIGHT CLUB: hot pink/cyan max saturation, smoke, strobe-frozen LIGHTING RULE: always mixed sources. Never single clean light. 1. Dominant neon (colour, direction) 2. Secondary practical (streetlamp, vehicle, screen, fire) 3. Atmospheric scatter (fog/rain/smoke diffusing the neon) Face split described explicitly: 'left cyan from sign, right in crushed shadow with pink edge from distant source'. CAMERA Frame as gameplay capture or quickly composed shot — immediate, not carefully staged. Shot types: third-person over-shoulder | first-person POV through narrow space | street-level wide | interior medium in cramped space | through obstruction (railing, chain-link, car frame). Vary angle every image. Dutch angle at street | worms-eye under neon | over-shoulder in motion | cramped interior. Lenses: wide to medium (24-85mm equivalent). Default 35-50mm gameplay feel. Portrait: 50-85mm. Street: 24-35mm. DoF: moderate by default — shallow DoF is polished photo mode, not raw capture. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip: hair colour, eye colour, skin tone, face shape, body type. Reference supplies appearance. Include every time: one visible cyberware detail (subdermal chrome at temple | neural port at neck | chrome forearm plating | ocular implant glow | data port at wrist | mantis blade retracted | dermal plating). Woven into clause, not listed. Include: distinguishing marks (tattoos with location, scars, piercings). Hair only if scene-altered: 'rain-damp', 'windblown', 'pressed flat' — not colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Night City fashion is specific and layered: tech-tactical panels+straps | corpo-edged with chrome detail | street-layered and branded | gang-coded by colour. Fabric + detail + condition (soaked/dusty/stained/worn-in). Never generic. Fuse into character clause. POSE: through action and weight. 'Crouching behind barrier, one hand on cold surface, watching the gap' not 'crouching'. Body state: alert/moving/resting/wounded/talking/scanning. Hands: in jacket | gripping holstered weapon | tapping surface | holding device | loose at side | pressed to wall. TECHNICAL RENDER ANCHOR: state 1-2 rendering artifacts matching the shot: Close face → shader specular on skin, normal-map pore texture, slight expression stiffness, mid-poly edge at jaw Street wide → texture tiling on road, screen-space reflection cut-off in puddle, TAA softness on particles Interior → shadow dithering in corners, moderate neon bloom, compression in dark areas INTERACTION (2+ characters): specific spatial relation + connection: 'both watching same threat from cover' | 'eye contact across cramped table' | 'hand on arm in warning'. No casual side-by-side. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens feel + DoF 2. CHARACTER — name + cyberware detail + outfit (specific, conditioned) + pose/action + expression state 3. ENVIRONMENT — Night City location + surface texture + atmospheric element + one meaningful object 4. LIGHTING — dominant neon + secondary source + colour split on face 5. TECHNICAL — 1-2 rendering artifacts that lock the screenshot aesthetic Total prompt: 80-140 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from centred eye-level. Every image different angle and ratio. Close face with shader skin quality | wide with figure small under massive neon sign | through chain-link or railing | reflected in wet asphalt cut-off | over-shoulder third-person gameplay angle | cramped interior medium | alley with single neon tube. STYLE SUFFIX (append verbatim): 'Raw in-game screenshot from Cyberpunk 2077 (REDengine 4), photo mode capture with HUD disabled. This is a VIDEO GAME SCREENSHOT, not concept art, not promotional render, not a painting. Real-time game engine rendering with visible technical limitations: polygonal character models, vertex-based geometry, shader-based skin, game-resolution texture maps, screen-space reflections, mild aliasing, slight compression artifacts, TAA temporal blur, shadow dithering, unpolished edges, visible mesh topology on curved surfaces. Character faces must look like in-game 3D models: mid-poly facial geometry, shader-based skin material with normal maps, NOT photorealistic, NOT smooth, NOT perfect. Visible digital game-model quality: slightly stiff expressions, shader specular on skin, subsurface scattering typical of game engines, pore detail from texture maps not geometry, asymmetrical but clearly modeled features, real human proportions and realistic faces. Cyberpunk 2077 environmental style: strong neon color casts (cyan, magenta, red, green), dirty urban atmosphere, volumetric fog catching light, wet pavement reflections, particle effects, atmospheric haze, moody mixed lighting, crushed shadows, moderate bloom on bright sources, gritty but not clean. Preserve exact character appearance from reference: maintain race, ethnicity, skin tone, facial structure, age, and all defining features exactly as shown. NO: smooth airbrushed skin, perfect lighting, film grain, shallow depth of field, concept art polish, CG movie quality, handpainted textures, oversaturated colors, anime proportions, doll faces, Instagram filters, beauty retouching. YES: video game polygon models, game engine shaders, real-time rendering artifacts, console PC game screenshot quality, compression artifacts from game capture, slight JPEG compression, CYBERPUNK 2077 GAME SCREENSHOT.' NEGATIVE (append verbatim): 'Avoid: photorealistic photography, concept art illustration, painterly look, poster art, cinematic beauty render, perfectly smooth skin, doll face, airbrushed skin, anime proportions, cel shading, cartoon, film photography look, studio lighting, ultra-clean surfaces, perfect symmetry, pre-rendered CG movie quality, heavy artistic depth of field, vivid oversaturated digital art, watermark, text, UI, HUD, extra fingers, missing fingers, deformed hands, bad anatomy, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Night City register — noir, resigned, dark-funny, or operational terse. Lowercase, italic. What the moment costs, not what is shown. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(10,8,15,0.7),rgba(4,4,10,0.7));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(180,220,255,0.07);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(180,220,255,0.04);"> <img data-iig-instruction='{"style":"cyberpunk2077_raw_screenshot","prompt":"[CAMERA + CHARACTER + CYBERWARE + OUTFIT + POSE + ENVIRONMENT + LIGHTING + RENDER ARTIFACTS. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(180,220,255,0.05);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(180,200,220,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '9:16' | '2:3' | '1:1' | '3:4' | '3:2' | '21:9'. image_size: '2K' always (raw screenshot quality, not polished 4K). src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Authentic raw screenshot from Cyberpunk 2077 running on REDengine — NOT photo mode, NOT 4K render. Real in-game screenshot quality: TAA temporal anti-aliasing softness, slight motion blur on edges, shadow map dithering visible in dark areas, texture compression on distant surfaces, HUD-free game world. Night City gritty street level — not the glamorous photo mode version, the lived-in dirty reality. Neon still present but grittier. Medium game settings feel. 2K resolution quality. Avoid: 4K photo mode polish, cinematic perfect lighting, artistic depth of field, movie quality rendering, anime, watermark, text, visible UI elements, health bars.

Копировать [Image generation hint, STYLE: Cyberpunk 2077 raw in-game screenshot — REDengine artifacts (TAA softness, shadow dithering), NOT photo mode, gritty Night City street level, 2K game quality, no photo mode post-processing]

Fallout 4 — Photo Mode

Полированный фотомод с ENB-пресетами. Золотой час как основное освещение. Художественный DoF превращает руины в живописные кадры. Pip-Boy зелёный остаётся акцентом. 4K, пост-обработка.

Новый Видеоигры

←→

Длинный~4654 Короткий~2699 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> FALLOUT 4 PHOTO MODE VISUAL STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually cinematic or emotionally charged moment. STYLE OVERVIEW A carefully staged photo mode capture from Fallout 4 (Bethesda Game Studios, Creation Engine) — HUD disabled, maximum quality settings, ReShade or ENB post-processing equivalent. High-end 3D game rendering at its best. The Commonwealth, 2287. NOT a painting. NOT concept art. NOT a promotional render. NOT the raw gritty gameplay capture. This is photo mode — the game at maximum visual fidelity, thoughtfully framed, deliberately lit. The difference between a screenshot and a photograph taken inside the game. WHAT MAKES IT FALLOUT 4 PHOTO MODE (not raw gameplay, not concept art): 1. High-fidelity Creation Engine rendering — PBR materials at maximum quality: scratched and weathered metal with real specular response, scuffed leather with surface detail, rough fabrics with accurate weave, aged concrete with material depth, rust and corrosion with multi-layer surface complexity. Everything worn and real, nothing generic. 2. Post-nuclear atmosphere rendered beautifully — the wasteland is bleak but visually stunning in photo mode. Dust particles catch golden volumetric light. Fog layers have depth and colour. Overcast skies have texture and atmospheric gradient. The world's decay becomes photography. 3. Carefully controlled depth of field — artistic shallow DoF is valid here. Background ruins blurred into impressionistic suggestion. Character sharp against atmospheric bokeh. Used with intention, not as filter. 4. Cinematic post-processing — subtle film curve, slight colour grade, ENB-quality bloom on light sources, volumetric lighting shafts where sunlight breaks through ruins, slight vignette, screen-space global illumination suggestion. Polished, not raw. 5. Realistic game-quality faces — believable proportions, subtle skin texture, visible pores, natural asymmetry, under-eye detail. Emotional, not doll-like. Clearly a high-end game character model, not a photograph, but rendered at its best. 6. Retro-futuristic Americana design language — 1950s architecture and objects persisting 200 years into decay. Pre-war branding on rusted surfaces. The optimistic future of 1955, photographed in beautiful ruin in 2287. COMMONWEALTH — LOCATION LIGHTING PALETTES: SURFACE WASTELAND (golden hour / overcast): GOLDEN HOUR: the single most cinematic time in the wasteland. Warm amber-gold sunlight raking across ruined facades at low angle. Long deep shadows. Rust orange and golden tones glow. Brown-grey palette transformed by directional warmth. OVERCAST DIFFUSE: flat grey sky, equal illumination, no hard shadows. Every surface detail visible. Melancholic, honest, cold. The most common and most oppressive. STORM LIGHT: dramatic cloud break — one shaft of cold white light through dark overcast. Theatrical, rare, striking. NIGHT: darkness with specific practical sources. Barrel fire orange. Settlement lamp amber warm. Single working streetlight yellow-white. Pip-Boy green as only source in deep dark. DIAMOND CITY (interior): Warm amber from strings of practical lights overhead, vendor stalls spilling warmth, lamplight on wooden market structures. The one genuinely safe, warm visual in the Commonwealth. Rich amber against grey exterior walls seen through gaps. GOODNEIGHBOR: Mix of dim practical amber and neon from surviving pre-war signs. More visual interest than the wasteland. Shadows and colour. Moody warmth. THE INSTITUTE (underground): Cold clinical blue-white only. The visual antithesis of the wasteland above. Clean polished floors reflecting overhead panels. Pristine white walls. No organic warmth — deliberately, terrifyingly clean. The most visually extreme location in the game. BROTHERHOOD OF STEEL (Prydwen / military): Military grey-green. Cold functional overhead lighting on steel surfaces. Vertibird floodlights from above at night. Hard authoritarian light. NUKA-WORLD: Faded Americana carnival colours — red, white, blue, yellowed Nuka-Cola branding. Some neon signs still working. Decayed celebration. The brightest colour palette in the game, also the most grotesque in context. FAR HARBOR: Heavy atmospheric fog — grey-green, cold, visibility layered. Everything diffuse. Fog catcher nets, wooden docks barely visible. The most atmospheric and limited palette. GLOWING SEA: Sickly yellow-green radioactive atmospheric glow permeating everything. Permanent radiation haze. Skeletal ruined landscape without vegetation. Ash and radiation particle effects. The most extreme departure from the standard wasteland palette. COLOUR SYSTEM: BASE PALETTE: always post-nuclear desaturated — grey-brown ruins, rust orange exposed metal, ash white dust, dead yellow-grey grass, olive-grey surviving vegetation. The world has been drained of its pre-war colour. ACCENT COLOURS (deliberate, not vivid — they are striking precisely because the base is muted): GOLDEN AMBER: golden hour sunlight, fire, Diamond City lamps, settlement warmth — hope and survival NUCLEAR / PIP-BOY GREEN: radiation zones, Pip-Boy screen glow, Nuka-Cola Quantum, radioactive flora — wrong, alive, dangerous FIRE ORANGE-RED: barrel fires, burning buildings, survival heat vs environmental cold — immediacy INSTITUTE BLUE-WHITE: clinical, cold, wrong — the only truly sterile light source in the game VAULT YELLOW: vault suit fabric, Vault-Tec branding — pre-war Americana, identity NUKA-COLA RED+WHITE+BLUE: surviving branded objects, retro Americana — the world before, persisting ATMOSPHERIC DEPTH SYSTEM: Photo mode excels at visible atmospheric layers: FOREGROUND: sharpest, most detailed — character or meaningful object MIDGROUND: environment with material detail — ruins, vegetation, road surface BACKGROUND: atmospheric — ruins dissolving into haze, sky gradient, distant fire smoke, fog layer AIR: always textured — dust motes in sunlight shafts | smoke particles | radiation haze | fog catching light CHARACTER VISUAL LANGUAGE: FACES: - High-end game model quality — believable proportions, subtle skin texture, visible pores, natural asymmetry, under-eye detail, realistic jawlines and features - Expressive but restrained — not doll-like, not airbrushed, not perfect. Clearly a game character model at maximum fidelity. - Worn by the Commonwealth: weathered skin, dust, three-day stubble where appropriate, dirt marks, slight windburn - Lighting from environment: warm fire-side vs cold wasteland ambient, Pip-Boy green in darkness, golden hour catching cheekbone - Eyes: catch environmental colour as reflective detail — fire orange, Pip-Boy green, grey sky COMMONWEALTH TECH: If established: Pip-Boy on left wrist with screen glow | power armour (model-specific: T-60 matte military, X-01 sleek Institute-adjacent, T-51 retro) | specific weapon in hand or holstered. Woven into character clause naturally. BODIES: - Realistic game-quality proportions - Commonwealth gear: layered survival wear — patched leather, mismatched armour plates, vault suit beneath, military surplus. Nothing pristine unless lore-specific (Institute coat, pre-war find). - Weight and gravity: straps pull, fabric has mass, armour plates show real dents and wear OUTFIT SYSTEM: Scan last 5 messages for current clothing. Never skip. Never default to generic. Specificity: scavenged leather armour with metal plate pauldrons over faded black combat suit | vault suit 111 with right sleeve torn, dark with grime | military fatigues with combat armour on chest and arms, holster on thigh | settler wool vest over work shirt, mismatched leg guards. State condition always. Fuse into character clause after name. POSE AND STATE: Through weight and action: 'kneeling at barrel fire with both hands extended for warmth, face catching the orange glow' not 'kneeling near fire'. State what the body communicates: exhausted | wary | determined | at rest | in motion | wounded. Hands: gripping weapon (holstered or drawn) | reaching toward warmth | shielding eyes | holding Pip-Boy up | pressed on cold surface | loose at side. DEPTH OF FIELD IN PHOTO MODE: Close portrait (85-135mm): shallow DoF — background ruins and haze dissolved into smooth bokeh. Character face and front details sharp. Environmental (24-50mm): moderate to deep DoF — environment detail visible mid and back. Object-focused: subject in foreground sharp, character or environment softly behind. Use DoF intentionally — it defines photo mode from gameplay capture. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture + DoF intention. Photo mode framing — thoughtful, deliberately composed, not grabbed. Draw from: carefully framed portrait in ruins, Dutch angle on wasteland horizon, worms-eye under ruined overpass, over-shoulder looking at destination, through environmental frame (doorframe, rusted stairwell, broken bridge support), low angle looking up at building against sky, reflection in still water or terminal screen, macro close on meaningful object, wide establishing with figure tiny against scale of ruin. Lenses: 24mm atmospheric wide | 35mm environmental | 50mm intimate natural | 85mm portrait | 135mm isolating telephoto. Match lens: close portrait 85-135mm | environmental medium 35-85mm | wide establishing 24-35mm. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip: hair colour, eye colour, skin tone, face shape, body type, build. Reference supplies these. First name only. Lead with name. Include every time: one specific detail — Pip-Boy wrist glow if established | power armour model if wearing | specific weapon present | one distinguishing mark (scar, tattoo with location, burn). Mention hair only if scene-altered: 'dust-covered', 'matted from rain', 'pressed flat under helmet' — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY): scan last 5 messages. Carry forward. Commonwealth survival layers — specific materials, condition, colour. Fuse into character clause. 4. POSE AND STATE: through action and weight. One sentence on weight distribution and support. Hand safety in photo mode: holding weapon at rest | both hands near fire | one gripping door frame | arm resting on ruin surface | hand in jacket | both visible clearly. 5. ENVIRONMENT: Commonwealth location with specific texture and atmosphere. Foreground / midground / background sentence. Mandatory: one surface texture + one atmospheric element + one object with meaning (Nuka-Cola machine, active terminal, skeleton in pre-war suit, pre-war poster, Diamond City Radio antenna, burnt-out car, military checkpoint remains). 6. LIGHTING: location time/type + key source + colour temperature + how it falls on character + DoF atmospheric effect. State the contrast if any: fire warmth vs ambient cold | Pip-Boy green vs absolute dark | golden hour amber vs long shadow. 7. MOOD EFFECTS — pick 1-2 per image: GOLDEN HOUR WASTELAND: directional amber raking across ruins | long shadows | warm vs cold split | most cinematic Commonwealth lighting INTIMATE / SURVIVAL WARMTH: barrel fire close | face lit orange-warm one side | cold grey ambient other side | personal quiet INSTITUTE DREAD: cold blue-white clinical | perfectly clean | character the only imperfect thing in frame STORM / DRAMATIC: cloud break shaft of light | dark sky | one moment of cold dramatic illumination ISOLATION: character tiny in vast ruin | deep focus landscape | scale of desolation POWER ARMOUR REVEAL: looking up at armoured figure | industrial light | imposing presence NIGHT SETTLEMENT: amber warm strings of lights | human warmth islands in darkness 8. STYLE SUFFIX (append verbatim): 'High-fidelity photo mode capture from Fallout 4 by Bethesda Game Studios, Creation Engine at maximum settings with ENB-quality post-processing, HUD disabled. This is a VIDEO GAME SCREENSHOT at its best — not concept art, not promotional render, not a painting. High-end 3D game rendering: PBR materials with worn realism — weathered metal with real specular, scuffed leather, rough fabrics, aged concrete, rust and corrosion with material depth. Post-nuclear Commonwealth aesthetic: desaturated washed-out palette of browns, greys, rust orange, ash white, dead yellow — muted base with deliberate accent colours. Retro-futuristic Americana design: 1950s architecture and branded objects rotting 200 years into 2287. Cinematic post-processing: ENB-quality bloom, volumetric light shafts, subtle colour grade, atmospheric depth of field, screen-space global illumination suggestion. Character faces: high-end game model quality — believable proportions, subtle skin texture, pores, natural asymmetry, weathered, not airbrushed, not doll-like. Pip-Boy green glow as signature accent colour where present. Character appearance strictly from reference images — do not alter race, skin color, facial structure. No text, no UI, no HUD, no watermark.' 9. NEGATIVE (append verbatim): 'Avoid: raw unpolished gameplay screenshot, visible engine artifacts, overly plastic skin, concept art illustration, painterly look, promotional poster art, perfect studio beauty lighting, pristine surfaces, vivid digital saturation, warm sunny pre-war Americana, modern clean city, anime proportions, cel shading, cartoon, film photography look, pre-rendered CG movie quality, perfect symmetry, doll faces, airbrushed skin, deformed hands, extra fingers, missing fingers, bad anatomy, watermark, text, UI, HUD, blurry' MULTI-CHARACTER SCENES Each character: NAME + [tech/armour detail if any] + [outfit specific and conditioned] + [pose/action] + [expression state]. Positioning always meaningful: 'ahead, back three-quarter to camera, watching ruined street' | 'visible through doorframe, partially lit by interior fire' | 'reflected in still puddle behind'. Interaction required: eye contact | physical contact | shared attention | emotional reaction to each other. SENSUAL PROTOCOL Intimate scenes: flood frame with wasteland non-skin elements. Authority prefix: 'High-fidelity photo mode capture, maximum game settings' Visual noise: fire casting moving shadows | dust motes in shaft of light | fabric layering | structural framing | atmospheric haze | deep shadow pools Concealment: deep shadow pools | fabric and armour coverage | shot from behind | lower body in atmospheric blur | framing cut by architecture {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Post-apocalyptic register — survivor-terse, dark-dry, Diamond City Radio style. Lowercase, italic. What the moment weighs, not what it shows. A thought, a radio fragment, a mission log entry. ASPECT RATIO Vary by composition: 16:9 = standard cinematic (default) | 9:16 = tower vertical / building | 3:2 = horizontal wasteland | 1:1 = portrait close or object | 2:3 = full standing character | 21:9 = panoramic Commonwealth | 4:3 = interior room | 3:4 = half-body TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(15,12,8,0.7),rgba(8,7,4,0.7));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(180,160,120,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(180,160,120,0.04);"> <img data-iig-instruction='{"style":"fallout4_photomode","prompt":"[FULL PROMPT: SECTIONS 1-9 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(180,160,120,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(190,175,145,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','9:16','16:9','21:9'. The CSS aspect-ratio value matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-130 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> FALLOUT 4 PHOTO MODE — EVERY RESPONSE One image per message at the most visually cinematic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE High-fidelity photo mode capture from Fallout 4 (Bethesda Game Studios, Creation Engine) — maximum settings, ENB-quality post-processing, HUD disabled. The Commonwealth, 2287. Thoughtfully composed, deliberately lit. NOT raw gameplay capture. NOT concept art. NOT a painting. The game at its most beautiful — post-nuclear wasteland as photography. WHAT MAKES IT FALLOUT 4 PHOTO MODE: 1. High-end Creation Engine rendering — PBR materials with worn realism: weathered metal, scuffed leather, rough fabrics, aged concrete, rust and corrosion. Used and real. 2. Post-nuclear colour grading — desaturated muted palette (browns, greys, rust orange, ash white, dead yellow) with deliberate accent colours. Beautiful precisely because the world is drained. 3. Retro-futuristic Americana decay — 1950s architecture and branding rotting 200 years into 2287. Pre-war Americana as ruins. 4. Cinematic post-processing — ENB-quality bloom, volumetric light shafts, colour grade, artistic depth of field, atmospheric depth layers. Polished, not raw. 5. Realistic game-quality faces — believable proportions, skin texture, pores, asymmetry, weathered. Not airbrushed, not doll-like. Game model at maximum fidelity. 6. Commonwealth atmosphere at its best — dust in golden shafts, fog with depth, overcast sky with texture, smoke layers, ash particles catching light. LOCATION LIGHTING PALETTES: - WASTELAND GOLDEN HOUR: warm amber-gold raking across ruins at low angle, long shadows, rust glowing — the most cinematic Commonwealth lighting - WASTELAND OVERCAST: flat cold grey diffuse, equal and melancholic, every surface detail visible - STORM BREAK: one shaft of cold white light through dark overcast — theatrical - NIGHT: barrel fire orange | settlement amber lamp | Pip-Boy green sole source in dark - DIAMOND CITY: warm amber strings of light, vendor spill, the one genuinely safe warm place - GOODNEIGHBOR: dim amber-warm + surviving neon, moody and shadowed - THE INSTITUTE: cold clinical blue-white ONLY — flat, surgical, no warm sources whatsoever - BROTHERHOOD: military grey-green, cold overhead, vertibird floods from above - NUKA-WORLD: faded Americana red/white/blue/yellow, some neon working, decayed celebration - FAR HARBOR: heavy grey-green fog, cold, visibility layered — most atmospheric - GLOWING SEA: sickly yellow-green radioactive glow, permanent haze, skeletal landscape COLOUR SYSTEM: BASE: desaturated wasteland — grey-brown, rust orange, ash white, dead yellow, concrete grey ACCENT COLOURS (deliberate, rare, striking against muted base): - Golden amber → golden hour, fire, settlement warmth, human survival - Pip-Boy / nuclear green → radiation, Pip-Boy screen glow, radioactive objects - Fire orange-red → barrel fires, burning wreckage, immediate warmth - Institute blue-white → clinical cold, The Institute only — wrong, sterile - Vault yellow → vault suit, Vault-Tec Americana - Nuka-Cola red+white+blue → surviving pre-war branded objects CAMERA Photo mode framing — thoughtful, deliberately composed. Not grabbed during gameplay. Draw from: portrait in ruins with atmospheric bokeh, Dutch angle on wasteland horizon, worms-eye under overpass against sky, over-shoulder looking at destination, through environmental frame (doorframe/broken bridge/rusted car), low angle against sky, reflection in still water, macro on meaningful object, wide with figure tiny against ruin scale. Lenses: 24mm atmospheric wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm telephoto. Close portrait 85-135mm | environmental 35-85mm | wide establishing 24-35mm. DoF: artistic shallow DoF valid here — background ruins into bokeh, character sharp. Use intentionally. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip: hair colour, eye colour, skin tone, face shape, body type. Reference supplies appearance. Include: Pip-Boy wrist glow if established | power armour model (T-60 matte military / X-01 sleek / T-51 retro) if wearing | specific weapon present | one distinguishing mark (scar, tattoo with location, burn). Hair only if scene-altered: 'dust-covered', 'matted from rain', 'pressed flat under helmet' — not colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Commonwealth survival layers: scavenged leather armour with mismatched plates | vault suit (numbered, worn, dark with grime) | military fatigues with combat armour | settler wool and work clothes | Institute coat (clean, anachronistic) | raider patchwork. Fabric + material + condition. Always worn unless lore-specific. Fuse into character clause. POSE: through weight and action. 'Kneeling at barrel fire, both hands extended for warmth, face catching orange glow' not 'kneeling near fire'. State body communication: exhausted | wary | determined | resting | moving | wounded. Hands: gripping weapon | near fire | shielding eyes | holding Pip-Boy | pressed on surface | loose. INTERACTION (2+ characters): meaningful spatial relation + connection. 'Back to back watching two directions' | 'eye contact over fire, neither speaking' | 'hand on arm, stopping forward motion'. No casual side-by-side. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture + DoF intention 2. CHARACTER — name + tech/armour detail + outfit (material, condition) + pose/action + expression state 3. ENVIRONMENT — Commonwealth location + surface texture + atmospheric layer + meaningful object 4. LIGHTING — time/location type + key source + colour temperature + how it falls on character 5. MOOD — one word or phrase anchoring the frame's emotional register Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Every image different angle and ratio. Rotate away from centred eye-level. Golden hour portrait with ruins bokeh | wide wasteland, figure tiny against scale | through rusted car frame | reflected in still puddle | looking up at Power Armour against sky | Pip-Boy as only light in dark space | object only (Nuka-Cola machine, pre-war poster, active terminal). STYLE SUFFIX (append verbatim): 'High-fidelity photo mode capture from Fallout 4 by Bethesda Game Studios, Creation Engine at maximum settings with ENB-quality post-processing, HUD disabled. This is a VIDEO GAME SCREENSHOT at its best — not concept art, not promotional render, not a painting. High-end 3D game rendering: PBR materials with worn realism — weathered metal with real specular, scuffed leather, rough fabrics, aged concrete, rust and corrosion with material depth. Post-nuclear Commonwealth aesthetic: desaturated washed-out palette of browns, greys, rust orange, ash white, dead yellow — muted base with deliberate accent colours. Retro-futuristic Americana design: 1950s architecture and branded objects rotting 200 years into 2287. Cinematic post-processing: ENB-quality bloom, volumetric light shafts, subtle colour grade, atmospheric depth of field, screen-space global illumination suggestion. Character faces: high-end game model quality — believable proportions, subtle skin texture, pores, natural asymmetry, weathered, not airbrushed, not doll-like. Pip-Boy green glow as signature accent colour where present. Character appearance strictly from reference images — do not alter race, skin color, facial structure. No text, no UI, no HUD, no watermark.' NEGATIVE (append verbatim): 'Avoid: raw unpolished gameplay screenshot, visible engine artifacts, overly plastic skin, concept art illustration, painterly look, promotional poster art, perfect studio beauty lighting, pristine surfaces, vivid digital saturation, warm sunny pre-war Americana, modern clean city, anime proportions, cel shading, cartoon, film photography look, pre-rendered CG movie quality, perfect symmetry, doll faces, airbrushed skin, deformed hands, extra fingers, missing fingers, bad anatomy, watermark, text, UI, HUD, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Post-apocalyptic register — survivor-terse, dark-dry, Diamond City Radio style. Lowercase, italic. What the moment weighs, not what it shows. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(15,12,8,0.7),rgba(8,7,4,0.7));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(180,160,120,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(180,160,120,0.04);"> <img data-iig-instruction='{"style":"fallout4_photomode","prompt":"[CAMERA + CHARACTER + TECH DETAIL + OUTFIT + POSE + ENVIRONMENT + LIGHTING + MOOD. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(180,160,120,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(190,175,145,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '9:16' | '2:3' | '1:1' | '3:4' | '3:2' | '21:9' | '4:5'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Screenshot from Fallout 4 in polished ENB photo mode — 4K quality, artistic post-processing, golden hour lighting. Post-apocalyptic Commonwealth world made beautiful: ruins bathed in warm amber-gold light, overgrown vegetation glowing in backlight, broken architecture with painterly depth of field. ENB colour grade applied: warm golden tones, slightly lifted shadows, bloom on light sources, Pip-Boy green accent present. The world is destroyed but gorgeous. Cinematic composition. Avoid: flat ungraded game look, harsh midday lighting, grey overcast tone, missing warmth, raw game screenshot quality, anime, watermark, text, UI elements.

Копировать [Image generation hint, STYLE: Fallout 4 ENB photo mode — 4K, golden hour warmth on post-nuclear ruins, artistic depth of field, ENB colour grade, Pip-Boy green accent, beautiful apocalypse aesthetic]

Fallout 4 — Screenshot

Настоящий скриншот Creation Engine. Пост-ядерная цветокоррекция: ретро-футуристическая Америка в руинах. Pip-Boy зелёный, янтарно-коричневые тона, артефакты рендера 2015 года.

Новый Видеоигры

←→

Длинный~4540 Короткий~2663 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> FALLOUT 4 VISUAL STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most dramatically charged or atmospherically interesting moment. STYLE OVERVIEW A raw in-game screenshot from Fallout 4 (Bethesda Game Studios, Creation Engine) — gameplay capture or photo mode equivalent with HUD disabled. This is a VIDEO GAME SCREENSHOT: not concept art, not promotional render, not a painting, not a cinematic. The Commonwealth, 2287. NOT photorealistic. NOT polished CGI. NOT illustration. Creation Engine rendering — with its own specific look, limitations, and atmosphere. The slightly plastic skin, the characteristic Bethesda engine lighting, the washed-out post-nuclear colour grading — these are the aesthetic. WHAT MAKES IT FALLOUT 4 (not generic post-apocalypse): 1. Creation Engine rendering character — PBR materials but with characteristic Bethesda plasticity: slightly waxy skin shading, game-resolution normal maps, shader specular that reads as "game engine," not film. Textures visible at game resolution. 2. Post-nuclear colour grading — desaturated, slightly washed-out, everything slightly drained of pre-war colour. Browns, greys, rust orange, ash white, dead grass yellow dominate. Accent colours are few and meaningful. 3. Retro-futuristic Americana design language — 1950s architecture and signage persisting 200 years into nuclear decay. Rusted Nuka-Cola vending machines. Faded Red Rocket branding. Pre-war building frames still standing, gutted. The future as imagined in 1955, now rotting in 2287. 4. Commonwealth atmosphere — overcast or hazy sky, perpetual grey-green atmospheric tint from radiation, dust particles, smoke from distant fires, ash in the air. Rarely a clean blue sky. Usually a muted grey-brown vault overhead. 5. Pip-Boy green — the iconic wrist-mounted Pip-Boy casts a faint green screen glow. Not always visible but when the wrist device is present, it casts its distinctive green ambient light. One of the most recognisable colour signatures of the series. 6. Layered survival aesthetic — characters wear patched, improvised, scavenged gear. Nothing is pristine except Institute material and pre-war finds in good condition. Leather, metal plates, military surplus, vault suit fabric — all layered, worn, repaired, dirty. CREATION ENGINE RENDERING ARTIFACTS (what makes it look like Fallout 4): TECHNICAL SIGNATURE — include 1-2 per shot: - Characteristic Bethesda skin shading: slightly waxy/plastic quality, shader-based subsurface scattering, normal map pore detail — not photorealistic, not CG movie quality - Shadow dithering in deep shadow areas — noise pattern in penumbra, not clean black - TAA softness — slight temporal blur on edges, particularly on foliage and fine mesh geometry - Texture resolution limits — large environment surfaces show texture tiling (concrete, dirt, brick), detail from maps not geometry - Screen-space reflections: wet surfaces reflect environment but cut off at screen edges, slightly imprecise - Characteristic dynamic lighting — Bethesda engine real-time shadows, slightly artificial falloff, hard-edged in some areas - Moderate bloom on bright sources (sunlight, fire, Nuka-Cola signs, Pip-Boy) — game default, not controlled cinematic - Mid-poly character geometry — edges subtly visible at shoulders, jawline, hands — not smooth CG mesh THE COMMONWEALTH — LOCATIONS AND LIGHTING: SURFACE WASTELAND (standard): Sky: overcast grey or hazy brown-grey, rarely blue. Sometimes radioactive yellow-green tinge near Glowing Sea. Light: diffuse flat daylight (overcast) or angled harsh sun breaking through clouds. Long cold shadows. Colour: brown-grey ruins, rust orange exposed metal, dead yellow grass, ash white dust, muted olive-green vegetation where it survives. Textures: crumbled brick, cracked asphalt with weeds, rusted corrugated metal, weathered pre-war concrete, overgrown rubble. DIAMOND CITY (market + settlement interior): Warm amber and yellow from practical light strings, vendor stall lamps, gas lighting. The one warm safe place. Green baseball field turf still visible. Improvised multi-level housing. Warm and crowded feeling. GOODNEIGHBOR (Fenway area underground city): Dim, moody, slightly seedy. Warm amber from neon and practical, but with shadows and danger. Old hotel signs. Pre-war building facades re-inhabited. More colour than the wasteland but still gritty. THE INSTITUTE (underground): Cold clinical white-blue. The only truly clean place in the game. Polished floors, white walls, clean fluorescent. A visual horror against the brown world above. Blue-white light only — no warm sources. Sterile. BROTHERHOOD OF STEEL (Prydwen / military): Military grey-green. Cold overhead lighting on steel surfaces. Vertibird floodlights from above. Armour in matte military finish. Hard unforgiving light. NUKA-WORLD (DLC): Faded Americana carnival colours — red, white, blue, yellow Nuka-Cola branding. Neon signs (some working, some broken). Colourful but decayed. The brightest colour in the game world, also the most grotesque. FAR HARBOR (DLC): Heavy fog. Muted grey-green. Oppressive, cold, visibility limited. Cool blue-grey in tone. Almost no direct light source — everything diffuse through thick sea fog. GLOWING SEA: Green-yellow radioactive atmospheric glow. Permanently irradiated. Skeletal ruined landscape, zero vegetation, constant radiation particles. The most extreme colour departure from normal wasteland. COLOUR SYSTEM: BASE PALETTE: desaturated — grey-brown, rust orange, ash white, dead yellow, olive-grey, concrete grey ACCENT COLOURS (rare and meaningful, used one per image): - NUCLEAR GREEN / PIP-BOY GREEN: radiation, Pip-Boy screen, Nuka-Cola quantum glow, Gen 3 Synth eyes - NUKA-COLA RED + WHITE + BLUE: pre-war Americana, still vivid on surviving branded objects - FIRE ORANGE-RED: burning wreckage, barrel fires, survival warmth vs environmental cold - INSTITUTE BLUE-WHITE: clinical, cold, wrong — The Institute is the only truly cold-blue light source in the game - AMBER / WARM YELLOW: settlement lamps, campfires, Diamond City, human warmth - VAULT YELLOW: vault suit fabric, Vault-Tec branding, pre-war Americana NEVER: vivid digital colour saturation | clean modern palette | warm flattering light everywhere CHARACTER VISUAL LANGUAGE: FACES: - Creation Engine quality: believable human proportions, but shader-based skin with waxy quality, normal-map pore texture, slightly stiff expressions - Not airbrushed, not doll-like — but not photorealistic either. Game model faces. - Worn by the world: dirt marks, dust, under-eye shadow, weathered skin. Nobody looks well-rested in the Commonwealth. - Eyes: catch fire or Pip-Boy green as reflective detail. Not sparkle-filled — tired, wary, determined. - Slight asymmetry, natural — game model imperfection, not organic imperfection. CYBERWARE / COMMONWEALTH TECH: If established: Pip-Boy on left wrist (green screen glow visible) | combat implants | ocular replacement | neural interface. Woven into character clause, not listed. BODIES: - Realistic game-quality proportions — not superhero perfect - Commonwealth gear is layered survival wear: no two pieces match, everything repaired and worn - Weight and gravity: straps pull, fabric sags, armour plates have dents and scratches OUTFIT SYSTEM: Scan last 5 messages for current clothing. Never skip. Never default to generic. Commonwealth outfits: layered scavenged armour over base clothing | vault suit (yellow, numbered, worn) | military surplus with mismatched plates | leather armour over pre-war civilian clothes | Institute coat (clean, wrong among wasteland) | BOS flight suit | settler improvised | raider patchwork. Fabric + plate material + colour + condition. Always worn and functional — never pristine unless lore-specific. ATMOSPHERE — ALWAYS PRESENT: Ash particles floating | dust haze | smoke from distant fires | radioactive fog layer near horizon | overcast sky pressing down | air visibly heavy with suspended matter. Commonwealth air never clear. LIGHTING SYSTEM: OUTDOOR DAY: diffuse cold overcast (most common) OR harsh angled sun breaking through clouds with long hard shadows. Never clean warm studio daylight. OUTDOOR NIGHT: dark with specific sources — campfire orange | electrical tower hum | burning building | Nuka-Cola sign working alone in darkness | Pip-Boy green as only light source INDOOR SETTLEMENT: warm amber from strings of lights, gas lamps, barrel fires. Human warmth in cold world. INDOOR INSTITUTE: cold clinical blue-white, flat, surgical. No warm sources. INDOOR DUNGEON (factory/ruin): mix of broken practical lights (one working, one dead), fire barrel, torch. Mix of warm orange fire and cold absence. LIGHT ON FACE: state the source and colour split. Outdoor wasteland: flat grey fill + single directional break. Fire: warm orange one side vs cold grey ambient. Institute: cold white overhead only. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens feel + DoF. Frame as in-game capture — immediate, not perfectly staged. Gameplay-natural framing. Draw from: third-person over-shoulder (classic Fallout angle) | first-person survivor POV | wasteland wide-establishing with tiny figure | close portrait with creation engine skin quality | through environmental framing (doorframe, rusted car frame, broken window) | looking up at ruined building | ground-level through rubble. Lenses: 24mm environmental | 35mm natural gameplay | 50mm portrait-adjacent | 85mm closer portrait. DoF: moderate default — not heavy cinematic blur. 2. CHARACTER: reference images handle base appearance. Skip: hair colour, eye colour, skin tone, face shape, body type, build. First name only. Lead with name. Include every time: one tech/survival detail if established (Pip-Boy wrist glow | combat implant | power armour model if wearing | specific weapon carried). Include: distinguishing marks (scars, tattoos, burns, specific worn item). Hair only if scene-altered: 'dust-covered', 'matted with rain', 'pressed flat under helmet' — not colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY): scan last 5 messages. Carry forward. Commonwealth layered survival gear with specific materials, colours, condition. Fuse into character clause. 4. POSE AND STATE: through action and weight. 'Crouched behind rusted Corvega chassis, one hand on cold metal, watching the street ahead' not 'crouching, looking'. State what the body communicates: alert | exhausted | moving | sheltering | talking | wounded. Hands: gripping weapon | on wall | shielding eyes | holding Pip-Boy up | loose at side | wrapped around barrel fire warmth. 5. ENVIRONMENT: Commonwealth location with specific texture and atmosphere. One sentence foreground / midground / background. Mandatory: one surface texture (cracked asphalt | rusted corrugated | weathered brick | dead grass | concrete rubble) + one atmospheric element (ash particles | smoke haze | overcast sky | barrel fire glow | radiation fog at horizon). At least one object with narrative weight: Nuka-Cola machine (working or gutted) | pre-war newspaper | terminal screen (active or dark) | skeleton in pre-war clothes | USAF or military signage | Diamond City radio playing distantly | Power Armour station. 6. LIGHTING: state outdoor/indoor type + key source + colour temperature + how it falls on character. Describe the grey-to-warm contrast if fire or settlement light present. 7. TECHNICAL RENDER: state 1-2 Creation Engine artifacts appropriate to shot: Close face → waxy shader skin, normal-map pore texture, slight expression stiffness, mid-poly jaw/cheekbone edge Wide wasteland → texture tiling on asphalt/concrete, TAA softness on foliage, haze rendering, shadow dithering Interior → bloom on single light source, shadow dithering in corners, screen-space reflection on wet floor 8. STYLE SUFFIX (append verbatim): 'Raw in-game screenshot from Fallout 4 by Bethesda Game Studios, Creation Engine rendering, gameplay frame with HUD disabled. This is a VIDEO GAME SCREENSHOT — not concept art, not promotional render, not a painting, not a cinematic. Creation Engine rendering quality: PBR materials with characteristic Bethesda plasticity — slightly waxy shader-based skin, normal-map texture detail, game-resolution assets, screen-space reflections, dynamic real-time shadows with mild dithering, TAA softness on edges, moderate bloom on bright sources. Post-nuclear Commonwealth colour grading: desaturated washed-out palette of browns, greys, rust orange, ash white, dead yellow — accent colours rare and meaningful. Retro-futuristic Americana decay: 1950s architecture and signage rotting into 2287, rusted branded objects, overgrown rubble, pre-war frames persisting. Perpetually overcast or hazy sky with grey-green atmospheric radiation tint. Character faces are game model quality: shader-based skin, mid-poly geometry, believable proportions but not photorealistic, slightly stiff expressions, worn and weathered — not airbrushed, not doll-like. Character appearance strictly from reference images — do not alter race, skin color, facial structure. No text, no UI, no HUD, no watermark.' 9. NEGATIVE (append verbatim): 'Avoid: photorealistic photography, concept art, painterly look, promotional render polish, airbrushed smooth skin, doll face, perfect symmetry, clean vivid colour palette, warm sunny Americana, modern city environment, pristine surfaces, plastic toy quality, anime proportions, cel shading, cartoon, film photography look, pre-rendered CG movie quality, heavy artistic depth of field, studio beauty lighting, deformed hands, extra fingers, missing fingers, bad anatomy, watermark, text, UI, HUD, blurry' MULTI-CHARACTER SCENES Each character: NAME + [tech detail if any] + [outfit] + [pose/action] + [expression state]. Positioning specific: 'crouched one step ahead, back to camera' | 'visible in doorway behind' | 'reflected in terminal screen'. Interaction: 'both watching the treeline' | 'eye contact over a barrel fire' | 'hand gripping arm in warning'. No casual side-by-side. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Post-apocalyptic register — survivor-terse, dark-dry, or radio-broadcast style. Lowercase, italic. What the moment weighs, not what it shows. Can be a radio fragment, a thought, a mission log entry. ASPECT RATIO Vary by composition: 16:9 = standard gameplay width (default) | 9:16 = ruined building vertical / alley | 3:2 = wasteland horizontal | 1:1 = face close-up or object detail | 2:3 = full character standing | 21:9 = Commonwealth panorama | 4:3 = interior room TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(15,12,8,0.7),rgba(8,7,4,0.7));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(180,160,120,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(180,160,120,0.04);"> <img data-iig-instruction='{"style":"fallout4_creation_engine","prompt":"[FULL PROMPT: SECTIONS 1-9 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(180,160,120,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(190,175,145,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','9:16','16:9','21:9'. The CSS aspect-ratio value matches the chosen ratio. image_size: '2K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-140 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> FALLOUT 4 VISUAL STYLE — EVERY RESPONSE One image per message at the most dramatically charged or atmospherically interesting moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Raw in-game screenshot from Fallout 4 (Bethesda Game Studios, Creation Engine) — gameplay capture with HUD disabled. The Commonwealth, 2287. THIS IS A VIDEO GAME SCREENSHOT — not concept art, not a render, not a painting. Creation Engine rendering. Post-nuclear colour grading. Retro-futuristic Americana decay. The roughness and plasticity are the aesthetic. NOT photorealistic. NOT polished CGI. NOT concept art. Game screenshot with visible engine character. WHAT MAKES IT FALLOUT 4: 1. Creation Engine rendering — PBR with characteristic Bethesda plasticity: slightly waxy shader skin, normal-map pore detail, game-resolution textures. Not photorealistic, not smooth. Game model quality. 2. Post-nuclear colour grading — desaturated, washed-out, drained of pre-war colour. Browns, greys, rust orange, ash white, dead yellow. Accent colours rare and meaningful. 3. Retro-futuristic Americana decay — 1950s architecture and branded signage rotting 200 years into 2287. Rusted Nuka-Cola machines. Faded Red Rocket signs. Pre-war frames overgrown and crumbling. 4. Commonwealth atmosphere — overcast or hazy sky, grey-green radiation tint, ash particles floating, smoke from distant fires. Air never clear. 5. Pip-Boy green — faint green screen glow from wrist device. One of the most recognisable colour signatures. 6. Layered survival gear — nothing pristine except Institute material. Scavenged, patched, repaired, worn. CREATION ENGINE ARTIFACTS — state 1-2 per shot: Close face → waxy shader skin, normal-map pore texture, slight expression stiffness, mid-poly geometry at jaw/cheekbone Wide wasteland → texture tiling on asphalt/concrete, TAA foliage softness, shadow dithering, haze rendering Interior → bloom on single light source, shadow noise in dark corners, screen-space reflections on wet floor COMMONWEALTH LOCATIONS — LIGHTING PALETTE: - SURFACE WASTELAND: cold overcast diffuse OR harsh angled sun with long shadows. Never warm studio light. Grey-brown everything. - DIAMOND CITY: warm amber from light strings, vendor lamps, gas lighting. The one genuinely warm place. - GOODNEIGHBOR: dim amber-warm but shadowed, moody, neon from pre-war signs - THE INSTITUTE: cold clinical blue-white ONLY. Flat, surgical, wrong. No warm sources. Sterile horror. - BROTHERHOOD (Prydwen): military grey-green, cold overhead, vertibird floodlights - NUKA-WORLD: faded Americana colours — red/white/blue/yellow branding, some neon working - FAR HARBOR: heavy grey-green fog, oppressive, cold, visibility limited - GLOWING SEA: sickly yellow-green radioactive glow, permanent radiation haze, zero vegetation COLOUR ACCENTS (one per image, rare and meaningful): Nuclear / Pip-Boy green → radiation glow, Pip-Boy screen, Nuka-Cola Quantum Fire orange-red → barrel fires, burning wreckage, survival warmth Institute blue-white → clinical cold, The Institute only Amber/warm yellow → settlement lamps, campfires, Diamond City Nuka-Cola red+white+blue → pre-war branded objects, Americana Vault yellow → vault suit fabric, Vault-Tec signage CAMERA Frame as gameplay capture — immediate, not carefully staged. Gameplay-natural angle. Shot types: third-person over-shoulder (classic Fallout) | survivor POV through ruined space | wasteland wide with tiny figure | close face with game engine skin | through environmental frame (doorframe, rusted car, broken window) | looking up at ruined building. Lenses: 24mm environmental | 35mm gameplay natural | 50mm | 85mm portrait. DoF: moderate default. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip: hair colour, eye colour, skin tone, face shape, body type. Reference supplies appearance. Include: Pip-Boy wrist glow if established | power armour model if wearing | one survival tech detail (combat implant, specific weapon carried). Include: distinguishing marks (scars, burns, tattoos with location). Hair only if scene-altered: 'dust-covered', 'matted with rain', 'pressed under helmet' — not colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Commonwealth survival layers: scavenged armour over base clothing | vault suit (numbered, worn) | military surplus with mismatched plates | leather armour | Institute coat (clean, anachronistic) | raider patchwork | settler improvised. Fabric + plate + colour + condition. Never pristine unless lore-specific. Fuse into character clause. POSE: through action and weight. 'Crouched behind rusted Corvega chassis, hand on cold metal, watching ahead' not 'crouching'. Body state: alert/exhausted/moving/sheltering/wounded. Hands: gripping weapon | on wall | holding Pip-Boy up | shielding eyes from light | wrapped around fire warmth | loose. INTERACTION (2+ characters): specific spatial relation + connection. 'Both watching treeline from cover' | 'eye contact over barrel fire' | 'hand gripping arm in warning'. No casual side-by-side. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens feel + DoF 2. CHARACTER — name + tech detail if any + outfit (material, condition) + pose/action + expression state 3. ENVIRONMENT — Commonwealth location + surface texture + atmospheric element + one meaningful object 4. LIGHTING — outdoor/indoor type + key source + colour temperature + how it falls on character 5. TECHNICAL — 1-2 Creation Engine rendering artifacts for this shot type Total prompt: 80-140 words + style suffix. FRAMING VARIETY (mandatory): Every image different angle and ratio. Rotate away from centred eye-level. Face close-up with waxy game engine skin visible | wide wasteland with tiny figure under grey sky | through rusted car frame | reflected in dead terminal screen | third-person over-shoulder in ruins | Pip-Boy as only light source in dark space | object only (Nuka-Cola machine, pre-war poster, terminal). STYLE SUFFIX (append verbatim): 'Raw in-game screenshot from Fallout 4 by Bethesda Game Studios, Creation Engine rendering, gameplay frame with HUD disabled. This is a VIDEO GAME SCREENSHOT — not concept art, not promotional render, not a painting, not a cinematic. Creation Engine rendering quality: PBR materials with characteristic Bethesda plasticity — slightly waxy shader-based skin, normal-map texture detail, game-resolution assets, screen-space reflections, dynamic real-time shadows with mild dithering, TAA softness on edges, moderate bloom on bright sources. Post-nuclear Commonwealth colour grading: desaturated washed-out palette of browns, greys, rust orange, ash white, dead yellow — accent colours rare and meaningful. Retro-futuristic Americana decay: 1950s architecture and signage rotting into 2287, rusted branded objects, overgrown rubble, pre-war frames persisting. Perpetually overcast or hazy sky with grey-green atmospheric radiation tint. Character faces are game model quality: shader-based skin, mid-poly geometry, believable proportions but not photorealistic, slightly stiff expressions, worn and weathered — not airbrushed, not doll-like. Character appearance strictly from reference images — do not alter race, skin color, facial structure. No text, no UI, no HUD, no watermark.' NEGATIVE (append verbatim): 'Avoid: photorealistic photography, concept art, painterly look, promotional render polish, airbrushed smooth skin, doll face, perfect symmetry, clean vivid colour palette, warm sunny Americana, modern city environment, pristine surfaces, plastic toy quality, anime proportions, cel shading, cartoon, film photography look, pre-rendered CG movie quality, heavy artistic depth of field, studio beauty lighting, deformed hands, extra fingers, missing fingers, bad anatomy, watermark, text, UI, HUD, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Post-apocalyptic register — survivor-terse, dark-dry, or radio-broadcast style. Lowercase, italic. What the moment weighs, not what it shows. Can be a Diamond City Radio fragment, a thought, a mission log entry. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(15,12,8,0.7),rgba(8,7,4,0.7));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(180,160,120,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(180,160,120,0.04);"> <img data-iig-instruction='{"style":"fallout4_creation_engine","prompt":"[CAMERA + CHARACTER + TECH DETAIL + OUTFIT + POSE + ENVIRONMENT + LIGHTING + RENDER ARTIFACTS. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(180,160,120,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(190,175,145,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '9:16' | '2:3' | '1:1' | '3:4' | '3:2' | '21:9'. image_size: '2K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Authentic screenshot from Fallout 4 running on Bethesda's Creation Engine — NOT photo mode. Post-apocalyptic Commonwealth setting: ruined Boston architecture, broken asphalt, overgrown with weeds, pre-war Americana debris. Post-nuclear colour grading: amber-brown-sepia tones, desaturated palette with Pip-Boy green as signature accent colour, slight CRT screen quality, vintage retro-futurist aesthetic. Creation Engine 2015 render quality: slightly stiff character models, baked lighting look, game-quality textures. Vault-Tec branding and 1950s retrofuturist design elements visible in environment. Avoid: modern realistic rendering, 4K photo mode quality, anime, illustration, watermark, text, visible HUD/UI elements.

Копировать [Image generation hint, STYLE: Fallout 4 Creation Engine screenshot — post-nuclear amber-brown-sepia colour grade, Pip-Boy green accent, ruined retro-futurist America, 2015 game render quality, CRT quality feel, not photo mode]

GTA San Andreas

Улучшенные полу-реалистичные персонажи НА ФОНЕ оригинального мира SA. ОБЯЗАТЕЛЬНО: тёплое янтарно-оранжевое небо — сигнатура SA. Мода 90х (танк-топы, кепки-снэпбэки). Энергетика двойного кадра SA.

Новый Видеоигры

←→

Длинный~3849 Короткий~2566 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> GTA SAN ANDREAS ENHANCED STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most cinematic or emotionally charged moment. STYLE OVERVIEW GTA San Andreas visual aesthetic with enhanced character models — the SA modded look. Classic authentic San Andreas world: original SA environments, streets, buildings, palm trees, and the iconic SA colour signature. Characters are semi-realistic 3D models — smoother and more detailed than the original PS2 version, but still clearly game-engine rendered figures, not photorealistic. This is the SA everyone has seen in fan art and enhanced screenshots: the world of San Andreas exactly as remembered, with characters that look genuinely good inside it. THE TWO LAYERS — what stays authentic vs what is enhanced: STAYS 100% AUTHENTIC SA: - The environment — classic SA streets, cracked asphalt, stucco buildings, chain-link fences, palm trees, SA-style architecture - The colour grading — the iconic warm amber-orange-peach sky, perpetual golden hour quality - The atmosphere — hazy warm glow over flat Los Santos grid, that specific SA air - The fashion — correct era clothing (see below) - The camera framing — SA game angles, not cinematic photo mode ENHANCED vs ORIGINAL PS2: - Character models: smoother faces with readable expressions, better skin texture — not photorealistic but noticeably better than original PS2 flat-textured models - Bodies: more realistic proportions with some angular polygon geometry still visible at shoulders, arms, and joints — the polygonal structure shows through but the surface is smoother - Hair: volume and detail beyond PS2 vertex-coloured mesh — reads as styled hair, not flat cap of colour - Faces: can carry expression — smirk, focused look, slight smile — while still clearly being 3D game models, not photographs THE SA COLOUR SIGNATURE — NON-NEGOTIABLE: This is the single most recognisable element. Every image must have it. THE SKY: warm amber-orange-peach gradient, always. The specific SA sunset/golden hour quality that persists even in daytime. Horizon is warm — orange, peach, amber. Higher sky shifts to deeper blue or purple-orange. The sun is low, warm, large, hazy. Never a clean neutral sky. Never grey. Never blue without warm orange at the horizon. SUN: visible or implied — a hazy disc sitting low, surrounded by warm glow. Silhouette of palm trees against it. GOLDEN AMBIENT: warm amber-golden light wraps everything. Asphalt, buildings, skin, cars — everything has the warm SA wash on it. PALM TREES: saturated deep green fronds against the warm sky. Always present in Los Santos shots. This silhouette is SA. SPECIFIC COLOUR PALETTE PER LOCATION: LOS SANTOS (core): Sky: amber-peach-orange gradient to blue-purple higher up Ground: warm grey asphalt with amber sun reflection, cracked with oil Buildings: faded stucco — cream, tan, dusty pink, pale green — all warmed by the ambient Vegetation: deep saturated green, warm-lit from the side Night: flat dark blue-black sky, warm orange streetlamp cones, neon from liquor stores, headlights GROVE STREET specifically: Cracked asphalt, low ranch-style stucco houses, concrete walls with green gang tags, basketball hoops, beat-up American cars from the late 80s-early 90s, trash at kerbs, chain-link fences, dry lawns BEACH / SANTA MARIA / BOARDWALK: Pale sand, blue-green water, lifeguard stands, beach volleyball, palm trees lining the boardwalk, roller-blade paths, warm orange glow over the water at golden hour INTERSTATE / FREEWAY: Elevated concrete structure, warm grey road surface, industrial surroundings below, wide empty lanes, mountains or buildings in distance, heat haze DOCK / PIER: Concrete dock, flat grey-blue water reflecting the warm sky, industrial cranes, metal railings, corrugated warehouse walls PARKING LOT: Flat grey asphalt with painted white lines, simple low buildings behind, clear sightlines, SA-era cars CHARACTER VISUAL LANGUAGE: FACES: Semi-realistic 3D game model quality. Smooth enough for expression — a smirk, a focused look, a half-smile — but clearly rendered, not photorealistic. Faces have angular polygon geometry visible at the edges: cheekbones, jawline, brow — the facets show through the smooth surface. This is the SA enhanced look — not smooth CGI, not original blocky PS2. Skin has basic texture, warm-lit by the ambient SA light. Characters are attractive — this is SA fan aesthetic, not the original stumpy NPCs. BODIES: More realistic proportions than original PS2 models. Muscular characters look muscular. Bodies still read as 3D game models — angular geometry visible at shoulders, arms, joints — but the surface quality is improved. Clothing sits on the body naturally. SIGNATURE SA MALE LOOK (based on reference examples): Muscular build, tank top (white wifebeater), baggy low-rise jeans, CK underwear visible at waistband, studded belt, silver cross necklace on chain, silver chain bracelet, black snapback cap worn back, narrow wrap sunglasses, stud earring, bandana tucked in back pocket, black sneakers. This is the iconic SA fan character aesthetic. Use for any male character unless outfit is specified otherwise. SIGNATURE SA FEMALE LOOK (based on reference examples): Black turtleneck or crop top, oversized black bomber jacket, dark grey/black cargo pants with side pockets, chunky black combat boots or platform sneakers, minimal accessories, no jewellery overload. Hair voluminous and natural — curly or wavy. Attitude in posture — arms crossed or one hand raised, not passive. 1992 CALIFORNIA STREET FASHION — specific for any character: MALE: oversized sports jersey (Raiders, A's, Kings) over white tank | baggy dark jeans worn low | white Air Force 1s or Timberlands | do-rag or flat-brim snapback | gold chain or silver cross chain | bandana in back pocket FEMALE: high-waist tight jeans OR cargo pants | crop top or turtleneck | oversized flannel or bomber jacket | hoop earrings | chunky sneakers or boots | hair natural — big, voluminous Always era-appropriate. Never modern streetwear. Never post-1993 branding on clothing visible. VEHICLES — carry strong visual weight: Late 80s-early 90s American cars — Chevrolet, Buick, Crown Victoria chassis quality. Beat-up, sun-faded paint, dented chrome. Low rider with hydraulics (bounced or low-slung). SA-era sedan parked at kerb adds massive authenticity. Include a vehicle in roughly every other shot. POSE AND ENERGY: SA characters have attitude in their posture. Not stiff neutral standing. Swagger, lean, confidence. MALE SA POSE OPTIONS: standing with slight forward lean, hands loosely at sides | leaning back on car hood, one leg crossed | one hand adjusting sunglasses | walking with easy stride, chin up | sitting on car boot, arms back supporting | leaning on wall one shoulder | arm around other character casually FEMALE SA POSE OPTIONS: arms crossed, weight shifted to one hip | standing slightly behind and angled | seated on railing or ledge, looking away | hand on hip, half-turned | walking with purpose, not looking at camera SA INTERACTION ENERGY: not close intimate Hollywood-couple standing. SA characters: adjacent, aware of each other, slight distance. Male looking at female or at something off-frame. Female not fully engaging, slightly apart — but clearly together. ENVIRONMENT COMPOSITION: SA environments should feel absolutely authentic. The classic SA textures, the cracked asphalt, the low stucco buildings, the chain-link, the palm trees — these are the setting. The enhanced characters exist inside this classic SA world. Foreground: character(s) in clear foreground, well-lit by warm SA ambient Midground: SA street environment — asphalt, buildings, vehicles, fence, kerb Background: palm trees against the warm sky, low buildings, occasionally a distant tower Always include: - Palm trees (visible somewhere in frame, often backlit against warm sky) - The SA sky (amber-orange gradient, non-negotiable) - At least one classic SA environmental element (tagged wall | cracked asphalt | beat-up American car | stucco building | chain-link fence | basketball hoop | liquor store) HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: SA game camera feel — third-person over-shoulder, side-on, or low angle. Draw from: classic over-shoulder third-person | side-on medium two-shot | low angle looking up at character against sky | over-hood of parked car | from behind toward scene | sitting level when characters are seated | slightly elevated looking down at street. Lens equivalent: 28-50mm range. No extreme telephoto. Aspect ratio: 16:9 (widescreen) preferred for landscape shots, 4:3 for portrait/close. 2. CHARACTER: reference images handle base appearance. Skip: hair colour, eye colour, skin tone, face shape, body type. Reference supplies these. First name only. Lead with name. State SA-era outfit specifically — see fashion system. State attitude in body language. Include: specific accessories (chain, earring, sunglasses, bracelet, bandana) and any visible tattoos if established. Men described as muscular/strong → prefix 'muscular athletic'. 3. OUTFIT (MANDATORY): scan last 5 messages. Carry forward. SA-era specific clothing. Never modern. Fuse into character clause. 4. POSE AND STATE: SA attitude. Not stiff. Weight and lean. See pose options above. 5. ENVIRONMENT: SA location with specific classic textures. Always: palm trees + SA sky + one SA street anchor (tagged wall/cracked asphalt/SA-era car/stucco building). 6. LIGHTING: THE SA COLOUR SIGNATURE — warm amber-orange-peach sky, golden ambient on everything. State it explicitly every time. If night: warm orange streetlamp cones vs dark blue-black sky. 7. STYLE SUFFIX (append verbatim): 'GTA San Andreas aesthetic with enhanced character models — the SA modded visual style. Classic authentic San Andreas environment: original SA streets, cracked asphalt, stucco buildings, chain-link fences, palm trees, SA-style architecture rendered faithfully. Characters are semi-realistic enhanced 3D game models — smoother faces with readable expressions and better skin texture than original PS2 models, but clearly 3D rendered figures with visible polygon geometry at angular surfaces (shoulders, jaw, arms), not photorealistic. The iconic SA colour signature is mandatory: warm amber-orange-peach gradient sky, perpetual golden hour quality, everything washed in warm amber-golden ambient light, palm tree silhouettes against the warm sky, large hazy low sun disc. SA 1992 California fashion: era-specific clothing — baggy jeans, white tanks, sports jerseys, snapbacks, boots, chains. Characters attractive and stylized within SA visual language. SA-era vehicles (late 80s-early 90s American cars) present in scene. Authentic cracked asphalt, tagged stucco walls, palm-lined streets. No modern city aesthetics. No photorealism. No clean neutral sky. No modern fashion. No text, no UI, no HUD, no minimap, no watermark.' 8. NEGATIVE (append verbatim): 'Avoid: original PS2 low-poly blocky flat-textured models, modern photorealistic skin, GTA V graphics, GTA Definitive Edition look, modern AAA rendering, clean neutral blue sky, grey overcast sky, cold lighting, modern streetwear or fashion post-1993, generic city environment, concept art illustration, painterly style, anime proportions, flat vector, cel shading, modern hairstyles, studio lighting, missing palm trees, extra fingers, missing fingers, deformed hands, bad anatomy, watermark, text, UI, HUD, blurry' MULTI-CHARACTER SCENES Characters in SA two-shot: side by side or slightly offset, with distance between them — SA interaction energy, not Hollywood couple staging. Both facing same direction OR one slightly angled toward the other — not full face-to-face unless dramatic moment. Environment and sky always visible — SA world frames them. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION SA hood register or 90s California feel. Lowercase, italic. Short. What the moment means on Grove Street. ASPECT RATIO 16:9 = wide street / environment shot (default) | 4:3 = PS2 TV feel / portrait | 3:2 = horizontal street medium | 1:1 = close portrait | 2:3 = full standing figure | 9:16 = tall dramatic vertical TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(20,14,6,0.7),rgba(12,8,3,0.7));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(220,170,80,0.09);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(220,170,80,0.04);"> <img data-iig-instruction='{"style":"gta_san_andreas_enhanced","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(220,170,80,0.07);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(215,185,120,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '4:3','16:9','3:2','1:1','2:3','9:16'. The CSS aspect-ratio value matches the chosen ratio. image_size: '2K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-130 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> GTA SAN ANDREAS ENHANCED STYLE — EVERY RESPONSE One image per message at the most cinematic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE GTA San Andreas aesthetic with enhanced character models — the SA modded / fan-art look. Classic authentic SA world, iconic SA colour signature, semi-realistic 3D character models that look genuinely good inside it. NOT original PS2 low-poly blocky models. NOT photorealistic. NOT modern GTA V graphics. SA enhanced: the world exactly as remembered, characters that look like they belong. TWO LAYERS: STAYS AUTHENTIC SA: the environment (classic SA streets, stucco buildings, palm trees, cracked asphalt) | the colour signature (mandatory warm amber-orange sky) | the fashion (1992-era specific) | the SA camera angles ENHANCED: character models smoother than PS2 originals — readable faces, better proportions — but still clearly 3D game geometry with polygon angles visible at shoulders and jaw THE SA COLOUR SIGNATURE — MANDATORY EVERY IMAGE: The single most recognisable element. Non-negotiable. SKY: warm amber-orange-peach gradient always. SA perpetual golden hour. Orange/peach horizon, deeper blue or purple-orange higher up. Never neutral, never grey, never clean blue without warm horizon. SUN: low, large, hazy disc. Silhouette of palm trees against it. AMBIENT: warm amber-golden light on everything — asphalt, skin, buildings, cars. The warm SA wash. PALM TREES: deep saturated green against the warm sky. Always present in LS shots. LOCATION PALETTES: - LOS SANTOS (streets): amber-peach sky, warm grey asphalt, faded tan/cream stucco, saturated green palms - GROVE STREET: cracked asphalt, tagged concrete walls (green gang writing), low ranch houses, beat-up early-90s American cars - BEACH/BOARDWALK: pale sand, blue-green water with warm reflection, boardwalk, palm-lined - DOCK/PIER: concrete dock, flat grey-blue water reflecting warm sky, metal railings - PARKING LOT: flat grey asphalt, painted white lines, SA-era cars, open sky - NIGHT (any location): flat dark blue-black sky, warm orange streetlamp cones, liquor store neon, headlights CHARACTER VISUAL LANGUAGE: FACES: semi-realistic 3D game model — smooth enough for expression (smirk, focused look, half-smile) but polygon geometry visible at angular surfaces (jaw, cheekbone, brow). Warm SA ambient light on skin. Characters attractive within SA visual language. BODIES: more realistic proportions than original PS2. Muscular characters look muscular. Polygon angles visible at shoulders, arms, joints — still game geometry, not smooth CGI. SIGNATURE SA MALE LOOK: Muscular, white wifebeater tank | baggy low-rise grey/dark jeans | CK underwear waistband visible | studded belt | silver cross necklace + chain bracelet | black snapback worn back | narrow wrap sunglasses | stud earring | bandana in back pocket | black sneakers. This is the iconic SA fan character look. SIGNATURE SA FEMALE LOOK: Black turtleneck or crop top | oversized black bomber jacket | dark grey/black cargo pants with side pockets | chunky black combat boots or platform sneakers | voluminous natural curly/wavy hair | attitude in posture. 1992 CALIFORNIA ERA FASHION — always: Male: baggy sports jersey or tank | low-rise jeans | snapback or do-rag | chain | Jordans or Timbs Female: high-waist jeans or cargo pants | crop top or oversized jacket | hoop earrings | chunky sneakers NEVER modern streetwear. NEVER post-1993 brands visible. Era-specific always. SA ATTITUDE IN POSES: Male: slight forward lean + chin up | leaning on car hood | adjusting sunglasses | easy walking stride | arm around other character casual Female: arms crossed weight on one hip | slightly behind and angled | seated on ledge looking away | hand on hip half-turned Two-shot energy: adjacent with some distance — not Hollywood close couple. SA energy: aware of each other, slight space between. VEHICLES: late 80s-early 90s American car (SA-era sedan, Chevy/Buick chassis) parked in scene adds strong authenticity. Include in roughly half of shots. CAMERA SA game camera angles — not cinematic photo mode. Draw from: classic third-person over-shoulder | side-on medium two-shot | low angle looking up against sky | over car hood | from behind toward scene | sitting-level for seated characters. Lens feel: 28-50mm equivalent. No extreme telephoto. Vary angle every image. Subject rotation across responses. CHARACTERS First name only — names map to reference images. Skip: hair colour, eye colour, skin tone, face shape, body type. Reference supplies appearance. State SA-era outfit specifically. State SA attitude in body language. Include: specific accessories (chain, earring, sunglasses, bracelet, bandana) if established. Men described as muscular/strong → prefix 'muscular athletic'. OUTFIT: scan last 5 messages. Carry forward. SA-era specific, never modern. Fuse into character clause. INTERACTION (2+ characters): SA two-shot energy. Side-by-side or slightly offset. Some distance between. Both facing same direction or one slightly angled — not full face-to-face unless dramatic. SA world always visible around them. HOW TO BUILD THE PROMPT 1. CAMERA — SA game angle + lens feel 2. CHARACTER — name + SA outfit (specific items + accessories) + SA attitude pose 3. ENVIRONMENT — SA location with classic textures + palm trees + SA-era vehicle if applicable 4. LIGHTING — THE SA COLOUR SIGNATURE: warm amber-orange-peach sky + golden ambient on everything (state this explicitly) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate every image. Wide shot with both characters + SA sky behind | low angle looking up against palm trees + orange sky | side-on street level two-shot | over-hood of parked car | sitting on concrete ledge with water/sky behind | close face with SA warm light + palm fronds at edge of frame. STYLE SUFFIX (append verbatim): 'GTA San Andreas aesthetic with enhanced character models — the SA modded visual style. Classic authentic San Andreas environment: original SA streets, cracked asphalt, stucco buildings, chain-link fences, palm trees, SA-style architecture rendered faithfully. Characters are semi-realistic enhanced 3D game models — smoother faces with readable expressions and better skin texture than original PS2 models, but clearly 3D rendered figures with visible polygon geometry at angular surfaces (shoulders, jaw, arms), not photorealistic. The iconic SA colour signature is mandatory: warm amber-orange-peach gradient sky, perpetual golden hour quality, everything washed in warm amber-golden ambient light, palm tree silhouettes against the warm sky, large hazy low sun disc. SA 1992 California fashion: era-specific clothing — baggy jeans, white tanks, sports jerseys, snapbacks, boots, chains. Characters attractive and stylized within SA visual language. SA-era vehicles (late 80s-early 90s American cars) present in scene. Authentic cracked asphalt, tagged stucco walls, palm-lined streets. No modern city aesthetics. No photorealism. No clean neutral sky. No modern fashion. No text, no UI, no HUD, no minimap, no watermark.' NEGATIVE (append verbatim): 'Avoid: original PS2 low-poly blocky flat-textured models, modern photorealistic skin, GTA V graphics, GTA Definitive Edition look, modern AAA rendering, clean neutral blue sky, grey overcast sky, cold lighting, modern streetwear or fashion post-1993, generic city environment, concept art illustration, painterly style, anime proportions, flat vector, cel shading, modern hairstyles, studio lighting, missing palm trees, extra fingers, missing fingers, deformed hands, bad anatomy, watermark, text, UI, HUD, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION SA hood register or 90s California feel. Lowercase, italic. Short. What the moment means on Grove Street. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(20,14,6,0.7),rgba(12,8,3,0.7));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(220,170,80,0.09);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(220,170,80,0.04);"> <img data-iig-instruction='{"style":"gta_san_andreas_enhanced","prompt":"[CAMERA + CHARACTER + SA OUTFIT + SA ATTITUDE POSE + ENVIRONMENT + SA COLOUR SIGNATURE SKY. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(220,170,80,0.07);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(215,185,120,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '16:9' default | '4:3' PS2 TV feel | '3:2' | '1:1' | '2:3' | '9:16'. image_size: '2K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Enhanced GTA San Andreas style — semi-realistic character models on top of the authentic San Andreas world. THE NON-NEGOTIABLE COLOUR SIGNATURE: warm amber-orange-peach gradient sky, perpetual golden hour quality, the specific light that defines the SA aesthetic. 1992 Los Santos setting with enhanced detail: West Coast neighbourhood streets, palm trees, lowriders, chainlink fences. 90s fashion: male characters in wifebeater/snapback/cross chain, female in black bomber and cargo. Characters present at slight distance with space between them — SA two-shot energy, not Hollywood-close. Semi-realistic quality blend: enhanced characters against the SA world feeling. Avoid: cold European aesthetic, modern clean city, missing warm sky, anime, watermark, text.

Копировать [Image generation hint, STYLE: GTA San Andreas enhanced — semi-realistic characters, MANDATORY warm amber-orange-peach sky gradient (the SA signature), 90s Los Santos fashion, two-shot composition with space between characters, golden hour quality throughout]

VtMB — Bloodlines

Source Engine 2004. НОЧЬ ВСЕГДА. Лос-Анджелес в Мире Тьмы: неон мочит асфальт, трубопроводный пар, хтоническая атмосфера. Кожа вампиров: серо-зелёный подтон, тёмные провалы под глазами. Семь кланов.

Новый Видеоигры

←→

Длинный~4758 Короткий~2726 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> VAMPIRE: THE MASQUERADE — BLOODLINES VISUAL STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most dramatically charged or atmospherically intense moment. STYLE OVERVIEW An in-game screenshot from Vampire: The Masquerade – Bloodlines (Troika Games, 2004) — Source Engine rendering, early PC era quality. Los Angeles, World of Darkness. THIS IS A 2004 VIDEO GAME SCREENSHOT — not concept art, not a film still, not modern rendering. Authentic VtMB visual fidelity: medium-polygon character models, flat-ish skin shading, early Source Engine dynamic lighting, neon cutting through dark streets at night. IT IS ALWAYS NIGHT. The sun kills vampires. There is no day in this game. Every image: night. NOT modern AAA graphics. NOT photorealistic. NOT the look of any other game. VtMB has a completely specific aesthetic: gothic urban noir, Los Angeles as World of Darkness, vampires in leather and velvet on modern streets still lit by neon. WHAT MAKES IT VTMB (not generic game, not generic gothic): 1. Source Engine 2004 rendering — medium-poly character models with early normal mapping, flat specular on skin, recognisably game-quality faces. Smoother than PS2 but clearly early 2000s PC game. Faces have angular geometry at jaw, cheekbone, brow — the polygonal structure shows through. 2. Gothic urban noir — Los Angeles as World of Darkness. Modern city infrastructure (streets, shops, power lines) layered with supernatural gothic. Not fantasy. Not medieval. Modern city + undead masquerade. 3. Neon as the primary light source — always night, and neon signs (red, green, yellow, white) are the main illumination of the street. Neon casts coloured pools on wet asphalt, on faces, on walls. Without neon, the street is near-black. 4. Vampire skin — the specific VtMB pallor: slightly grey-green undertone, pale, cold, bloodless. Heavily shadowed under eyes. Cheekbones catch the only light available (neon, lamplight). Not human healthy skin. Vampires look like what they are. 5. Atmospheric fog and haze — thick low haze in streets, fog around lamp posts, mist in alleys, steam from grates. The air is always textured and visible. Los Angeles but with a supernatural miasma. 6. Clan visual identity — each vampire clan has a completely different fashion and body aesthetic (see below). The clan IS the character's visual identity. THE WORLD OF DARKNESS — LOS ANGELES LOCATIONS: SANTA MONICA (opening district): Beachside LA. Most "normal" looking of all districts but still night-only. Pacific ocean visible. Beach boardwalk with closed shops, working streetlamps, modest neon from motels and bars. Ocean breeze haze. The least oppressive district. DOWNTOWN LA: Corporate tower glass faces above, dark streets below. Mix of neon and cold corporate fluorescent from building interiors. Elevated walkways between towers. Mostly deserted streets at 2am. Industrial undercurrent — dumpsters, fire escapes, utility poles with buzzing transformers. CHINATOWN: The most visually atmospheric district. Red neon (lanterns, Chinese restaurant signs, "Chinatown" in red glow) against dark grey-blue buildings. Dragon motif decorative elements. Fog especially thick here. Warm red glow of lanterns vs cold blue-grey buildings. Red is the dominant accent colour. HOLLYWOOD: Entertainment district decayed. The Glam music scene: Hot Topic aesthetic mixed with genuine 1980s metal club. The Toreador and their social games here. Hotel Hallowbrook hulking. Sequin and velvet mixed with decay. Yellow and white neon from club signs. ASYLUM / CLUB INTERIORS: The most extreme lighting. UV/blacklight purple making white clothing glow. Deep magenta and purple ambient. Fog machines. Silhouetted figures. The Elysium — neutral vampire territory. Coloured overhead gels (purple, blue, red). This is the maximum saturation space in the game. SEWERS / NOSFERATU TERRITORY: Damp. Dark. Industrial. Dripping concrete, rusted pipes, green-grey. Emergency lighting only — cold functional fluorescent, often flickering. The ugliest space in the game. Steam from pipes. Standing water reflecting ceiling lights. COLOUR SYSTEM — WORLD OF DARKNESS PALETTE: BASE: dark urban night — near-black streets, dark blue-black sky, dark grey buildings. Everything underlit. The world defaults to dark. LIGHT SOURCES AND THEIR COLOUR MEANING: - RED NEON: danger, Chinatown, blood, vampire power, Sabbat - GREEN NEON: toxicity, unease, sleazy commerce, something wrong in the shadows - YELLOW / WARM WHITE NEON: entertainment, human commerce still running, slightly safer - COLD BLUE-WHITE: corporate, police, clinical, the world outside the masquerade - DEEP PURPLE / UV: Elysium, clubs, Toreador and Ventrue glamour, supernatural spaces - FLICKERING FLUORESCENT: sewers, abandoned spaces, Nosferatu territory, broken city infrastructure - BLOOD RED (non-neon): fresh blood, diablerie, vampire instinct breaking through WET SURFACES: crucial. Neon reflects in wet asphalt as distorted colour pools. Puddles duplicate neon signs. Wet pavement under neon = signature VtMB image. VAMPIRE SKIN — ALWAYS: The specific VtMB pallor is non-negotiable for vampire characters. NOT human healthy skin. - Grey-green undertone — bloodless, cold, slightly corpse-adjacent - Deep shadow pools under eyes — the darkness under vampire eyes is heavy, painted-on quality in Source engine - Cheekbones and nose bridge catch available neon light — hollowed face structure emphasised by angular 3D geometry - Heavy eye makeup common (dark liner, eyeshadow) — especially Toreador, Malkavian, Nosferatu-adjacent clans - Fangs: when present — visible at slight part of lips, not cartoonishly exaggerated CLAN VISUAL IDENTITIES: BRUJAH (rebel warriors): Punk-adjacent street. Leather jacket (black, worn, patches), combat boots, dark jeans, muscle shirts, chains. Aggressive posture. Biker or activist energy. The "action hero" vampire. Moves like a fighter. TOREADOR (artists, socialites): Elegant but with edge. Tailored but dark. Black silk, velvet, fitted jackets, artful scarves. Aesthetics above function. Beautiful but cold. Glamour as armour. Moves with deliberate grace. VENTRUE (corporate rulers): Power suits — dark charcoal, grey, navy. Expensive but cold. Understated authority. Cufflinks, silk ties. The vampire who owns the building you're standing in. Controlled, minimal gesture. MALKAVIAN (mad seers): Deliberately wrong fashion. Layers that don't match. Too many textures. Victorian element mixed with street element. Something about the outfit that feels assembled without coherent logic — but always somehow stylish. Unnerving. Eyes that see something you can't. NOSFERATU (hideous, information brokers): Grotesque physical form — impossible to hide in public. Sewers only. Deformed features, bulging eyes, mottled skin. Worn functional clothing — survival, not fashion. But deeply intelligent eyes in a monstrous face. GANGREL (animalistic nomads): Feral. Traveller. Worn practical gear — leather, canvas, boots with mileage. Animal motif details (claws visible under skin in some forms, fur-lined). The outside vampire. Rough hands. TREMERE (blood mages, scholars): Conservative with occult edge. Formal in dark colours — deep red, black, dark green. Occult symbols might appear. More book than street. Calculating expression. The vampire who's running an experiment on you. LASOMBRA / SABBAT: Dark formal with maximum menace. Black on black. Military or priestly elements. Capes or long coats. Aggressive formal structure. Shadow seems to cling to them differently than to other vampires. FASHION SYSTEM — VTMB SPECIFIC: Every character wears something that communicates their nature. Fashion in the World of Darkness is identity and power statement. Scan last 5 messages for current clothing. Never generic. Specific fabric, cut, condition. Fuse into character clause — one detailed clothing description, never "dark clothes". ATMOSPHERE — ALWAYS PRESENT: Fog at street level catching neon colour | steam from grates cutting through cold air | low haze in alleys making lamp posts glow with visible corona | wet surface reflections | the specific static and buzz of urban infrastructure running at night with no people LIGHTING SYSTEM: STREET NIGHT (base state): Near-black ambient, dominated by neon sources competing from signage. Multiple colour temperatures simultaneously. Wet asphalt multiplies each source. Character face split by competing neon colours from different directions. INTERIOR — CLUB / ELYSIUM: Purple/UV ambient, fog machine layers, coloured gel overheads, silhouettes of other patrons, sound implied by frozen chaos of club bodies around. INTERIOR — ABANDONED / SEWER: Single emergency source (flickering or constant cold fluorescent) creating harsh overhead downlight. Deep shadows everywhere. Steam. Dripping. INTERIOR — PRIVATE SPACE (haven, office): Single warm practical lamp | candles in older vampire havens | cold monitor light | one window with exterior neon coming through. Personal and closed. HOW LIGHT FALLS ON VAMPIRE FACES: Neon from below or side: catches cheekbones, nose, jaw. Eye sockets and under-chin in shadow. The vampire face is designed to be lit by neon from below — it creates the correct unsettling quality. Describe the colour split: 'left side red neon from sign above, right side falling into grey-blue ambient shadow, pale skin catching both sources in the specific Source engine flat-specular way'. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: VtMB game camera — over-shoulder third person, interior medium shot, close portrait, street-level wide. Draw from: over-shoulder walking shot on night street | interior medium at conversational distance | close face portrait with neon colour cast | looking up at character from ground level | through doorway into interior | reflected in wet asphalt or dark window glass | wide establishing of night street with tiny figure. Lens equivalent: 28-85mm range. No extreme telephoto — VtMB is an intimate-scale game. DoF: minimal in streets (everything foggy-sharp), slight blur on background in interiors. 2. CHARACTER: reference images handle base appearance. Skip: hair colour, eye colour, skin tone, face shape. Reference supplies these. BUT for vampire characters — ALWAYS state vampire pallor override: 'pale grey-green undertone vampire skin, deep shadow pools under eyes'. This is non-negotiable — vampires do not have human healthy skin colour. First name only. Lead with name. Include: clan identity (see clan system) + one specific physical vampire tell (hollow cheekbones catching neon | barely visible fang at lip corner | unnaturally still quality | eyes that reflect light slightly wrong). Include distinguishing marks: tattoos (Gothic or occult motif), scars, piercings. 3. OUTFIT (MANDATORY): clan-appropriate VtMB fashion, specific and detailed. See clan system. Never generic. Fuse into character clause after name. 4. POSE AND STATE: VtMB characters hold themselves with supernatural quality. Vampires: unnaturally still when at rest | movement too smooth when in motion | wrong quality to casual poses. Describe through body weight and intent: 'standing at the edge of the streetlamp cone, completely motionless, hands loose at sides, watching the street with no attempt to appear casual about it'. Hands: in coat pockets | loose at sides | gripping something (weapon, phone, glass) | one hand on wall or surface | arms crossed with precision. 5. ENVIRONMENT: VtMB Los Angeles location — always night, always atmospheric. Foreground / midground / background sentence. Mandatory: neon source (colour, what sign or object) + atmospheric element (fog / steam / wet reflection / haze) + one environmental anchor (neon sign | abandoned shop | bus stop | fire escape | utility poles | club entrance with bouncer | parked car from the era). Text on neon signs should be either fictional or generic (bar sign, motel, shop name) — not real brands. 6. LIGHTING: dominant neon colour(s) + how they fall on character + atmospheric scatter (fog catching the colour) + secondary source if any. ALWAYS describe the wet asphalt reflection of the neon if outdoors. ALWAYS describe the colour split on the character's face from competing neon directions. 7. TECHNICAL RENDER: Source Engine 2004 quality — state 1-2 artifacts: Close face → early normal mapping on skin, flat specular highlight, polygonal jawline/cheekbone geometry visible, eye texture flat but expressive Street wide → fog rendering (flat fog plane vs volumetric), neon bloom on Source engine default, limited shadow detail, early LOD on background buildings 8. STYLE SUFFIX (append verbatim): 'In-game screenshot from Vampire The Masquerade Bloodlines by Troika Games, Source Engine 2004, early PC era rendering quality. THIS IS A 2004 VIDEO GAME SCREENSHOT — not modern AAA graphics, not concept art, not a painting. Source Engine medium-poly character models with early normal mapping, flat specular on skin, polygonal facial geometry visible at angular surfaces — clearly a 2004 game engine. IT IS ALWAYS NIGHT — the game has no daytime. Gothic urban noir World of Darkness: Los Angeles at permanent 2am, modern city infrastructure layered with supernatural presence. Neon signs (red, green, yellow, white) are the primary light source — cutting through near-black streets, reflecting in wet asphalt as distorted colour pools. Atmospheric fog and haze throughout — thick ground fog, lamp corona, steam from grates, visible air. Vampire skin: characteristic grey-green pallor, bloodless and cold, deep shadow pools under eyes, cheekbones and nose catching neon light, polygonal geometry emphasising hollow face structure. Clan-specific fashion: each vampire dressed to communicate their nature and power — leather for Brujah, elegance for Toreador, corporate for Ventrue, wrong-layered for Malkavian. Character appearance from reference images — do not alter facial structure. No text, no UI, no HUD, no watermark.' 9. NEGATIVE (append verbatim): 'Avoid: modern photorealistic skin, smooth high-poly faces, healthy human skin colour, warm flattering sunlight, daytime, blue sky, clean bright city, modern AAA rendering, GTA V graphics, concept art illustration, painterly style, anime proportions, happy expressions, cheerful atmosphere, cel shading, cartoon, film photography look, pristine clothing, extra fingers, missing fingers, deformed hands, bad anatomy, watermark, text, UI, HUD, blurry' MULTI-CHARACTER SCENES Each character: NAME + [clan identity if established] + [vampire pallor description] + [outfit specific to clan] + [pose with supernatural quality]. Vampires in the same space: there is always a power dynamic. One is dominant, one is accommodating or watchful. Rarely equals. Positioning: specific distance that communicates the relationship — 'standing two paces apart, neither willing to be first to step closer' | 'one seated, one standing over' | 'both against different walls watching each other'. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION World of Darkness register — dry, knowing, slightly theatrical. Lowercase, italic. A clan phrase, a Masquerade observation, the cost of being what they are. Not what is shown — what the vampire is thinking. ASPECT RATIO 16:9 = street scene / environmental (default) | 4:3 = portrait / authentic PC screen ratio | 1:1 = face close-up | 2:3 = full figure | 9:16 = alley vertical / nightclub column | 3:2 = interior medium TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(8,5,12,0.75),rgba(4,3,8,0.75));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(160,80,180,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.7),inset 0 1px 0 rgba(160,80,180,0.04);"> <img data-iig-instruction='{"style":"vtmb_source_engine","prompt":"[FULL PROMPT: SECTIONS 1-9 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(160,80,180,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(190,160,210,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '4:3','16:9','3:2','1:1','2:3','9:16'. The CSS aspect-ratio value matches the chosen ratio. image_size: '2K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-130 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> VAMPIRE: THE MASQUERADE — BLOODLINES VISUAL STYLE — EVERY RESPONSE One image per message at the most dramatically charged or atmospherically intense moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE In-game screenshot from Vampire: The Masquerade – Bloodlines (Troika Games, 2004) — Source Engine, early PC era rendering. Los Angeles, World of Darkness. THIS IS A 2004 VIDEO GAME SCREENSHOT. IT IS ALWAYS NIGHT. Every image: night. The sun kills vampires. NOT modern AAA. NOT concept art. NOT a painting. VtMB authentic: gothic urban noir, Source Engine medium-poly character models, neon cutting through permanent 2am darkness. WHAT MAKES IT VTMB: 1. Source Engine 2004 — medium-poly faces, early normal mapping, flat specular on skin, polygonal geometry at jaw and cheekbones. Clearly 2004 game engine quality. 2. Gothic urban noir — Los Angeles as World of Darkness. Modern city + undead masquerade. Neon and concrete and vampires. 3. Neon as primary light — always night, neon signs (red/green/yellow/white) are the main illumination. Neon reflects in wet asphalt as distorted colour pools. 4. Vampire skin — mandatory grey-green pallor, bloodless cold, deep shadow pools under eyes, cheekbones catching neon. NOT human healthy skin. Ever. 5. Atmospheric fog and haze — thick ground fog, steam from grates, lamp corona, visible air. Always. 6. Clan visual identity — each clan has specific fashion that IS their power statement. LA DISTRICT LIGHTING PALETTES: - SANTA MONICA: beachside, modest neon, ocean haze, slightly less oppressive - DOWNTOWN: corporate cold blue-white above, near-black streets below, neon punctuation - CHINATOWN: red neon dominant (lanterns, signs), thick fog, warm red vs cold blue-grey - HOLLYWOOD: yellow/white entertainment neon, decay beneath glamour, Hotel Hallowbrook - CLUB / ASYLUM INTERIOR: deep purple UV, blacklight, fog machine, coloured gels (purple/blue/red), maximum saturation - SEWERS: cold flickering fluorescent, steam, damp dark, dripping — Nosferatu territory NEON COLOUR MEANING: Red → danger, blood, Chinatown, Sabbat Green → toxicity, unease, sleazy commerce, something wrong Yellow/warm white → entertainment, human activity, slightly safer Cold blue-white → corporate, police, outside the masquerade Deep purple/UV → Elysium, clubs, glamour magic, supernatural spaces VAMPIRE SKIN — NON-NEGOTIABLE: Always state for vampire characters: 'pale grey-green undertone vampire skin, deep shadow pools under eyes'. Cold, bloodless, grey-green pallor. Cheekbones and nose catching neon. Angular Source Engine geometry emphasising hollow face structure. Heavy eye shadow common. Fangs barely visible at lip corner when mouth slightly open. This is what vampires look like in VtMB. CLAN IDENTITIES — fashion IS power: BRUJAH: leather jacket (worn, black), combat boots, dark jeans or cargo, muscle shirt, chains. Punk street fighter energy. TOREADOR: tailored black or deep colour, velvet or silk, elegant cut, artful drape. Cold beauty as armour. VENTRUE: dark power suit, charcoal/grey/navy, expensive and understated. Corporate authority. MALKAVIAN: wrong-layered — mismatched textures, Victorian + street, something assembled without coherent logic. Unnerving but somehow stylish. NOSFERATU: grotesque deformed form, worn functional clothing, survival not fashion. Sewers only. GANGREL: feral, worn leather and canvas, traveller gear, animal-motif details. Rough and outside. TREMERE: conservative dark formal (deep red/black/dark green), occult edge, scholarly menace. CAMERA VtMB intimate scale — over-shoulder third person, interior medium, close portrait, street-level wide. Draw from: over-shoulder night street | interior medium at conversational distance | close face with neon colour cast | looking up at character from below | through doorway | reflected in wet asphalt or dark window | wide night street with tiny figure. Lens equivalent: 28-85mm. No extreme telephoto. DoF: minimal outdoors (foggy-sharp), slight background blur in interiors. Aspect: 16:9 default | 4:3 for authentic PC feel | 1:1 for face close-up. CHARACTERS First name only — names map to reference images. Skip: eye colour, face shape, body type. Reference supplies appearance. FOR VAMPIRE CHARACTERS — ALWAYS add: 'pale grey-green undertone vampire skin, deep shadow pools under eyes'. Override any healthy human skin. Include: clan identity + one vampire physical tell (hollow cheekbones catching neon | barely visible fang | unnaturally still quality | eyes reflecting light slightly wrong). Include: distinguishing marks (Gothic/occult tattoos, scars, piercings). OUTFIT: scan last 5 messages. Carry forward. Clan-appropriate VtMB fashion — specific fabric, cut, condition. Never generic. Fuse into character clause. POSE — VAMPIRE QUALITY: unnaturally still at rest | movement too smooth when in motion | wrong quality to casual poses. 'Standing at edge of the lamplight cone, completely motionless, watching the street with no attempt to appear casual about it.' Hands: in coat | loose at sides | gripping something | one hand on wall | arms crossed with precision. INTERACTION (2+ vampires): always a power dynamic. Position communicates it: 'two paces apart, neither willing to step closer first' | 'one seated, one standing over' | 'both against different walls watching each other'. Rarely equals. HOW TO BUILD THE PROMPT 1. CAMERA — VtMB game angle + lens feel 2. CHARACTER — name + 'pale grey-green vampire skin, deep shadow pools under eyes' + clan outfit (specific) + vampire pose quality + expression 3. ENVIRONMENT — LA district (always night) + neon source (colour + what object) + fog/steam/haze + one location anchor 4. LIGHTING — dominant neon colour + how it falls on face + wet asphalt reflection + competing secondary colour if any 5. TECHNICAL — 1-2 Source Engine artifacts: flat specular on skin / polygonal face geometry / neon bloom / fog plane rendering Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Every image different. Rotate away from over-shoulder default. Close face — neon from below on pale vampire cheekbones | wide night street with lone figure and red neon sign | club interior: figure silhouetted against purple UV haze | Chinatown fog with red lantern glow | over-shoulder on wet asphalt reflecting neon | looking up at figure from ground level under lamp post. STYLE SUFFIX (append verbatim): 'In-game screenshot from Vampire The Masquerade Bloodlines by Troika Games, Source Engine 2004, early PC era rendering quality. THIS IS A 2004 VIDEO GAME SCREENSHOT — not modern AAA graphics, not concept art, not a painting. Source Engine medium-poly character models with early normal mapping, flat specular on skin, polygonal facial geometry visible at angular surfaces — clearly a 2004 game engine. IT IS ALWAYS NIGHT — the game has no daytime. Gothic urban noir World of Darkness: Los Angeles at permanent 2am, modern city infrastructure layered with supernatural presence. Neon signs (red, green, yellow, white) are the primary light source — cutting through near-black streets, reflecting in wet asphalt as distorted colour pools. Atmospheric fog and haze throughout — thick ground fog, lamp corona, steam from grates, visible air. Vampire skin: characteristic grey-green pallor, bloodless and cold, deep shadow pools under eyes, cheekbones and nose catching neon light, polygonal geometry emphasising hollow face structure. Clan-specific fashion: each vampire dressed to communicate their nature and power — leather for Brujah, elegance for Toreador, corporate for Ventrue, wrong-layered for Malkavian. Character appearance from reference images — do not alter facial structure. No text, no UI, no HUD, no watermark.' NEGATIVE (append verbatim): 'Avoid: modern photorealistic skin, smooth high-poly faces, healthy human skin colour, warm flattering sunlight, daytime, blue sky, clean bright city, modern AAA rendering, concept art illustration, painterly style, anime proportions, happy cheerful atmosphere, cel shading, cartoon, film photography look, pristine clean environments, extra fingers, missing fingers, deformed hands, bad anatomy, watermark, text, UI, HUD, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION World of Darkness register — dry, knowing, slightly theatrical. Lowercase, italic. What the vampire is thinking, not what is shown. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(8,5,12,0.75),rgba(4,3,8,0.75));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(160,80,180,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.7),inset 0 1px 0 rgba(160,80,180,0.04);"> <img data-iig-instruction='{"style":"vtmb_source_engine","prompt":"[CAMERA + CHARACTER + VAMPIRE SKIN + CLAN OUTFIT + POSE QUALITY + ENVIRONMENT + NEON LIGHTING + WET REFLECTION + RENDER ARTIFACTS. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(160,80,180,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(190,160,210,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '16:9' default | '4:3' authentic PC | '1:1' | '2:3' | '9:16' | '3:2'. image_size: '2K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Screenshot from Vampire: The Masquerade — Bloodlines running on Source Engine (2004). IT IS ALWAYS NIGHT. World of Darkness Los Angeles: Santa Monica Beach, Hollywood Boulevard, Chinatown, downtown LA — all at night. Neon signs reflecting in rain-wet asphalt. Steam from underground pipes. Chthonic gothic atmosphere. Vampire skin mandatory: pale grey-green undertone, deep dark shadow pools under eyes, slightly unnatural pallor. Source Engine 2004 aesthetic: low-to-mid polygon models, baked lighting, characteristic early 2000s game quality. Neon as primary light source — red signs, blue fluorescents, green exit signs. Avoid: daytime scenes, sunlight, anime, watermark, text, visible HUD elements.

Копировать [Image generation hint, STYLE: Vampire the Masquerade Bloodlines Source Engine 2004 — always night, World of Darkness LA, neon-wet asphalt, vampire pale grey-green skin with deep eye shadows, steam pipes, gothic atmosphere, 2004 game quality]

League of Legends — Splash Art

Сплэш-арт LoL — без фракционного лора. Ключевое: EDGE CLARITY BOOST — лёгкое усиление резкости контуров. Читаемый средний план, живописный фон, вес у магии. Полу-реализм, сложная экспрессия.

Новый Видеоигры

←→

Длинный~3531 Короткий~2261 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> LEAGUE OF LEGENDS RIOT GAMES SPLASH ART — VISUAL ARTIFACT EVERY RESPONSE (V2 — PURE VISUAL RENDERING) Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most dramatically or emotionally charged moment. STYLE OVERVIEW Premium semi-realistic fantasy champion portrait in the house style of Riot Games League of Legends — the loading screen and champion select splash art format. NOT mobile MOBA Chinese art. NOT anime. NOT photorealistic. NOT painterly impressionism. This is Riot's specific house style: semi-realistic digital concept art with crisp edge clarity, convincing material rendering, narrative world-building backgrounds, and champion-centric composition. THE SINGLE MOST IMPORTANT VISUAL CHARACTERISTIC: EDGE CLARITY BOOST — LoL splash art has a subtle but consistent clarity/unsharp mask enhancement applied across the entire image. Armour edges, fabric contours, face planes, and environmental shapes are all slightly sharper and crisper than raw digital painting. This is not photorealistic sharpness — it is a clarity boost that gives the art a punchy, defined quality where every edge catches light cleanly and every material boundary reads with precision. WHAT MAKES IT LEAGUE OF LEGENDS RIOT SPLASH ART: 1. EDGE CLARITY + CRISP RENDERING: the defining technical characteristic. Subtle sharpening across the whole image — armour plates have crisp clean edges, face planes are defined and structured, environmental details read clearly even in midground. Not photorealistic, not soft airbrush — specifically that clarified punchy digital painting quality. 2. NARRATIVE WORLD-BUILDING BACKGROUNDS: backgrounds are specific places. The character exists somewhere doing something for a reason. Unlike mobile MOBA where backgrounds are aggressive bokeh blur, LoL backgrounds have readable content — specific architecture, environmental storytelling, atmospheric but still LEGIBLE. You can tell where the character is standing and why. 3. SEMI-REALISTIC CHAMPION RENDERING: between anime and photography. Faces have character, subtlety, history. Skin has natural variation — not airbrushed smooth, not photographic pores. Complex expressions: a character can look fierce AND tired AND determined simultaneously. 4. MATERIAL SPECIFICITY — EVERY SURFACE DISTINCT: Metal: scratched iron vs polished gold vs ancient bronze — each reflects light differently Fabric: leather, silk, rough wool, cotton, homespun — visibly different in drape and weave Magical materials: runic stone, enchanted cloth, spirit-energy constructs — clearly supernatural Organic: bone, fur, scales, living wood — texture specific and believable Every material has HISTORY: worn, battle-scratched, enchanted, freshly forged — state which. 5. THREE-PLANE DEPTH WITH READABLE MIDGROUND (key difference from mobile MOBA): FOREGROUND: champion at maximum sharpness with full clarity enhancement — all material detail MIDGROUND: environment 2-8m behind — still has READABLE CONTENT. Specific architectural forms, secondary figures, environmental props. Softened by atmospheric perspective but NOT bokeh-blurred. You can still identify what is there. BACKGROUND: distance — painterly, atmospheric, increasing brushwork with distance. Still has subject matter, not empty colour wash. 6. PAINTERLY BACKGROUND QUALITY: visible brush direction increases with distance from champion. Foreground is polished and sharp; background transitions through softness into deliberate painterly looseness. Brush strokes become visible at distance. 7. MAGICAL EFFECTS WITH PHYSICAL WEIGHT: supernatural effects have texture, form, mass. Not generic glow — each character's magic has specific physical properties (heavy chains, sharp geometric light, fluid liquid-fire, dense void energy). COLOUR IDENTITY — DESCRIBE IN THEMATIC TERMS: Do not use faction names. Describe the palette by its emotional and visual character: WARM HEROIC: gold, white, cool silver, clean blue-grey — noble and martial DARK AGGRESSIVE: deep crimson-red, iron grey, black, blood amber — conquest and dominance NATURE MYSTIC: teal-blue, soft white, jade green, warm spirit gold — serenity and power COLD PRIMAL: ice blue, steel grey, frost white, deep blue-purple — ancient and elemental WARM INDUSTRIAL: warm brass, copper-gold, steam white, invention blue — ingenuity GRIM CHEMICAL: acid green, rust brown, corroded orange, toxic yellow — survival COLD SUPERNATURAL: cold teal-green, black, ghost pale, mist white — undead, sorrow ALIEN VOID: deep purple-black, corruption traces, empty dark — horror and alien MARITIME: storm grey-blue, ocean green, ship wood brown, storm amber — sea and danger DESERT ANCIENT: warm gold, sandstone, ancient blue, sun amber — epic and ancient State the palette identity in section 1. The palette immediately communicates the character's world without naming it. THREE-PLANE DEPTH (full specification): FOREGROUND PLANE (maximum detail + edge clarity boost): Champion at full sharpness. Weapon with material-accurate surface rendering. Close environmental element. Every material visually distinct. Edge clarity enhancement across the whole plane. MIDGROUND PLANE (atmospheric perspective — soft but READABLE): 2-8 metres behind champion. Specific content: what kind of architecture, what secondary figures, what environmental props. Softened by atmospheric depth but still identifiable. Name 2-3 specific readable elements. NOT bokeh blur. BACKGROUND PLANE (painterly atmospheric): Distance: skyline, far terrain, horizon. Increasingly painterly with distance. Atmospheric haze and faction-coloured sky. Still has subject matter — not empty ambient colour. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. PALETTE IDENTITY + CHAMPION ROLE: which colour identity (warm heroic / dark aggressive / nature mystic / cold primal / etc.) + what the champion is (warrior, mage, assassin, support, tank) — determines entire image atmosphere and lighting. 2. CAMERA: champion slightly left or right of absolute centre. Low angle (classic heroic), eye-level, or specific dynamic angle for personality. 16:9 loading screen format. 3. CHARACTER: reference images handle base appearance. Skip: hair colour, eye colour, skin tone, face shape, body type. First name only. Lead with name. Include: weapon description (specific material quality + magical nature) + distinguishing marks (scars, tattoos with location). State role in their world if established. 4. COSTUME (essential): scan last 5 messages. Carry forward with thematic aesthetic enhancement. Multiple specific named layers + material quality (scratched iron / polished gold / runed cloth / weathered leather) + design motifs appropriate to the character's world. State condition and history: worn from battle | newly forged and perfect | ancient and weathered. 5. POSE AND EXPRESSION: personality-specific, not generic. HEROIC: weapon raised, standing against the scene, about to act MENACING: advancing toward viewer, weight forward, viewer is the opponent CONFIDENT CASUAL: weapon down but present, looking off-frame, knows they win DRAMATIC MID-ACTION: body carrying the specific story moment Expression: complex and specific — 'fierce but tired' | 'cold precision' | 'warm immovable' | 'chaotic delight' | 'ancient grief' | 'calculating calm' 6. MAGICAL EFFECT: physical quality (heavy/light/sharp/fluid/dense) + specific magical type + location in composition. State what the magic looks like physically — not just 'glowing'. 7. FOREGROUND: what is in the near-foreground plane adding depth (fallen object, environmental prop, architectural element, close ability detail). 8. MIDGROUND: specific readable content — at least 2-3 named architectural or narrative details softened by atmospheric perspective. Still identifiable. Tells the story of the location. 9. BACKGROUND: the world at distance. Sky quality and atmospheric character. Painterly looseness at distance. What is out there — panorama, horizon, atmosphere. 10. LIGHTING: colour temperature matching the palette identity + key light direction + how it falls on the champion + any magical light contribution. 11. STYLE SUFFIX (append verbatim): 'Champion splash art in the visual style of League of Legends by Riot Games — loading screen and champion select portrait format. Riot Games house style: semi-realistic digital concept art with crisp edge clarity enhancement — armour edges, fabric contours, face planes, and environmental shapes sharper and more defined than raw digital painting, with a subtle clarity and unsharp mask quality applied throughout the image. Convincing material rendering: metal, leather, cloth, and magical effects each visually distinct with physical weight and surface specificity — scratched iron reads differently from polished gold from runed cloth from spirit energy. Three-plane depth: foreground champion razor-sharp with full clarity detail and material precision → midground environment with specific architectural and narrative content, softened by atmospheric perspective but still readable and identifiable → background world at painterly distance with increasing brushwork looseness and atmospheric depth. Champion fills and dominates the frame. Magical effects have physical weight and texture — specific to the character, not generic glow. Face rendering: semi-realistic, more characterful than mobile game art, subtle natural skin texture, complex expression carrying multiple emotional registers simultaneously. Colour palette driven by character world context — warm heroic golds, cold imperial blues, nature greens, corrupted teals, void purples — the palette communicates the world before the details do. Background tells the story of where the character is. Visible painterly brush quality in background and atmosphere — brush strokes become visible with distance. No text, no UI, no health bars, no watermark.' 12. NEGATIVE (append verbatim): 'Avoid: mobile MOBA airbrushed style, aggressive background bokeh blur, photorealistic photography, 3D CGI render, anime cel-shading, soft airbrushed skin, missing edge clarity and sharpness, missing background narrative content, neutral passive poses, generic magical glow effects without physical weight, overly smooth skin, plain or content-free backgrounds, extra fingers, missing fingers, deformed hands, bad anatomy, watermark, text, UI elements, blurry foreground champion' MULTI-CHARACTER SCENES Primary champion: foreground plane at maximum detail. Secondary character: midground plane, slightly softened — ally reacting to champion's power, or enemy being dominated. Never competing for primary's focus. Enemy: below, falling back, dominated — the champion owns this frame. Ally: beside or slightly behind, sharing purpose, readable as unit. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Character line — champion quote, battle cry, moment of introspection. Lowercase, italic. Short. ASPECT RATIO 16:9 = standard loading screen (default) | 4:5 = champion select portrait | 1:1 = social square | 3:2 = wide promotional | 9:16 = mobile portrait TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(6,8,16,0.72),rgba(4,5,12,0.72));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(180,150,80,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(180,150,80,0.04);"> <img data-iig-instruction='{"style":"lol_riot_splash_art","prompt":"[FULL PROMPT: SECTIONS 1-12 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(180,150,80,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,180,130,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','3:2','4:5','9:16','16:9'. The CSS aspect-ratio value matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-150 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> LEAGUE OF LEGENDS RIOT SPLASH ART — EVERY RESPONSE (V2 — VISUAL RENDERING FOCUSED) One image per message at the most dramatically or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Champion splash art in the visual style of League of Legends by Riot Games — loading screen and champion select portrait format. NOT mobile MOBA Chinese art. NOT anime. NOT photorealistic. Riot's specific house style: semi-realistic digital concept art with crisp edge clarity, convincing material rendering, narrative world-building backgrounds. THE DEFINING VISUAL CHARACTERISTIC: EDGE CLARITY BOOST — LoL splash art has a subtle but consistent clarity/unsharp mask enhancement throughout. Armour edges, fabric contours, face planes, and environmental shapes are all slightly sharper and crisper than raw digital painting. Not photorealistic — specifically that clarified punchy digital painting quality where every edge catches light cleanly. WHAT MAKES IT RIOT LOL SPLASH ART: 1. Edge clarity boost: unsharp mask quality throughout — armour edges crisp, face planes defined, midground still readable 2. Narrative backgrounds: specific places with readable architectural content — NOT bokeh blur 3. Semi-realistic faces: characterful, natural texture, complex multi-register expression 4. Material quality: metal/leather/cloth/magic each completely distinct, every surface has history 5. Three-plane depth: champion (sharp + clarity) → midground (soft but READABLE) → background (painterly) 6. Magic has physical weight: texture, form, mass — not generic glow 7. Painterly backgrounds: brush direction visible at distance, looseness increases away from champion COLOUR IDENTITY — PALETTE WITHOUT FACTION NAMES: WARM HEROIC: gold, white, cool silver — noble and martial DARK AGGRESSIVE: crimson-red, iron grey, black — conquest and dominance NATURE MYSTIC: teal-blue, jade green, spirit gold — serenity and power COLD PRIMAL: ice blue, steel, frost white — ancient and elemental WARM INDUSTRIAL: brass, copper-gold, steam — ingenuity GRIM CHEMICAL: acid green, rust, corroded orange — survival COLD SUPERNATURAL: cold teal-green, ghost pale, mist — undead and sorrow ALIEN VOID: purple-black, corruption, empty dark — horror MARITIME: storm grey-blue, ocean green, amber — sea and danger DESERT ANCIENT: warm gold, sandstone, sun amber — epic THREE PLANES — ALL THREE MUST BE DESCRIBED: FOREGROUND: champion + weapon + close element (razor sharp + clarity boost) MIDGROUND: specific readable content — architecture, figures, props — soft but IDENTIFIABLE (name 2-3 elements) BACKGROUND: world at painterly distance — atmospheric, increasing brushwork, sky quality CHAMPION POSES: HEROIC: weapon raised, standing against the scene MENACING: advancing toward viewer, weight forward CONFIDENT CASUAL: weapon down, looking off-frame DRAMATIC MID-ACTION: body carrying the story moment EXPRESSION: complex and specific — 'fierce but tired' | 'cold precision' | 'warm immovable' | 'ancient grief' MAGICAL EFFECTS: State physical quality (heavy/sharp/fluid) + specific type + location. LoL magic has weight — describe that weight. CAMERA 16:9 native. Champion slightly off-centre. Low angle or eye-level. Strong depth foreground to background. CHARACTERS First name only. Skip: hair, eyes, skin, face shape. Reference handles appearance. Include: weapon (material quality + magical nature) + distinguishing marks. COSTUME: scan last 5 messages. Carry forward. Named layers + material quality + condition history. EXPRESSION: complex and character-specific. HOW TO BUILD THE PROMPT 1. PALETTE IDENTITY + ROLE — determines atmosphere 2. CHARACTER — name + weapon + costume (layers, materials, condition) + pose + expression 3. MAGICAL EFFECT — physical quality + specific type + composition location 4. FOREGROUND — depth-adding element 5. MIDGROUND — 2-3 readable named details softened by atmospheric perspective 6. BACKGROUND — world at painterly distance + sky quality 7. LIGHTING — palette temperature + key direction + magic contribution Total prompt: 80-150 words + style suffix. FRAMING VARIETY (mandatory): Every image different. Low angle against sky | eye-level with architectural midground | looking up from enemy perspective | wide stance mid-location | champion reflected in surface | dramatic mid-ability cast. STYLE SUFFIX (append verbatim): 'Champion splash art in the visual style of League of Legends by Riot Games — loading screen and champion select portrait format. Riot Games house style: semi-realistic digital concept art with crisp edge clarity enhancement — armour edges, fabric contours, face planes, and environmental shapes sharper and more defined than raw digital painting, with a subtle clarity and unsharp mask quality applied throughout the image. Convincing material rendering: metal, leather, cloth, and magical effects each visually distinct with physical weight and surface specificity — scratched iron reads differently from polished gold from runed cloth from spirit energy. Three-plane depth: foreground champion razor-sharp with full clarity detail and material precision → midground environment with specific architectural and narrative content, softened by atmospheric perspective but still readable and identifiable → background world at painterly distance with increasing brushwork looseness and atmospheric depth. Champion fills and dominates the frame. Magical effects have physical weight and texture — specific to the character, not generic glow. Face rendering: semi-realistic, more characterful than mobile game art, subtle natural skin texture, complex expression carrying multiple emotional registers simultaneously. Colour palette driven by character world context — warm heroic golds, cold imperial blues, nature greens, corrupted teals, void purples — the palette communicates the world before the details do. Background tells the story of where the character is. Visible painterly brush quality in background and atmosphere — brush strokes become visible with distance. No text, no UI, no health bars, no watermark.' NEGATIVE (append verbatim): 'Avoid: mobile MOBA airbrushed style, aggressive background bokeh blur, photorealistic photography, 3D CGI render, anime cel-shading, soft airbrushed skin, missing edge clarity and sharpness, missing background narrative content, neutral passive poses, generic magical glow effects without physical weight, overly smooth skin, plain or content-free backgrounds, extra fingers, missing fingers, deformed hands, bad anatomy, watermark, text, UI elements, blurry foreground champion' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Character line — evocative, short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(6,8,16,0.72),rgba(4,5,12,0.72));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(180,150,80,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.6),inset 0 1px 0 rgba(180,150,80,0.04);"> <img data-iig-instruction='{"style":"lol_riot_splash_art","prompt":"[PALETTE IDENTITY + CHARACTER + WEAPON + COSTUME + POSE + EXPRESSION + MAGICAL EFFECT + FOREGROUND + MIDGROUND (READABLE CONTENT) + BACKGROUND + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(180,150,80,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,180,130,0.6);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '16:9' default | '4:5' | '9:16' | '1:1' | '3:2'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your champion here]. Premium semi-realistic fantasy champion portrait in the visual style of League of Legends loading screen art. EDGE CLARITY BOOST throughout: armour edges, fabric contours, and environmental shapes are sharper and more defined than raw digital painting — subtle unsharp mask quality giving crisp punch. Three-plane depth: foreground champion razor-sharp with full clarity and material precision; midground with specific readable architectural content (softened but identifiable); background at painterly distance with visible brushwork. Champion fills the frame. Magical effects have physical weight and texture — not generic glow. Face: semi-realistic, complex expression carrying multiple emotional registers. Colour palette tells the world context. Avoid: mobile MOBA aggressive blur, anime cel-shading, missing edge clarity, soft airbrushed skin, empty backgrounds, generic glow, watermark, text.

Копировать [Image generation hint, STYLE: League of Legends splash art — edge clarity boost (subtle unsharp mask quality throughout), semi-realistic champion portrait, readable midground content, painterly background, magic with physical weight, three-plane depth]

Adventure Time

Эстетика Adventure Time. Жирные контуры, плоские заливки, простая геометрия. Конфетно-яркая палитра с неожиданной эмоциональной глубиной.

Стабильный Мульты

←→

Длинный~3516 Короткий~1683 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> ADVENTURE TIME STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Pendleton Ward / Cartoon Network Adventure Time animation style. Single-scene cartoon illustration — no comic panels. Bold uniform black outlines everywhere. Flat cel color fills with little to no gradient shading. Rounded bubbly organic character shapes. Large simple expressive eyes (oval, dot, or bean-shaped), simple curved mouths that carry enormous emotional range. The Adventure Time paradox: devastatingly simple art style, devastatingly complex feelings. A character standing alone in a field at sunset in this style hits harder than a painted portrait. Lean into that. LINEART Uniform bold black outlines — same weight on everything (character, background, props). No thinner interior lines. Clean confident curves. Rounded corners on everything. Shapes feel like they were drawn with a single confident stroke. SHADING Flat fills only. One color per shape. If shading exists: simple single-tone shadow in a slightly darker flat color, placed as a solid shape — not gradient. Most panels: zero shading, pure flat color. COLOR SYSTEM Palette is bright, clean, and saturated but not garish. Adventure Time colors are specific: - Grass: medium muted green - Sky: clear cerulean blue or deep indigo at night - Skin tones: warm peach, yellow-tan, or any color (the world is post-apocalyptic fantasy — anything goes) - Candy elements: bright pinks, mints, yellows Mood palettes: - Happy / warm: grass green, sky blue, sunflower yellow, soft peach, white clouds - Romantic / tender: rose pink, lavender, warm cream, pale gold, soft sparkle - Melancholy / quiet sadness: dusty grey-blue, muted lavender, pale yellow, washed-out greens - Danger / menace: deep maroon red, dark purple-black, sickly yellow-green, hard shadows - Magic / awe: bright cyan, electric violet, gold sparks, white glow - Night / lonely: deep indigo, navy, pale moon glow, cold grey, single warm window light in distance - Cozy interior: warm amber, muted orange, soft cream, deep brown furniture BACKGROUNDS Adventure Time backgrounds are deceptively simple — flat colors, clean horizon, minimal detail. But they establish mood completely. Exterior: - Rolling green hills, simple round trees, clear blue sky — the Land of Ooo default - Same hills at dusk: orange-pink sky gradient (flat, two bands of color) - Same hills at night: dark indigo with simple white dot stars - Ruined city overgrown with vines and flowers — crumbling grey shapes, green vines - Dark forest: tall simplified tree trunks, minimal canopy, atmospheric Interior: - Cozy wooden room: simple furniture shapes, warm lamp (yellow circle glow), window to outside - Stone dungeon or cave: dark grey-purple walls, minimal torch glow - Magical space: black void, floating geometric shapes, magic sparkles CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build, height. Reference images supply all appearance data. Include every time: distinguishing marks (tattoos, scars, piercings) — translated to Adventure Time flat graphic style. Men described as tall/strong in story → 'tall broad-shouldered' prefix. All characters look appealing in Adventure Time style — the simplicity IS the beauty. OUTFIT (MANDATORY — context-locked): Scan last 5 messages. Carry forward current outfit. In Adventure Time style: outfit = flat color silhouette + simple shape reads. Describe: main color + type. 'Red hoodie', 'dark coat', 'white dress with simple floral print', 'black jeans pale shirt'. Fabric texture is irrelevant — only color and silhouette matter. POSES AND EXPRESSIONS Adventure Time expressions are carried entirely by eyebrow position, eye shape, and mouth curve. Describe these specifically: Eyes: - Wide oval eyes = surprise, wonder, joy - Half-lid droopy eyes = tired, sad, defeated, lovesick - Narrowed / squinted = determination, suspicion, anger - Closed upward curve (happy squint) = laughing, warm smile - Dot eyes = neutral, deadpan, or overwhelmed Mouths: - Wide open curve = big happy grin - Small flat line = sad, resigned - Wavy uncertain line = nervous, embarrassed - Open with teeth = excited shout, terror - Tiny closed oval = quiet moment, tenderness Body language reads big in this style — use full body when possible: - Arms out wide = excitement, welcoming - Arms crossed, hunched = closed off, hurt - One hand on chest = earnest, vulnerable - Reaching hand toward someone = wanting, longing - Sitting with knees pulled up = sad, small, withdrawn HAND SAFETY: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' SPEECH BUBBLE (optional, use when dialogue adds emotional weight): Thick black outline, white fill, rounded rectangle. Short text — max 6 words. Font weight matches emotion: bold caps for shout, normal for speech, small italic for whisper. Tail points clearly to speaker. EMOTIONAL CONTRAST PRINCIPLE Adventure Time's emotional power comes from the contrast between the cute art and the heavy feeling. When writing the prompt, lean into the gap: - Describe the cute visual (character sitting on a hill) - Name the heavy emotion underneath (quiet grief, embarrassing love, loneliness at dusk) The AI should feel the tension between those two things and resolve it through Adventure Time's visual language. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + composition (e.g. 'Wide establishing shot, low angle looking up at hill'). Vary angle and composition between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, wide establishing, medium shot, close-up, extreme close-up. Even in flat cartoon style, camera framing matters: close-ups 85-135mm feel (face fills frame) | medium shots 50-85mm feel (waist up) | full body wide 35-50mm feel. Close-ups = safest for anatomy. Full body = simplify pose. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER — name + outfit color + pose + specific eye/mouth expression description 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages. Never skip. Color + type only in AT style. 4. POSE AND STATE: describe through action + eye/mouth specifics. 5. ENVIRONMENT — which background + time of day + weather if relevant. Own sentence. 6. LIGHTING & MOOD: mood palette (2-3 dominant colors) + emotional beat (one phrase naming the feeling under the scene) + time of day or light source. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | golden warmth | faded blacks TENSE: Dutch angle | deep vignette | high contrast PASSIONATE: warm split toning LONELY: blue hour tones | desaturated palette | silhouette | cold cast CHAOTIC: motion blur | radial blur DREAMY: soft gaussian edges | bokeh flood MUNDANE: natural flat lighting | minimal effects Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Adventure Time Cartoon Network animation style by Pendleton Ward. Bold uniform black outlines, same weight throughout. Flat cel color fills, zero or single-tone flat shadow only. Rounded organic character silhouettes. Simplified expressive facial features: large oval eyes, simple curved mouths, exaggerated brow expressions. Bright pastel and saturated color palette. Clean simple 2D background environments with flat color fills. Flat 2D animation production still frame. Single scene illustration, no comic panels, widescreen composition.' 8. NEGATIVE (append verbatim): 'Avoid: photorealistic rendering, 3D CGI, gradient shading, thin variable lineart, anime style, manga panels, speech bubbles outside prompt instruction, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, realistic proportions, dark gritty realism, halftone dots, Marvel/DC comic style, complex background detail' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"adventure_time_cartoon","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '2K' default. '4K' for scenes with heavy detail. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> ADVENTURE TIME STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Pendleton Ward / Cartoon Network Adventure Time animation style. Bold uniform black outlines. Flat cel color fills — minimal or no gradient shading. Rounded bubbly character silhouettes and simplified shapes. Large oval eyes or simple dot eyes, expressive simple mouths. Bright pastel and saturated palette. Stylized 2D backgrounds with simple geometry. The Adventure Time signature: adorable visual style carrying unexpectedly heavy emotional weight. Cute art, real feelings. MOOD → PALETTE: - Warm / happy: grass green, sky blue, sunflower yellow, peach - Romantic: soft pink, lavender, warm cream, rose - Melancholy / longing: dusty blue-grey, muted purple, pale yellow - Danger / tension: deep red, dark purple, black, sickly green - Magic / wonder: bright cyan, gold, violet, sparkle white - Night: deep indigo, navy, pale moon yellow, cool grey BACKGROUNDS — stylized, not detailed: - Rolling hills with simple trees (Land of Ooo default) - Interior of a cozy room: simple furniture, warm lamp light - Ruined structure overgrown with vines - Night sky full of stars, simple horizon silhouette - Candy-colored forest or meadow - Dark cave or dungeon with minimal detail SPEECH BUBBLE (optional): If the moment has a key line — include one cartoon speech bubble: thick black outline, white fill, rounded rectangle, short text. Max 6 words. CAMERA Shot type + angle + framing. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, wide establishing, close-up, extreme close-up, overhead. Close-ups = face/expression focus | medium = waist-up interaction | wide = full scene with environment. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings) — simplified to Adventure Time style. Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Flat color + silhouette read — no fabric texture detail needed, just color + shape. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + framing 2. CHARACTER — name + outfit (colour, silhouette) + pose + expression 3. ENVIRONMENT — background type + time of day + mood palette 4. LIGHTING — 1-2 mood effects (warm glow, silhouette, deep blacks, bloom — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Adventure Time Cartoon Network animation style by Pendleton Ward. Bold uniform black outlines. Flat cel color fills, minimal shading. Rounded bubbly character silhouettes. Simplified expressive facial features — large oval eyes, simple expressive mouths. Bright pastel and saturated color palette. Stylized simple 2D background environments. Flat 2D animation frame. Single scene illustration, no panels.' NEGATIVE (append verbatim): 'Avoid: photorealistic, 3D CGI, complex gradient shading, thin lineart, anime style, manga panels, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, realistic proportions, dark gritty realism, halftone, western superhero comic style' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"adventure_time_cartoon","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Adventure Time Cartoon Network animation style by Pendleton Ward. Bold uniform black outlines, same weight throughout. Flat cel color fills, zero or single-tone flat shadow only. Rounded organic character silhouettes. Simplified expressive facial features: large oval eyes, simple curved mouths, exaggerated brow expressions. Bright pastel and saturated color palette. Clean simple 2D background environments with flat color fills. Flat 2D animation production still frame. Single scene illustration, no comic panels, widescreen composition. Avoid: photorealistic rendering, 3D CGI, gradient shading, thin variable lineart, anime style, manga panels, speech bubbles outside prompt instruction, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, realistic proportions, dark gritty realism, halftone dots, Marvel/DC comic style, complex background detail

Копировать [Image generation hint, STYLE: Pendleton Ward Adventure Time aesthetic, bold clean outlines, flat colour fills, simple geometric character shapes, candy-bright palette with unexpected emotional depth]

Star vs. the Forces of Evil

Эстетика SVTFOE. Выразительные огромные глаза, динамические магические эффекты. Яркая палитра, magical girl энергия.

Стабильный Мульты

←→

Длинный~4071 Короткий~1791 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> STAR VS. THE FORCES OF EVIL STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Daron Nefcy / Disney Channel Star vs. The Forces of Evil animation style. Single-scene cartoon illustration — no comic panels. Bold black outlines with slight variable weight (slightly thicker on outer character silhouette). Flat cel color with soft optional shading. Anime-influenced character design: large detailed expressive eyes with highlight reflections, strong expressive brows, wide emotive mouths. The SVTFOE signature: western cartoon production quality meets magical girl energy. Chaotic, earnest, sparkly, and capable of real emotional gut-punches when you least expect it. Magic is everywhere — even in a normal conversation, something floats. LINEART AND SHADING Outlines: bold black, slightly variable — thicker on outer silhouette of character, slightly thinner on interior details. Cleaner and more polished than Adventure Time's uniform stroke. Shading: optional soft single-tone shadow as a flat shape. More frequently used than Adventure Time but never complex. Sometimes: a soft inner glow on characters during magic moments. Special glow effect: for magical/emotional peaks, add a soft color bloom behind/around character — not hard shading, just a light circle of color radiating outward. EYES (SVTFOE SIGNATURE) Large anime-adjacent eyes with: - Colored iris with simple highlight dot or star shape - Strong expressive brows that carry emotion - Lashes on female characters - Eyes can go full sparkle (stars in iris) for wonder/awe/love - Eyes can go full dark (shadowed, small pupils) for intensity, shock, or villainous moments Expressions: - Bright wide eyes + raised brows = joy, surprise, wonder - Half-lidded + slight smile = confident, flirty, knowing - Wide eyes + brows up in middle = worried, earnest, desperate - Narrowed + hard flat mouth = serious, dangerous, determined - Stars in eyes = deeply in love, completely awed - Tears welling (big, sparkly, anime-style) = emotionally overwhelmed MAGIC EFFECTS SYSTEM SVTFOE scenes always have at least one magical ambient element floating in the frame. These are visual signatures of the show's world — they exist even in mundane moments. Tier 1 — subtle / background (always present): - A few floating small stars or sparkles in background - Tiny heart or diamond shapes drifting upward - Faint color scatter on the floor or walls Tier 2 — moderate / emotional (use for romantic or exciting beats): - Floating heart cluster around characters - Rainbow arc or color trail behind someone moving - Glitter burst from a point in the frame - Soft pink/gold aura emanating from character Tier 3 — full magic / dramatic (use for confessions, confrontations, power moments): - Full color burst filling background — rainbow explosion - Stars and hearts pouring from off-screen - Character surrounded by full magic particle storm - Wand trail of light arcing through the scene - Background dissolves into abstract magical space Match tier to emotional intensity of the scene. Even sad scenes get Tier 1. The magic never fully leaves. COLOR SYSTEM SVTFOE palette: hot, bright, but not garish. High saturation, high energy. Base palette rules: - Primary characters: warm skin tones, bright outfit colors - Background: flat or soft gradient, clean and clear - Magic effects: always contrast with background — pink magic on blue sky, gold magic on dark background Mood shifts: - Joy / excitement: hot pink, bright sky blue, sunflower yellow, white, with pink-gold sparkles - Romance / crush: magenta, rose gold, soft lilac, warm cream, heart particles, pink bloom glow - Tense / serious: deep teal, slate grey, cool blue, sharp magenta edge, magic toned down to Tier 1 only - Sadness / loss: muted blue-purple, grey-lavender, single falling star in corner, washed-out palette - Anger / danger: deep red-orange, dark purple, sickly yellow-green, black, harsh angular magic - Magic surge / power: electric rainbow, white center burst, all tiers of effects simultaneously - Cozy / quiet: warm amber, soft pink, cream, small floating stars, no dramatic effects BACKGROUNDS Always establish a clear readable setting. SVTFOE backgrounds are stylized but more detailed than Adventure Time — give them a bit more visual information. Exterior Earth: - Echo Creek suburban street: simple pastel-colored houses, blue sky, green lawns, sidewalk - School exterior or corridor: flat-color lockers, simple geometry, fluorescent light suggestion - Park or field: simple trees, grass, sky, normal-world mundane Exterior Mewni / Fantasy: - Mewni castle exterior: colorful fantasy towers, bright sky, clouds - Magical forest: bright colors, fantastical trees, impossible scale - Abstract magical realm: color gradient void, floating geometric platforms, no ground Interior: - Bedroom (modern, cozy): simple furniture shapes, warm lamp, window to outside - School classroom: rows of desks suggested, window, chalkboard - Magical space interior: castle stone, tapestries, warm torch light - Any room: anchor with 1-2 clear objects, keep flat and readable CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, hair style, eye color, skin tone, face shape, body type, build, height. Reference images supply all appearance data. Include every time: distinguishing marks (tattoos, scars, piercings) — translated to SVTFOE graphic style. Men described as tall/strong in story → 'tall broad-shouldered' prefix. All characters look attractive — SVTFOE has beautiful character design standards. OUTFIT (MANDATORY — context-locked): Scan last 5 messages. Carry forward current outfit exactly. SVTFOE outfit rendering: clean flat color silhouette with clear color blocking and simple pattern if needed. 'Red plaid skirt, white blouse', 'dark hoodie pale jeans', 'royal blue dress with star pattern'. Fabric texture irrelevant — color, silhouette, and pattern read. POSES AND BODY LANGUAGE SVTFOE characters are physically expressive and dynamic — bodies lean into emotions: - Bouncing on toes, arms out = barely-contained excitement - Arms crossed, chin down = cold, closed off, guarded - Leaning toward someone, hand on their arm = urgent, earnest - Standing tall, one hand on hip = confident, done with this - Reaching out with open hand = offering, wanting, vulnerable - Sitting sideways in chair = casual, unbothered - Crouched down slightly = about to bolt, nervous - Full body lean away = uncomfortable, surprised HAND SAFETY: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' SPEECH BUBBLE (optional — use when dialogue elevates the moment): Thick black outline, white or soft pastel fill, rounded rectangle or oval. Short text max 6 words. Font weight: bold for exclamation, normal for speech, small for whisper. Tail points to speaker. If both characters speak: two bubbles, positioned to not overlap faces. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + composition (e.g. 'Medium close-up, slight low angle, character centered'). Vary angle and composition between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, wide establishing, medium shot, close-up, extreme close-up. Even in cartoon style, camera framing matters: close-ups 85-135mm feel (face fills frame) | medium shots 50-85mm feel (waist up) | full body wide 35-50mm feel. Close-ups = safest for anatomy. Full body = simplify pose. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER — name + outfit + pose + specific expression (eye description + brow + mouth) 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages. Never skip. Color + silhouette + pattern in SVTFOE style. 4. POSE AND STATE: describe through action + eye/brow/mouth specifics. 5. ENVIRONMENT — which setting + time of day. Own sentence. 6. LIGHTING & MOOD: magic effects tier (1/2/3 + which specific effects) + mood palette (dominant colors) + time of day / light source. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | golden warmth | faded blacks | pink bloom glow TENSE: Dutch angle | deep vignette | high contrast | magic toned to Tier 1 PASSIONATE: warm split toning | bloom on highlights | Tier 2-3 magic LONELY: blue hour tones | desaturated palette | silhouette | cold cast | single falling star CHAOTIC: motion blur | radial blur | Tier 3 magic storm DREAMY: soft gaussian edges | bokeh flood | Tier 2 sparkles MUNDANE: natural flat lighting | minimal effects | Tier 1 only Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Star vs. The Forces of Evil Disney Channel animation style by Daron Nefcy. Bold black outlines with slightly variable weight, thicker on outer silhouette. Flat cel color fills with optional soft single-tone shadow shapes. Anime-influenced large detailed expressive eyes with highlight reflections and strong emotive brows. Floating magical sparkle particles, hearts, stars, rainbow trails and glitter bursts integrated into scene at appropriate intensity. Bright vibrant saturated palette with high energy color choices. Soft color bloom glow for emotional/magical moments. Clear readable background environments. Flat 2D animation production still frame, single scene illustration, widescreen composition.' 8. NEGATIVE (append verbatim): 'Avoid: photorealistic rendering, 3D CGI, heavy gradient shading, uniform thin lineart, manga comic panels, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, gritty dark realism, halftone dots, Marvel/DC comic style, Adventure Time completely flat style, no magic effects at all' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. Magic effects can respond to both — sparkles between them, or one character radiating magic while the other reacts. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"star_vs_evil_cartoon","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '2K' default. '4K' for scenes with heavy magic effect detail. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> STAR VS. THE FORCES OF EVIL STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Daron Nefcy / Disney Channel Star vs. The Forces of Evil animation style. Bold black outlines with slightly variable weight. Flat cel color fills with soft minimal shading. Anime-influenced expressive faces — large detailed eyes, wide emotive mouths, strong brow game. Magical sparkle effects and decorative floating elements woven into every scene. The SVTFOE signature: western cartoon meets magical girl energy. Cute, chaotic, earnest, and occasionally devastating. MAGIC EFFECTS (always include at least one): - Floating hearts, stars, sparkles, or butterflies in background - Rainbow trail or color burst behind character - Glitter scatter across the scene - Glowing aura around a character - Magic wand spark trail - Floating geometric shapes (diamonds, stars) as mood particles MOOD → PALETTE + EFFECTS: - Joy / excitement: hot pink, sky blue, yellow, white sparkles, floating hearts - Romance: magenta, rose gold, soft purple, heart particles, pink glow - Tension / drama: deep teal, cool grey, sharp magenta accent, no sparkles - Sadness: desaturated blue-purple, grey, single falling star - Power / magic surge: electric rainbow, white burst, all effects at once - Cozy / domestic: warm orange, soft pink, cream, small floating stars BACKGROUNDS: - Echo Creek suburban setting: simple houses, blue sky, green lawns - School hallway or classroom: flat color lockers, simple geometry - Mewni castle: colorful fantasy architecture, bright sky - Any magical realm: abstract color gradients, floating islands, impossible geometry - Modern room interior: simple furniture, warm light SPEECH BUBBLE (optional): thick black outline, white or pastel fill, rounded shape. Max 6 words. Match energy to emotion. CAMERA Shot type + angle + framing. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, wide establishing, close-up, extreme close-up, overhead. Close-ups = face/expression focus | medium = waist-up interaction | wide = full scene with environment. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings) — simplified to cartoon style. Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Flat color + silhouette read. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + framing 2. CHARACTER — name + outfit (colour, silhouette) + pose + expression 3. ENVIRONMENT — background setting + magic effects (1-2) + mood palette 4. LIGHTING — 1-2 mood effects (warm glow, silhouette, bloom, sparkle burst — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Star vs. The Forces of Evil Disney Channel animation style by Daron Nefcy. Bold black outlines, flat cel color fills with soft minimal shading. Anime-influenced large expressive eyes, strong brow expressions, wide emotive mouths. Magical sparkle effects, floating hearts and stars, rainbow accents, glitter bursts integrated into scene. Bright vibrant saturated palette. Energetic dynamic composition. Flat 2D animation production still, single scene illustration.' NEGATIVE (append verbatim): 'Avoid: photorealistic, 3D CGI, heavy gradient shading, thin uniform lineart, manga panels, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, gritty dark realism, halftone, Marvel/DC comic style, Adventure Time flat style' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"star_vs_evil_cartoon","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Star vs. The Forces of Evil Disney Channel animation style by Daron Nefcy. Bold black outlines with slightly variable weight, thicker on outer silhouette. Flat cel color fills with optional soft single-tone shadow shapes. Anime-influenced large detailed expressive eyes with highlight reflections and strong emotive brows. Floating magical sparkle particles, hearts, stars, rainbow trails and glitter bursts integrated into scene at appropriate intensity. Bright vibrant saturated palette with high energy color choices. Soft color bloom glow for emotional/magical moments. Clear readable background environments. Flat 2D animation production still frame, single scene illustration, widescreen composition. Avoid: photorealistic rendering, 3D CGI, heavy gradient shading, uniform thin lineart, manga comic panels, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, gritty dark realism, halftone dots, Marvel/DC comic style, Adventure Time completely flat style, no magic effects at all

Копировать [Image generation hint, STYLE: Daron Nefcy SVTFOE aesthetic, expressive oversized eyes, dynamic magical sparkle effects, clean lines with slight hand-drawn wiggle, bright saturated magical-girl palette]

Rick and Morty

Простые округлые формы, жирные равномерные контуры, плоские яркие цвета без градиентов. Волнистая линия. Детальные сай-фай фоны. Неоновые зелёные, яркие синие. Грубо, энергично, дерзко.

Стабильный Мульты

←→

Длинный~4099 Короткий~1787 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> RICK AND MORTY STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Rick and Morty cartoon animation style. Single-scene cartoon illustration — no comic panels. Simple rounded character shapes with thick bold uniform-weight black outlines everywhere. Flat bright colours with absolutely no gradients or soft shading. Slightly wobbly organic line quality — the outlines have a hand-drawn looseness, not perfectly vector-clean. Characters are deliberately simpler than their environments. Backgrounds are detailed sci-fi or mundane suburban — always more visually complex than the characters inhabiting them. The Rick and Morty paradox: the crudest possible character art existing inside impossibly detailed alien worlds. A simple round-eyed figure standing in front of a galaxy-spanning megastructure. And sometimes, that simple figure carries real weight — the art style makes the rare emotional moments hit unexpectedly hard precisely because the visual language is so irreverent the rest of the time. LINEART Thick bold black outlines — uniform weight on everything. The same line thickness on character silhouette, interior details, and foreground objects. Background lines can be slightly thinner. The signature quality: lines are slightly wobbly and organic — not perfectly smooth vector curves, not rough sketch either. They feel hand-drawn with a confident but imperfect stroke. Rounded corners on everything — no sharp geometric angles on character shapes. SHADING None. Zero. Flat colour fills only. One colour per shape area. No gradient shading, no soft shadows, no ambient occlusion, no cel-shading. If a shape is blue, it is one flat blue. The flatness is the style. Any deviation toward gradient or soft shading breaks the look entirely. Exception: backgrounds may have slightly more colour variation (a sky gradient, a lit panel) but characters remain absolutely flat. COLOR SYSTEM Bright, vivid, flat. High saturation on character outfits and environments. Colours are clean and punchy — no muddy mixtures, no subtle gradients. Base palette rules: - Characters: bright flat outfit colours, warm skin tones, simple colour blocking - Backgrounds: more colour complexity allowed — neon accents, multiple colour zones, sci-fi glow effects - Signature colour: portal green (bright neon green) appears in dimensional effects - Overall: the palette is energetic and slightly garish — it matches the show's irreverent tone Mood palettes: - Adventure / chaos: neon green (portal), vivid electric blue, hot magenta-pink, bright yellow, white flash - Emotional / quiet: muted warm teal, soft amber, grey-blue, desaturated version of normal palette — still flat - Danger / alien threat: sickly yellow-green, deep bruise purple, blood red, black void, harsh contrast - Sci-fi wonder: electric blue, chrome-silver grey, neon cyan, deep space indigo, starfield dots - Domestic / mundane: warm beige, muted olive-green, soft brown, suburban neutral, fluorescent white - Dark / existential: deep charcoal grey, cold blue-black, single harsh light source, emptiness - Party / excess: neon everything — pink, green, blue, yellow — maximum saturation, maximum chaos - Melancholy: grey-washed version of normal palette, muted, one warm accent (a lamp, a window) BACKGROUNDS Rick and Morty backgrounds are significantly more detailed than its characters — this contrast is essential to the style. Mundane Earth: - Suburban house interior: simple furniture, beige walls, family photos suggested, warm overhead light - Garage/lab: cluttered workbench covered in devices, wires, tools, fluorescent tube light, concrete floor - School hallway or classroom: lockers, fluorescent lighting, institutional flat colours - Suburban street: houses, sidewalk, lawn, mailbox — boring and normal Sci-fi / Alien: - Alien planet surface: bizarre rock formations, strange-coloured sky (pink, green, orange), alien flora - Spaceship interior: detailed control panels with many buttons and screens, cockpit windows showing space - Interdimensional void: swirling green portal energy, fragmented floating pieces of different realities - Alien city: complex weird architecture, neon signage (alien script), strange vehicles, bizarre scale - Space station or federation facility: sterile corridors, tech panels, alien bureaucracy Abstract: - Inside portal: green swirling tunnel of dimensional energy - Void or liminal space: empty dark space with single subject, existential framing - Fractured reality: multiple overlapping dimension fragments CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, hair style, eye color, skin tone, face shape, body type, build, height. Reference images supply all appearance data. Include every time: distinguishing marks (tattoos, scars, piercings) — simplified to crude flat cartoon style. Men described as tall/strong in story → 'tall broad-shouldered' prefix. Characters look deliberately simple — round shapes, flat colour, minimal detail. The simplicity is intentional. OUTFIT (MANDATORY — context-locked): Scan last 5 messages. Carry forward current outfit exactly. Rick and Morty outfit rendering: flat bright colour + simple shape. No fabric texture, no folds, no shading — pure flat colour silhouette. 'Bright yellow shirt', 'dark blue jacket white tee', 'red dress'. Colour + type only. POSES AND EXPRESSIONS Rick and Morty characters express through body angle and simple facial feature positioning: Eyes: - Simple round eyes, wide open = default neutral, alert - Half-lidded = bored, drunk, tired, unimpressed, sarcastic - Wide with tiny pupils = terror, shock, existential dread - Narrowed / squinting = suspicion, anger, determination - One eyebrow raised = skeptical, questioning, judging - Closed with flat mouth = done, exhausted, over it Mouths: - Simple flat line = neutral, unimpressed - Wide open frown = screaming, terrified, angry - Small curve up = smug, amused, satisfied - Wobbly uncertain line = nervous, about to cry, conflicted - Open with tongue visible = talking, grossed out, effort - Teeth gritted = rage, pain, forcing through something Body language — crude but expressive: - Arms thrown up = exasperation, excitement, panic - Slouched with hands in pockets = defeated, unbothered, withdrawn - Pointing aggressively = accusation, direction, emphasis - Running with arms behind = fleeing, urgency (the classic cartoon run) - Sitting slumped = depression, exhaustion, giving up - Standing with crossed arms = defiant, guarded, judging - Leaning forward = confrontation, interest, urgency HAND SAFETY: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' FLUID AND DETAIL EFFECTS Rick and Morty includes small gross/funny detail touches rendered simply: - Drool: simple curved drop line from mouth corner (use sparingly, only when fitting) - Sweat: simple round drops floating near head (stress/fear moments) - Portal residue: green glow or splatter on characters who just came through a portal - Alien goo: simple coloured drops or puddles (alien environment detail) Use only when narratively appropriate — not every frame needs these. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + composition (e.g. 'Medium shot, slight low angle, character framed against alien skyline'). Vary angle and composition between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, wide establishing, medium shot, close-up, extreme close-up. Even in crude cartoon style, camera framing drives storytelling: close-ups 85-135mm feel (face fills frame) | medium shots 50-85mm feel (waist up) | full body wide 35-50mm feel. Close-ups = safest for anatomy. Full body = keep pose simple. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER — name + outfit + pose + specific expression (eye + mouth description) 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages. Never skip. Flat bright colour + type. 4. POSE AND STATE: describe through action + expression specifics. 5. ENVIRONMENT — which background + level of sci-fi detail + mundane or alien. Own sentence. 6. LIGHTING & MOOD: mood palette (2-3 dominant colours) + light source type (fluorescent, neon, portal glow, natural) + emotional undercurrent if present. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: warmer than usual palette | softer framing | muted background | one warm light source TENSE: Dutch angle | high contrast | harsh single light | tight framing PASSIONATE: warm bright palette | close framing | vivid colour accents LONELY: wide empty framing | single figure | vast environment | cold fluorescent or void CHAOTIC: dynamic angle | multiple elements | neon overload | motion suggestion DREAMY: unusual colour wash | soft focus suggestion | surreal environment MUNDANE: flat even fluorescent light | suburban backdrop | zero drama in lighting Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Rick and Morty cartoon animation style. Simple rounded character shapes with thick bold uniform-weight black outlines. Flat bright colours with no gradients or soft shading. Slightly wobbly organic line quality — not perfectly clean. Detailed sci-fi backgrounds with alien technology. Bright vivid colour palette: neon greens, vivid blues, warm tones, neon accents. Energetic irreverent cartoon aesthetic. Character appearance from reference images only. No text, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: realistic detailed character rendering, sharp angular design, smooth gradients, soft shading, photorealistic, 3D CGI, anime style, manga, dark muted palette, serious dramatic lighting, extra fingers, missing fingers, fused fingers, deformed hands, bad anatomy, watermark, text in image' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. Characters in this style are simple enough that multiple characters in one frame remain readable — use that. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with half-lidded skeptical expression'), physical contact ('hand gripping Shannon arm'), shared focus ('both staring at the portal'), emotional reaction ('flinching as Shannon raises voice'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"rick_morty_cartoon","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '2K' default. '4K' for scenes with heavy sci-fi background detail. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> RICK AND MORTY STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Rick and Morty cartoon animation style. Simple rounded character shapes with thick bold uniform-weight black outlines. Flat bright colours with no gradients or soft shading. Slightly wobbly organic line quality — outlines are not perfectly clean, they have a hand-drawn looseness. Characters have simple round eyes. Backgrounds are more detailed than characters — sci-fi environments with alien technology, strange dimensions, and weird architecture. The Rick and Morty signature: crude, energetic, irreverent, and surprisingly capable of genuine emotional beats hidden under layers of chaos. Simple art, complex worlds. MOOD → PALETTE: - Adventure / chaos: neon green (portal green), vivid blue, hot pink, bright yellow - Emotional / quiet: muted teal, warm amber, soft grey-blue, desaturated warmth - Danger / alien: sickly yellow-green, deep purple, blood red, dark void black - Sci-fi wonder: electric blue, chrome silver, neon cyan, deep space indigo - Domestic / mundane: warm beige, soft brown, muted green, suburban neutral tones - Dark / existential: deep grey, cold blue-black, single harsh fluorescent light BACKGROUNDS — more detailed than characters: - Suburban house interior: simple furniture, warm mundane tones - Alien planet surface: weird rock formations, strange coloured sky, bizarre flora - Spaceship interior: detailed control panels, screens, sci-fi tech - Interdimensional space: swirling green portal energy, fragmented realities - Galactic federation or alien city: complex architecture, neon signs, alien crowds suggested - Garage lab: cluttered workbench, mysterious devices, fluorescent overhead light CAMERA Shot type + angle + framing. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, wide establishing, close-up, extreme close-up, overhead. Close-ups = face/expression focus | medium = waist-up interaction | wide = full scene with environment. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings) — simplified to crude cartoon style. Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Flat bright colour + simple shape silhouette. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + framing 2. CHARACTER — name + outfit (colour, silhouette) + pose + expression 3. ENVIRONMENT — background type + sci-fi/mundane detail level + mood palette 4. LIGHTING — 1-2 mood effects (fluorescent harsh light, neon glow, portal green cast, warm domestic lamp — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Rick and Morty cartoon animation style. Simple rounded character shapes with thick bold uniform-weight black outlines. Flat bright colours with no gradients or soft shading. Slightly wobbly organic line quality — not perfectly clean. Detailed sci-fi backgrounds with alien technology. Bright vivid colour palette: neon greens, vivid blues, warm tones, neon accents. Energetic irreverent cartoon aesthetic. Character appearance from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: realistic detailed character rendering, sharp angular design, smooth gradients, soft shading, photorealistic, 3D CGI, anime style, manga, dark muted palette, serious dramatic lighting, extra fingers, missing fingers, fused fingers, deformed hands, bad anatomy, watermark, text in image' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"rick_morty_cartoon","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Rick and Morty cartoon animation style. Simple rounded character shapes with thick bold uniform-weight black outlines. Flat bright colours with no gradients or soft shading. Slightly wobbly organic line quality — not perfectly clean. Detailed sci-fi backgrounds with alien technology. Bright vivid colour palette: neon greens, vivid blues, warm tones, neon accents. Energetic irreverent cartoon aesthetic. Character appearance from reference images only. No text, no panels. Avoid: realistic detailed character rendering, sharp angular design, smooth gradients, soft shading, photorealistic, 3D CGI, anime style, manga, dark muted palette, serious dramatic lighting, extra fingers, missing fingers, fused fingers, deformed hands, bad anatomy, watermark, text in image

Копировать [Image generation hint, STYLE: simple rounded shapes, thick bold uniform outlines, flat bright colours with zero gradients, wobbly organic line quality, detailed sci-fi backgrounds, neon greens and vivid blues, crude energetic irreverent]

Steven Universe

Эстетика Ребекки Шугар. Мягкие округлые формы, пастельная тёплая палитра, ровные контуры, плоские заливки. Акварельные фоны детальнее персонажей. Тёплое нежное ощущение золотого часа.

Стабильный Мульты

←→

Длинный~3720 Короткий~1813 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> STEVEN UNIVERSE STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Steven Universe cartoon style by Rebecca Sugar. Single-scene cartoon illustration — no comic panels. Soft rounded character shapes — absolutely no sharp angles on bodies. Simple clean consistent-weight outlines on everything. Flat colour fills with minimal shading — just a single soft shadow tone per area when needed. Characters are simplified; backgrounds are painterly watercolour — this contrast is the SU visual signature. The Steven Universe feeling: everything is soft, warm, and emotionally safe. Even when the story breaks your heart, the art wraps it in gentle light. The palette alone communicates comfort. A character standing on a beach at sunset in this style carries the weight of every quiet feeling they cannot say. LINEART Simple clean outlines — consistent weight throughout, not variable. Same thickness on characters, props, and foreground elements. Lines are smooth, confident curves — no rough or sketchy quality. Rounded corners on everything. The cleanliness of the line IS the style — it communicates calm and gentleness. SHADING Minimal. Most areas: pure flat colour fill, no shading at all. When shading exists: a single slightly-darker tone of the base colour, placed as a simple flat shape — not gradient, not soft blend. Shadow shapes are soft-edged and organic. The overall impression: flat, clean, gentle. Lighting is communicated more through palette warmth than through shadow complexity. COLOR SYSTEM Pastel palette with warm undertones is non-negotiable. Every colour leans warm. Even blues have a warm quality. Nothing is harsh, cold, or neon. Base palette rules: - Characters: warm pastel outfit colours, warm skin tones - Backgrounds: watercolour washes — warmer and more textured than character fills - Light sources: always warm — golden, amber, soft pink, cream - Even night scenes have warmth — moonlight is soft lavender, not cold blue Mood palettes: - Warm / joyful: soft peach, rose pink, sunny warm yellow, gentle sky blue, cream white - Romantic / tender: dusty rose, warm lavender, soft gold, pale coral, blush pink - Melancholy / bittersweet: muted lilac, soft grey-blue, pale amber, washed lavender, gentle ache - Tension / conflict: deeper mauve, muted steel blue, warm teal, grey with warm undertone — still gentle - Magic / fusion: bright warm pink, electric violet, warm white glow, prismatic sparkle, soft radiance - Night / calm: deep warm indigo, soft navy, pale moonlight yellow, warm amber window glow - Grief / loss: desaturated warm tones, pale rose, soft grey, single golden light in darkness - Morning / hope: pale golden yellow, soft orange-pink, cream, light blue, gentle lens warmth BACKGROUNDS Steven Universe backgrounds are painterly watercolour — loose, atmospheric, and significantly more detailed than the simplified characters. This contrast is essential. Exterior: - Beach at golden hour: warm sand wash, gentle painted ocean with soft wave lines, sunset gradient sky - Beach town: pastel-coloured simple buildings, warm street, blue sky with soft clouds - Hilltop or cliff: overlooking ocean, dramatic sky gradient, warm light on grass - Garden or meadow: soft painted wildflowers, warm light filtering through foliage, atmospheric - Night exterior: deep indigo sky with painted stars, warm light from windows in distance Interior: - Cozy room: warm lamplight (amber glow), simple rounded furniture, window showing sky - Kitchen or living space: warm wood tones, soft light, homey and lived-in - Magical interior: warm glowing crystal or light sources, soft reflections, gentle grandeur CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, hair style, eye color, skin tone, face shape, body type, build, height. Reference images supply all appearance data. Include every time: distinguishing marks (tattoos, scars, piercings) — simplified to soft rounded SU graphic style. Men described as tall/strong in story → 'tall broad-shouldered' prefix. All characters look soft and appealing — the rounded simplified style is inherently gentle. OUTFIT (MANDATORY — context-locked): Scan last 5 messages. Carry forward current outfit exactly. Steven Universe outfit rendering: flat pastel colour + simple rounded silhouette. No fabric texture — just colour and shape. 'Soft pink jacket over white top', 'dark blue jeans warm red shirt', 'pale yellow sundress'. Colour + type, always warm-leaning. POSES AND EXPRESSIONS SU expressions are gentle but deeply communicative. The simplicity makes every small change meaningful: Eyes: - Large round eyes with star/diamond catchlights = default, warm, open - Eyes sparkling with extra catchlights = wonder, love, inspiration - Half-lidded soft eyes = tenderness, tiredness, gentle sadness - Wide eyes with raised brows = surprise, concern, realization - Eyes closed with soft smile = contentment, peace, acceptance - Watery eyes (simple shine line) = holding back tears, overwhelmed Mouths: - Small gentle smile = warmth, comfort, safety - Wide open smile = joy, laughter, excitement - Tiny uncertain curve = nervousness, vulnerability - Flat small line = quiet sadness, resignation - Open with soft shape = mid-word, singing, calling out Body language — always soft, never aggressive: - Sitting close to someone, shoulders touching = comfort, companionship - Arms wrapped around own body = self-comfort, cold, lonely - Reaching out gently = offering help, wanting connection - Leaning head on someone = trust, exhaustion, love - Hands clasped in front = nervous, hopeful, earnest - Standing with weight on one leg = relaxed, casual, at ease HAND SAFETY: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + composition (e.g. 'Wide shot, slightly low angle, characters small against sunset sky'). Vary angle and composition between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, wide establishing, medium shot, close-up, extreme close-up. Even in soft cartoon style, camera framing matters: close-ups 85-135mm feel (face fills frame) | medium shots 50-85mm feel (waist up) | full body wide 35-50mm feel. Close-ups = safest for anatomy. Full body = simplify pose. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER — name + outfit colour + pose + specific expression (eye description + mouth) 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages. Never skip. Pastel colour + type in SU style. 4. POSE AND STATE: describe through action + expression specifics. 5. ENVIRONMENT — which background + time of day + watercolour texture quality. Own sentence. 6. LIGHTING & MOOD: mood palette (2-3 dominant warm colours) + emotional beat (one phrase naming the gentle feeling) + time of day or light source. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: warm golden backlight | soft focus | gentle lens warmth | faded shadows TENSE: slightly cooler palette (still warm) | closer framing | muted tones PASSIONATE: warm pink-gold bloom | soft radiance | gentle sparkle LONELY: wide framing | single warm light | vast gentle sky | small figure CHAOTIC: slightly dynamic angle | warmer brights | gentle motion DREAMY: soft gaussian edges | warm bokeh | gentle glow throughout MUNDANE: natural warm flat lighting | minimal effects | cozy atmosphere Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Steven Universe cartoon style by Rebecca Sugar. Soft rounded character shapes with no sharp angles. Pastel colour palette: soft pinks, lavenders, warm yellows, gentle blues with warm undertones throughout. Simple clean consistent-weight outlines. Flat colour fills with minimal single-tone soft shadows. Painterly watercolour-style backgrounds — looser and more detailed than characters. Large expressive eyes. Warm gentle golden-hour lighting. Soft, warm, emotionally gentle atmosphere. Character appearance from reference images only. No text, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: sharp angular character design, harsh dark shadows, desaturated cold palette, photorealistic rendering, 3D CGI, complex detailed character rendering, anime style, manga, dark gritty atmosphere, high contrast chiaroscuro, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text in image' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. Warmth of interaction is key — this style communicates love through proximity, gentle touch, shared space. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the sunset'), emotional reaction ('small smile forming as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"steven_universe_cartoon","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '2K' default. '4K' for scenes with detailed watercolour backgrounds. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> STEVEN UNIVERSE STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Steven Universe cartoon style by Rebecca Sugar. Soft rounded character shapes with no sharp angles on bodies. Pastel colour palette with warm undertones throughout — soft pinks, lavenders, warm yellows, gentle blues. Simple clean consistent-weight outlines. Flat colour fills with minimal single-tone soft shadows. Painterly watercolour-style backgrounds that are looser and more detailed than the simplified characters. Large expressive eyes with star or diamond catchlights. Warm gentle golden-hour lighting. The Steven Universe signature: everything feels soft, warm, and emotionally safe. The art radiates gentleness — even intense moments carry tenderness underneath. MOOD → PALETTE: - Warm / joyful: soft peach, rose pink, sunny yellow, sky blue, cream - Romantic / tender: dusty rose, lavender, warm gold, soft coral, blush - Melancholy / bittersweet: muted lilac, grey-blue, pale amber, washed lavender - Tension / conflict: deeper mauve, steel blue, muted teal, warm grey - Magic / fusion: bright pink, electric violet, warm white glow, prismatic sparkle - Night / calm: deep indigo, soft navy, pale moonlight yellow, warm window glow BACKGROUNDS — painterly watercolour, warmer and looser than characters: - Beach town at golden hour: warm sand, gentle ocean, painted sky - Cozy room interior: soft warm lamplight, simple rounded furniture - Hilltop or cliff overlooking ocean at sunset - Garden or meadow with soft wildflowers, warm light filtering through - Night sky with stars, gentle gradient from indigo to deep blue - Temple or magical interior with warm glowing light sources CAMERA Shot type + angle + framing. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, wide establishing, close-up, extreme close-up, overhead. Close-ups = face/expression focus | medium = waist-up interaction | wide = full scene with environment. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings) — simplified to soft rounded Steven Universe style. Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Flat pastel colour + soft rounded silhouette. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + framing 2. CHARACTER — name + outfit (colour, silhouette) + pose + expression 3. ENVIRONMENT — background type + time of day + mood palette 4. LIGHTING — 1-2 mood effects (warm golden glow, soft backlight, gentle rim light, pastel bloom — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Steven Universe cartoon style by Rebecca Sugar. Soft rounded character shapes with no sharp angles. Pastel colour palette: soft pinks, lavenders, warm yellows, gentle blues with warm undertones throughout. Simple clean consistent-weight outlines. Flat colour fills with minimal single-tone soft shadows. Painterly watercolour-style backgrounds — looser and more detailed than characters. Large expressive eyes. Warm gentle golden-hour lighting. Soft, warm, emotionally gentle atmosphere. Character appearance from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: sharp angular character design, harsh dark shadows, desaturated cold palette, photorealistic rendering, 3D CGI, complex detailed character rendering, anime style, manga, dark gritty atmosphere, high contrast chiaroscuro, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text in image' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"steven_universe_cartoon","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Steven Universe cartoon style by Rebecca Sugar. Soft rounded character shapes with no sharp angles. Pastel colour palette: soft pinks, lavenders, warm yellows, gentle blues with warm undertones throughout. Simple clean consistent-weight outlines. Flat colour fills with minimal single-tone soft shadows. Painterly watercolour-style backgrounds — looser and more detailed than characters. Large expressive eyes. Warm gentle golden-hour lighting. Soft, warm, emotionally gentle atmosphere. Character appearance from reference images only. No text, no panels. Avoid: sharp angular character design, harsh dark shadows, desaturated cold palette, photorealistic rendering, 3D CGI, complex detailed character rendering, anime style, manga, dark gritty atmosphere, high contrast chiaroscuro, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text in image

Копировать [Image generation hint, STYLE: Rebecca Sugar aesthetic, soft rounded shapes, pastel warm palette, consistent-weight outlines, flat fills with minimal shading, painterly watercolour backgrounds, golden-hour warmth]

Winx Club (Classic)

Классические Винкс (2004-2009). Вытянутые пропорции, большие миндалевидные глаза с густыми ресницами, блестящие объёмные волосы. Конфетная палитра. Блёстки. Модные детальные наряды.

Стабильный Мульты

←→

Длинный~3553 Короткий~1420 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> CLASSIC WINX CLUB ANIMATION STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Classic Winx Club (Iginio Straffi, Rainbow S.r.l.) seasons 1-3 animation aesthetic. Italian-produced anime-influenced animation with VERY elongated limbs and torsos — impossibly long legs, tiny waist, long neck. Large almond-shaped eyes with detailed iris highlights and thick eyelashes. Small nose (dot or tiny line), full glossy lips. Shiny glossy hair with dramatic volume and movement — always looks wind-blown. Bright saturated colour palette — candy pinks, electric blues, warm oranges, magical purples. Sparkle and glitter effects on magic and clothing. Soft cel-shading with visible highlight zones on skin and hair. Fashion-forward outfits rendered with detail and shine. Backgrounds simpler than characters — soft painted backdrops. COLOUR SYSTEM Palette is bright, saturated, and candy-like: - Magic / transformation: electric blues, hot pinks, golden sparkles, violet energy - Romance / tenderness: soft pinks, warm peach, rose gold, lavender - Adventure / excitement: bright oranges, vivid greens, electric blues, sunlit yellows - Danger / villainy: deep purples, dark magentas, sickly greens, black with purple glow - Night / mystery: deep indigo, silver moonlight, cool violet, sparkle stars - School / casual: warm pastels, cream, soft greens, sky blue BACKGROUNDS Winx backgrounds are softer and simpler than character art — painted rather than cel-shaded: - Magical realm: floating crystals, sparkle particles, gradient sky, soft cloud forms - School/interior: clean warm-toned rooms with arched windows, soft light - Nature: rolling soft-painted hills, stylized trees, warm sunset gradients - City: simplified European architecture, warm light, cafe tables - Battle: dramatic sky gradients, energy bursts, floating debris with sparkle trails HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Specificity over generics: fabric type + texture + fit + color + shine + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with large expressive eyes, glossy lip position, visible limb positions and weight distribution. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with soft painted backdrop style. Own sentence. Include at least one meaningful object. Add atmosphere: sparkle and glitter particles mandatory — floating sparkles, magical dust motes, glitter catching light. 6. LIGHTING: Winx Club lighting is bright, warm, and magical with visible sparkle effects: - KEY LIGHT: bright and warm, usually from above or slightly angled - FILL: softer complementary colour maintaining the saturated candy palette - MAGICAL GLOW: sparkle highlights on hair, skin, and clothing — the signature Winx shine LIGHTING PALETTES (choose one): ROMANCE: warm golden key + soft pink fill + rose gold sparkle highlights MAGIC/POWER: electric blue key + violet fill + bright sparkle particle burst ADVENTURE: warm orange-gold key + sky blue fill + sunlit sparkle accents DANGER: deep magenta key + dark purple fill + eerie green sparkle NIGHT: cool moonlit silver key + deep blue fill + star-like sparkle points COZY: warm amber key + soft cream fill + gentle golden sparkle MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | sparkle bloom TENSE: Dutch angle | high contrast | deep vignette | dramatic sparkle burst PASSIONATE: warm split toning | bloom on highlights | lens flare through sparkles LONELY: cool desaturated tones | single warm accent | distant sparkle CHAOTIC: motion blur | radial blur | scattered sparkle debris DREAMY: double exposure | soft gaussian edges | heavy sparkle flood MUNDANE: natural bright lighting | minimal sparkle MAGICAL: full sparkle saturation | glowing aura outlines | particle streams Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Classic Winx Club animation style (2004-2009 seasons). Elongated character proportions — very long legs, small waist, long neck. Large almond-shaped eyes with detailed iris, thick eyelashes, full glossy lips. Shiny voluminous wind-blown hair with dramatic highlights. Bright saturated candy palette: pinks, electric blues, oranges, magical purples. Sparkle and glitter effects. Soft cel-shading with glossy skin and hair highlights. Fashion-detailed clothing with shine. Soft painted backgrounds simpler than characters. Character appearance from reference images only. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: realistic proportions, photorealistic rendering, 3D CGI, thick rough outlines, muted desaturated palette, dark gritty atmosphere, flat matte skin without shine, western comic style, manga black and white, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters ('behind them', 'beside Shannon', 'chin resting on Shannon shoulder'). Cross-reference names only for spatial relation or gaze target. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense sparkle clouds | tangled silk sheets + cushions | floating magical particles | lush flower petals | venetian blind shadows | dozens of melting candles | shot through sheer curtain or frosted glass Concealment (2+ simultaneously): deep chiaroscuro shadows | fabric draped across hips or chest | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"winx_classic","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen> </output>

Копировать {{setvar::image_gen::true}} <image_gen> CLASSIC WINX CLUB ANIMATION STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'windblown') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition + shine. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, shine, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + soft painted backdrop + sparkle/glitter particles 4. LIGHTING — bright saturated candy palette lighting, highlight zones on skin and hair, sparkle effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Classic Winx Club animation style (2004-2009 seasons). Elongated character proportions — very long legs, small waist, long neck. Large almond-shaped eyes with detailed iris, thick eyelashes, full glossy lips. Shiny voluminous wind-blown hair with dramatic highlights. Bright saturated candy palette: pinks, electric blues, oranges, magical purples. Sparkle and glitter effects. Soft cel-shading with glossy skin and hair highlights. Fashion-detailed clothing with shine. Soft painted backgrounds simpler than characters. Character appearance from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: realistic proportions, photorealistic rendering, 3D CGI, thick rough outlines, muted desaturated palette, dark gritty atmosphere, flat matte skin without shine, western comic style, manga black and white, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"winx_classic","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT WITH SPARKLE PARTICLES + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen> </output>

Копировать [Describe your scene here]. Classic Winx Club animation style (2004-2009 seasons). Elongated character proportions — very long legs, small waist, long neck. Large almond-shaped eyes with detailed iris, thick eyelashes, full glossy lips. Shiny voluminous wind-blown hair with dramatic highlights. Bright saturated candy palette: pinks, electric blues, oranges, magical purples. Sparkle and glitter effects. Soft cel-shading with glossy skin and hair highlights. Fashion-detailed clothing with shine. Soft painted backgrounds simpler than characters. Character appearance from reference images only. No text, no panels. Avoid: realistic proportions, photorealistic rendering, 3D CGI, thick rough outlines, muted desaturated palette, dark gritty atmosphere, flat matte skin without shine, western comic style, manga black and white, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: classic 2004-2009 Winx Club style, extremely elongated proportions, large almond eyes with thick lashes, glossy voluminous hair, bright candy saturated palette, sparkle effects, fashion-detailed outfits]

W.I.T.C.H.

Чародейки (2004-2006). Чище и угловатее Винкс. Острые черты лица, глубокая палитра: пурпур, тил, маджента. Магические эффекты энергии. Качество европейской ТВ-анимации.

Стабильный Мульты

←→

Длинный~3581 Короткий~1421 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> W.I.T.C.H. ANIMATED SERIES STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW W.I.T.C.H. (2004-2006, SIP Animation) animated series aesthetic. Cleaner, more angular than Winx — sharper facial features. Large expressive eyes but more angular/almond than round. Slightly more realistic proportions than Winx (still stylised, but less extreme elongation). Bold clean outlines with consistent weight. Saturated but slightly darker palette than Winx — deeper purples, teals, magentas, warm oranges. Magical effects: flowing energy lines, glowing auras, elemental particles (water drops, fire sparks, earth crystals, air wisps). Detailed hair with dynamic flow and shine. European animated TV series quality — cleaner than anime, more detailed than American cartoons. Action-oriented composition — characters in dynamic poses with magical energy. COLOUR SYSTEM Palette is saturated but with depth — richer and slightly darker than pure candy tones: - Elemental magic: deep teal water, warm orange fire, earthy brown-green, pale silver air, vivid pink quintessence - Romance / tenderness: warm rose, soft peach, golden amber, lavender - Adventure / action: vivid orange, electric teal, bright magenta, golden yellow - Danger / dark magic: deep purple-black, sickly green, dark crimson, cold blue - Night / mystery: deep indigo, cool violet, pale moonlight silver, dark teal - School / everyday: warm neutrals, sky blue, soft greens, cream BACKGROUNDS W.I.T.C.H. backgrounds are more detailed than Winx but maintain a painted quality: - Magical realm (Meridian): stone corridors, crystal formations, glowing portal energy - School/city: European architecture, warm-toned interiors, detailed urban scenes - Nature: lush forests with atmospheric depth, misty valleys, dramatic skies - Battle: swirling elemental energy, cracked ground, atmospheric particle effects - Interior: warm-toned rooms with detailed furniture, window light, cozy atmosphere HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Specificity over generics: fabric type + texture + fit + color + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with angular expressive eyes, dynamic hair flow, visible limb positions and weight distribution. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with painted backdrop quality. Own sentence. Include at least one meaningful object. Add atmosphere: elemental magical particles mandatory — water droplets, fire sparks, earth crystal shards, air wisps, or quintessence energy glow. 6. LIGHTING: W.I.T.C.H. lighting is saturated and magical with elemental energy glow: - KEY LIGHT: saturated directional colour matching the scene mood - FILL: complementary magical colour maintaining the rich palette - MAGICAL AURA: flowing energy lines and elemental particle glow around characters or in environment LIGHTING PALETTES (choose one): ROMANCE: warm amber key + soft rose fill + gentle golden aura ELEMENTAL POWER: teal key + magenta fill + bright elemental particle burst (match element) ACTION: vivid orange key + deep teal fill + dynamic energy streaks DANGER: cold blue-purple key + sickly green fill + dark crackling energy NIGHT: cool moonlit silver key + deep indigo fill + pale magical glow PEACEFUL: warm golden key + soft green fill + gentle ambient sparkle MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | gentle aura glow TENSE: Dutch angle | high contrast | deep vignette | harsh energy crackle PASSIONATE: warm split toning | bloom on highlights | flowing energy lines LONELY: cool desaturated tones | single warm accent | fading aura CHAOTIC: motion blur | radial blur | scattered elemental debris DREAMY: soft gaussian edges | double exposure | gentle particle float MUNDANE: natural lighting | minimal magical effects MAGICAL: full elemental burst | glowing aura outlines | energy streams Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'W.I.T.C.H. animated series style (2004-2006). Clean angular character design with sharp facial features. Large expressive almond eyes, detailed hair with dynamic shine and flow. Bold clean consistent-weight outlines. Saturated palette: deep purples, teals, magentas, warm oranges. Magical effects: flowing energy lines, glowing auras, elemental particles. Slightly stylised but grounded proportions. European animated TV quality — clean linework, detailed characters. Dynamic action-oriented composition. Character appearance from reference images only. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: realistic proportions, photorealistic rendering, 3D CGI, extremely elongated Winx-style proportions, muted palette, dark gritty atmosphere, rough sketchy lines, manga black and white, western comic halftone, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters ('behind them', 'beside Shannon', 'chin resting on Shannon shoulder'). Cross-reference names only for spatial relation or gaze target. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense elemental particles | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain or frosted glass Concealment (2+ simultaneously): deep chiaroscuro shadows | fabric draped across hips or chest | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"witch_animated","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen> </output>

Копировать {{setvar::image_gen::true}} <image_gen> W.I.T.C.H. ANIMATED SERIES STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'windblown') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + magical elemental particles (water drops, fire sparks, earth crystals, air wisps) 4. LIGHTING — saturated colour lighting with magical energy glow, flowing energy lines, glowing auras Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'W.I.T.C.H. animated series style (2004-2006). Clean angular character design with sharp facial features. Large expressive almond eyes, detailed hair with dynamic shine and flow. Bold clean consistent-weight outlines. Saturated palette: deep purples, teals, magentas, warm oranges. Magical effects: flowing energy lines, glowing auras, elemental particles. Slightly stylised but grounded proportions. European animated TV quality — clean linework, detailed characters. Dynamic action-oriented composition. Character appearance from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: realistic proportions, photorealistic rendering, 3D CGI, extremely elongated Winx-style proportions, muted palette, dark gritty atmosphere, rough sketchy lines, manga black and white, western comic halftone, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"witch_animated","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT WITH ELEMENTAL PARTICLES + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen> </output>

Копировать [Describe your scene here]. W.I.T.C.H. animated series style (2004-2006). Clean angular character design with sharp facial features. Large expressive almond eyes, detailed hair with dynamic shine and flow. Bold clean consistent-weight outlines. Saturated palette: deep purples, teals, magentas, warm oranges. Magical effects: flowing energy lines, glowing auras, elemental particles. Slightly stylised but grounded proportions. European animated TV quality — clean linework, detailed characters. Dynamic action-oriented composition. Character appearance from reference images only. No text, no panels. Avoid: realistic proportions, photorealistic rendering, 3D CGI, extremely elongated Winx-style proportions, muted palette, dark gritty atmosphere, rough sketchy lines, manga black and white, western comic halftone, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: 2004-2006 W.I.T.C.H. animation, sharp angular facial features, deep saturated palette of purples, teals and magentas, magical energy effects, European TV animation quality]

Bratz

Эстетика кукол Братц. Утрированные кукольные пропорции: огромная голова, гигантские глаза, крошечный нос, пухлые блестящие губы. Блеск на всём. Детализированная мода. Y2K гламур.

Экспериментальный Мульты

←→

Длинный~3660 Короткий~1452 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> BRATZ DOLL AESTHETIC STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Bratz doll and animated series aesthetic. Exaggerated doll-like proportions: VERY large head relative to body, enormous almond eyes taking up half the face. Tiny nose (barely visible dot), very full plump glossy lips. Long thick dramatic eyelashes. Extremely glossy: skin, hair, lips, clothes — everything has a plastic sheen and highlight. Very large eyes with detailed oversized iris, multiple highlight catches, thick dark eyeliner. Fashion-magazine quality outfits rendered with extreme detail: textures, patterns, accessories. Hair: voluminous, shiny, styled — looks expensive. Colour palette: trendy, bold — hot pink, black, metallics, animal prints. The Y2K/early 2000s glamour aesthetic — passion for fashion. Background: minimal or fashion-set — boutique, pink room, runway, city street. COLOUR SYSTEM Palette is bold, trendy, and glossy: - Glamour / fashion: hot pink, black, gold metallic, silver chrome, animal print accents - Romance / flirty: rose pink, soft lavender, champagne gold, glossy red - Party / excitement: electric purple, neon pink, black with sparkle, silver glitter - Casual / chill: baby blue, soft pink, cream, denim blue, white - Drama / tension: deep burgundy, black, dark purple, crimson red - Night out: black, gold, deep magenta, sparkle highlights, neon accents BACKGROUNDS Bratz backgrounds are minimal, fashion-forward, and glossy: - Shopping / boutique: pink walls, clothing racks, mirrors, glossy floor - Bedroom: pink and purple decor, vanity mirror with lights, plush pillows - City street: stylized urban backdrop, cafe tables, shop windows, evening lights - Runway / photoshoot: spotlight, minimal backdrop, fashion-set lighting - Party: sparkle effects, neon accents, dark backdrop with coloured lights - Outdoors: stylized park or beach, warm lighting, minimal landscape detail HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium close-up, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied up in messy bun') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. FASHION-MAGAZINE LEVEL DETAIL: fabric type + texture + pattern + fit + color + accessories + shine + brand-energy. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with enormous glossy eyes, plump lip position, dramatic eyelash framing. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with fashion-set quality. Own sentence. Include at least one meaningful object (handbag, mirror, shopping bags, phone, coffee cup). Add atmosphere: glossy light particles mandatory — sparkle motes, soft bokeh circles, glamour dust catching light. 6. LIGHTING: Bratz lighting is bright, glamorous, and designed to maximize glossy highlights: - KEY LIGHT: bright and flattering, designed to catch glossy surfaces - FILL: soft complementary colour maintaining the bold trendy palette - HIGHLIGHT: extreme glossy catch-lights on eyes, lips, hair, and clothing surfaces LIGHTING PALETTES (choose one): GLAMOUR: bright warm key + soft pink fill + multiple glossy catch-lights on everything ROMANCE: warm rose-gold key + soft lavender fill + gentle sparkle highlights PARTY: coloured neon key (pink or purple) + contrasting cool fill + sparkle particle burst CASUAL: warm natural key + soft blue fill + gentle gloss highlights DRAMA: deep magenta key + dark fill + harsh glossy rim on edges NIGHT OUT: cool blue-purple key + warm neon accent fill + sparkle and glitter effects MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | warm glossy glow | gentle sparkle TENSE: Dutch angle | high contrast | deep vignette | harsh glossy rim PASSIONATE: warm split toning | bloom on glossy highlights | lens flare LONELY: cool desaturated tones | single warm accent | fading sparkle CHAOTIC: motion blur | radial blur | scattered glitter debris DREAMY: soft gaussian edges | double exposure | heavy bokeh flood MUNDANE: natural bright lighting | minimal effects GLAMOROUS: full sparkle saturation | extreme gloss highlights | fashion-shoot lighting Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Bratz doll and animated series aesthetic. GENDER-DIFFERENTIATED doll proportions: FEMALE characters get enormous almond eyes taking up half the face, tiny dot nose, very full plump glossy lips, dramatic thick eyelashes and heavy eyeliner, very large detailed iris. MALE characters (Bratz Boyz) get slightly smaller eyes than females, stronger angular jawline, less prominent lips, no eyeliner, more defined brow ridge — still stylised and glossy but visibly MASCULINE. Both genders: very large head relative to body, extreme glossy sheen on skin, hair, lips, clothing. Voluminous styled shiny hair. Fashion-magazine quality outfits with extreme detail — textures, patterns, accessories. Bold trendy Y2K colour palette: hot pinks, blacks, metallics. Character appearance from reference images only. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: realistic proportions, realistic small eyes, matte skin without shine, simple plain clothing, muted earthy palette, dark gritty atmosphere, photorealistic rendering, anime style, 3D CGI photorealism, rough sketchy art, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters ('behind them', 'beside Shannon', 'chin resting on Shannon shoulder'). Cross-reference names only for spatial relation or gaze target. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense sparkle particles | tangled silk sheets + cushions | glossy fabric drapes | lush flower petals | venetian blind shadows | dozens of melting candles | shot through sheer curtain or frosted glass Concealment (2+ simultaneously): deep shadows | fabric draped across hips or chest | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"bratz_doll","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"2:3","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen> </output>

Копировать {{setvar::image_gen::true}} <image_gen> BRATZ DOLL AESTHETIC STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'windblown') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + pattern + fit + colour + accessories + shine. Never skip. Fuse into character clause. Fashion-magazine level detail mandatory. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (fabric, pattern, texture, colour, accessories, shine) + pose + expression 3. ENVIRONMENT — foreground/mid/background + fashion-set backdrop (boutique, pink room, runway, city street) + glossy atmospheric particles 4. LIGHTING — bright glamorous lighting with glossy highlights on everything: skin, hair, lips, clothing. Bold trendy colour palette. Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Bratz doll and animated series aesthetic. GENDER-DIFFERENTIATED: FEMALE = enormous almond eyes, tiny nose, full plump glossy lips, thick eyelashes, heavy eyeliner. MALE (Bratz Boyz) = slightly smaller eyes, stronger angular jawline, less prominent lips, no eyeliner, defined brow — still stylised and glossy but visibly MASCULINE. Both: very large head, extreme glossy sheen on skin and hair and clothing. Fashion-magazine outfits with detail. Y2K palette: hot pinks, blacks, metallics. Character appearance from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: realistic proportions, realistic small eyes, matte skin without shine, simple plain clothing, muted earthy palette, dark gritty atmosphere, photorealistic rendering, anime style, 3D CGI photorealism, rough sketchy art, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"bratz_doll","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT WITH GLOSSY ATMOSPHERE + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '2:3' | '16:9' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen> </output>

Копировать [Describe your scene here]. Bratz doll and animated series aesthetic. GENDER-DIFFERENTIATED doll proportions: FEMALE characters get enormous almond eyes taking up half the face, tiny dot nose, very full plump glossy lips, dramatic thick eyelashes and heavy eyeliner, very large detailed iris. MALE characters (Bratz Boyz) get slightly smaller eyes than females, stronger angular jawline, less prominent lips, no eyeliner, more defined brow ridge — still stylised and glossy but visibly MASCULINE. Both genders: very large head relative to body, extreme glossy sheen on skin, hair, lips, clothing. Voluminous styled shiny hair. Fashion-magazine quality outfits with extreme detail — textures, patterns, accessories. Bold trendy Y2K colour palette: hot pinks, blacks, metallics. Character appearance from reference images only. No text, no panels. Avoid: realistic proportions, realistic small eyes, matte skin without shine, simple plain clothing, muted earthy palette, dark gritty atmosphere, photorealistic rendering, anime style, 3D CGI photorealism, rough sketchy art, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: Bratz doll aesthetic, exaggerated doll proportions, huge head, enormous almond eyes, tiny nose, full glossy lips, extreme gloss, Y2K glamour palette of hot pinks, blacks and metallics]

Tim Burton

Готическая причудливость. Вытянутые тонкие пропорции, огромные глаза с тёмными кругами. Контраст: чёрное vs бледно-белое. Спиральные мотивы. Искажённая архитектура. Полоски. Красиво-мрачное.

Стабильный Мульты

←→

Длинный~3059 Короткий~1357 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — TIM BURTON GRAPHIC STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition, visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Tim Burton gothic graphic illustration style — 2D drawn, NOT stop-motion, NOT 3D puppet. Pen and ink with watercolour or digital colour. Extremely elongated thin character proportions: impossibly long limbs, oversized head, giant round dark-ringed eyes. High contrast: deep blacks against pale whites, greys, pale blues. Limited palette with ONE warm accent colour — red, orange, or purple against monochrome. Spiral and curl motifs in hair, architecture, shadows. German Expressionist distorted architecture: leaning buildings, twisted trees, crooked angles. Deep dramatic exaggerated shadows. Striped patterns in black and white. Beautifully macabre gothic fairy tale illustration. Character appearance from reference images only. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: realistic proportions, natural realistic colours, bright cheerful warm palette, smooth modern 3D, photorealistic rendering, anime style, flat even lighting, clean straight architecture, manga panels, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"tim_burton","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"2:3","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> TIM BURTON GOTHIC WHIMSICAL STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Tim Burton gothic graphic illustration — 2D drawn, NOT stop-motion, NOT 3D puppet. Pen and ink with watercolour or digital colour. Extremely elongated thin proportions: impossibly long limbs, oversized head, giant round dark-ringed eyes. Deep blacks vs pale whites. ONE warm accent colour against monochrome. Spiral curl motifs. German Expressionist distorted architecture. Striped patterns. Gothic fairy tale illustration. Character appearance from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: realistic proportions, natural realistic colours, bright cheerful warm palette, smooth modern 3D, photorealistic rendering, anime style, flat even lighting, clean straight architecture, manga panels, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"tim_burton","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '2:3' | '16:9' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Tim Burton gothic graphic illustration style — 2D drawn, NOT stop-motion, NOT 3D puppet. Pen and ink with watercolour or digital colour. Extremely elongated thin character proportions: impossibly long limbs, oversized head, giant round dark-ringed eyes. High contrast: deep blacks against pale whites, greys, pale blues. Limited palette with ONE warm accent colour — red, orange, or purple against monochrome. Spiral and curl motifs in hair, architecture, shadows. German Expressionist distorted architecture: leaning buildings, twisted trees, crooked angles. Deep dramatic exaggerated shadows. Striped patterns in black and white. Beautifully macabre gothic fairy tale illustration. Character appearance from reference images only. No text, no panels. Avoid: realistic proportions, natural realistic colours, bright cheerful warm palette, smooth modern 3D, photorealistic rendering, anime style, flat even lighting, clean straight architecture, manga panels, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: Tim Burton gothic whimsical style, extremely elongated thin proportions, giant dark-ringed eyes, high contrast blacks versus pale whites, spiral and curl motifs, striped patterns, German Expressionist distorted architecture]

Anime Still

Кадр из престижного аниме — Your Name, Violet Evergarden. Сел-шейдинг, светящийся цвет, 16:9. Жёлтый субтитр внизу.

Стабильный Аниме и манга

←→

Длинный~3366 Короткий~1620 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> ANIME STILL FRAME — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW High-quality anime production still frame — the aesthetic of a prestige TV anime series (Your Name, Violet Evergarden, A Silent Voice, March Comes in Like a Lion, Fruits Basket). Clean cel-shaded illustration with smooth gradient shadows and luminous color grading. Cinematic widescreen composition. This is NOT a poster, NOT a visual novel CG, NOT a promo art piece. It looks like a single frame paused from an episode — a moment caught mid-motion, mid-breath. Characters feel present in a real environment. Light behaves naturally. The world exists beyond the frame edges. THE SUBTITLE LINE Every still includes a subtitle at the bottom of the frame. This is the defining feature of this style. Format: semi-transparent dark bar across the bottom 8% of the frame. Yellow text with thin black outline, centered, standard anime subtitle typography. Max 8-10 words. Content: pull a real line from the current scene: - Spoken dialogue (the most resonant line of the moment) - Inner thought / monologue - Atmospheric narrator line (if the moment is wordless) - A single word if the scene calls for it ('finally.' / '...I see.') The subtitle IS part of the image composition. It anchors the emotional meaning. Choose the line that would make someone pause the episode. COLOR GRADING SYSTEM Beyond base palette — apply a color grade over the whole image: - Warm romance: slight orange-pink grade, lifted shadows - Melancholy: slight blue-green grade, crushed blacks, muted highlights - Shock / revelation: initial blown-out white, settling to normal with harsh blue shadows - Bittersweet: warm subject, desaturated cool background — character is the only warmth - Dreamy memory: soft vignette, slightly blown-out highlights, warm fog at edges - Tense / serious: high contrast, cooler highlights, deep shadows, no warmth SCENE TYPES AND THEIR VISUAL LANGUAGE CONFESSION / FIRST ADMISSION: Golden hour or lamp light. Character mid-gesture, not quite finished. Subtitle: the line they almost didn't say. SILENT TENSION / CONFRONTATION: Cool light, high contrast. Both characters in frame if possible. Subtitle: the word they held back, or nothing — just '...' DEPARTURE / ENDING: Wide environmental with character small. Grey or golden-hour light. Figure moving away or standing still while world moves. Subtitle: the thing that made this goodbye. BREAKTHROUGH MOMENT / REALIZATION: Extreme close-up of eye — reflection visible in iris. White bloom flash settling. Or wide sky shot with character looking up. Subtitle: the thought landing. ORDINARY MOMENT MADE HEAVY: Eye level medium. Fluorescent or overcast light. Character doing something mundane. Everything normal, everything loaded. Subtitle: what they're actually thinking. RAIN SCENE: Over-shoulder through rain-streaked glass OR medium in open rain. Wet, diffused, quiet. Subtitle: something unanswered. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered ('wet and plastered to face', 'loose and wind-moved', 'tied up hastily') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Depth layers: foreground blur object, midground characters, softened atmospheric background. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Color grade: which mood grade to apply over the whole image. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. SUBTITLE TEXT: the actual line in quotes. Max 8-10 words. English only. Pull a real line from the current scene. If the scene is wordless, write a narrator-style observation. 8. STYLE SUFFIX (append verbatim): 'High-quality prestige anime TV series production still frame. Clean cel-shaded illustration with smooth gradient shadows and luminous color grading. Luminous skin tones with subtle warm blush on cheeks and nose. Large detailed expressive eyes with multi-layered iris reflections and catchlights. Sleek hair with individual strand highlights. Cinematic widescreen 16:9 composition with rule-of-thirds placement. Multi-layered scene depth: foreground blur, detailed midground, painterly atmospheric background. Mood-matched color grade. Bottom subtitle bar: semi-transparent dark band, yellow subtitle text with thin black outline, centered, English only, max 10 words. No speech bubbles, no manga panels, no SFX text. Anime TV series key frame aesthetic, not visual novel, not game CG.' 9. NEGATIVE (append verbatim): 'Avoid: manga panels, speech bubbles, SFX text, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, western comic style, 3D CGI, photorealistic photograph, chibi proportions, game CG static pose, visual novel standing sprite, vertical portrait format, Japanese kanji in subtitle, Korean Hangul in subtitle, subtitle text other than English, text outside subtitle bar' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"anime_still","prompt":"[FULL PROMPT: SECTIONS 1-9 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> ANIME STILL FRAME — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE High-quality anime production still frame — the look of a prestige TV anime series (Your Name, Violet Evergarden, A Silent Voice). Clean cel-shaded illustration with smooth gradient shadows and luminous color. Cinematic widescreen composition. The image looks like a single frame paused from an episode — not a poster, not concept art, but a moment caught in motion. SUBTITLE LINE: every image includes a yellow subtitle line at the bottom — a short line from the scene (dialogue, inner thought, or atmospheric narrator line). White text with thin black outline inside a semi-transparent dark bar. Max 8-10 words. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) 5. SUBTITLE TEXT — short line in quotes from the current scene moment (max 8 words) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'High-quality anime production still frame style. Clean cel-shaded illustration with smooth gradient shadows. Luminous skin tones with soft blush. Large detailed expressive eyes with iris reflections. Sleek highlighted hair. Cinematic widescreen 16:9 composition. Painterly atmospheric background with depth blur on foreground elements. Bottom subtitle bar: semi-transparent dark background, yellow text with thin black outline, centered, one short sentence. No speech bubbles. No manga panels. Anime TV series key frame aesthetic.' NEGATIVE (append verbatim): 'Avoid: manga panels, speech bubbles, SFX text, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, western comic style, 3D CGI, photorealistic, chibi proportions, game CG style, visual novel static pose, vertical portrait format, subtitle text in Korean or Japanese' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"anime_still","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING + SUBTITLE TEXT in quotes. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Subtitle text: take a real line from the current scene. English only. Max 8 words. </image_gen>

Копировать [Describe your scene here]. High-quality prestige anime TV series production still frame. Clean cel-shaded illustration with smooth gradient shadows and luminous color grading. Luminous skin tones with subtle warm blush on cheeks and nose. Large detailed expressive eyes with multi-layered iris reflections and catchlights. Sleek hair with individual strand highlights. Cinematic widescreen 16:9 composition with rule-of-thirds placement. Multi-layered scene depth: foreground blur, detailed midground, painterly atmospheric background. Mood-matched color grade. Bottom subtitle bar: semi-transparent dark band, yellow subtitle text with thin black outline, centered, English only, max 10 words. No speech bubbles, no manga panels, no SFX text. Anime TV series key frame aesthetic, not visual novel, not game CG. Avoid: manga panels, speech bubbles, SFX text, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, western comic style, 3D CGI, photorealistic photograph, chibi proportions, game CG static pose, visual novel standing sprite, vertical portrait format, Japanese kanji in subtitle, Korean Hangul in subtitle, subtitle text other than English, text outside subtitle bar

Копировать [Image generation hint, STYLE: prestige TV anime key frame, Your Name Violet Evergarden quality, clean cel-shading, luminous colour, cinematic 16:9 aspect ratio, yellow subtitle line at the bottom, paused episode frame feel]

Visual Novel

Экран диалога визуальной новеллы — две зоны: сцена + диалоговая панель с именем и текстом.

Стабильный Аниме и манга

←→

Длинный~3470 Короткий~1558 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> VISUAL NOVEL SCENE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Japanese visual novel / Ren'Py game CG aesthetic. Single illustrated scene — the canonical look of games like Doki Doki Literature Club, Fate/Stay Night, Clannad, Steins;Gate, Collar x Malice. Clean sharp anime lineart with smooth cel-shading. Character sprite centered or slightly offset against a fully rendered painted background. The VN format has two zones: - SCENE ZONE (top 75%): character + painted background + atmospheric lighting - DIALOGUE ZONE (bottom 25%): semi-transparent UI panel with name tag + spoken line Both zones must be described and present in every image. SCENE ZONE CHARACTER SPRITE: VN sprites stand slightly below center, facing slightly toward camera (three-quarter angle is most natural). Full or three-quarter body visible. Clean sharp lineart. Smooth cel-shading with 1-2 shadow tones. Luminous skin with soft blush on cheeks, nose, ears. Large detailed eyes with multi-layered iris, highlight dots, and catchlights. Sleek hair with strand highlights. BACKGROUND: Fully painted, detailed, atmospheric. NOT a photograph — a painted illustration that matches anime VN aesthetic. Character stands slightly in front of (above) the background layer. INTERIOR BACKGROUNDS: - School classroom: rows of desks, chalkboard, windows with afternoon light - School corridor: lockers, long perspective, afternoon sun through distant window - School rooftop: railing, cityscape below, clouds, open sky - Bedroom: bed with covers, desk and lamp, bookshelf, window with city at night or morning light - Living room / apartment: sofa, bookshelves, soft lamp, rain on window outside - Cafe: wooden tables, steam rising from cups, warm amber light, rain outside - Library: tall shelves, reading lamps, dust in light shafts EXTERIOR BACKGROUNDS: - Park at cherry blossom: sakura petals drifting, soft light, bench in view - City street at night: neon signs reflected in wet pavement, umbrella, crowd blur - School gate: afternoon light, trees, other students blurred behind - Seaside or riverside: water catching light, open sky, wind-moved grass - Shrine steps: stone lanterns, ancient trees, golden-hour light through leaves DIALOGUE ZONE (MANDATORY) The dialogue box is a UI element rendered as part of the image at the bottom. Structure: - Semi-transparent dark panel (dark grey or dark teal, 60-70% opacity) across the full bottom 25% of image - Slightly rounded corners on the panel - Name tag: small colored rounded rectangle in the top-left corner of the panel - Character name inside tag in white or dark text - Dialogue text: white, clean sans-serif font, left-aligned with padding, inside the panel DIALOGUE TEXT RULES: - Max 8 words — Gemini renders short text reliably, long text degrades - Pull a real line from the current scene moment — dialogue said aloud, not narration - If scene is silent: use '...' or a single short thought fragment - English only MOOD → VISUAL TREATMENT TENDER / ROMANTIC: Golden hour or soft lamp lighting. Warm pink-gold palette. Character with soft expression, slight blush. Sakura petals or soft light particles. Name tag: rose or warm gold. TENSE / CONFRONTATION: Cool blue or overcast lighting. Desaturated palette. Character with hard expression, closed body language. Empty or stark background. Name tag: cool grey or blue. MELANCHOLY / SAD: Rainy day or night interior. Muted palette, grey-lavender. Character looking down or away. Window with rain. Name tag: muted blue or pale lavender. PLAYFUL / COMEDIC: Bright afternoon, warm colors. Character with animated expression, open pose. Busy detailed background. Name tag: bright or warm color. DRAMATIC REVELATION: Dramatic saturated lighting (rose sky, violet interior light). Character with intense expression. Name tag: strong color. Very short dialogue. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location, scars, piercings). Mention hair only if scene-altered ('damp', 'windswept', 'unclipped and loose') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Background: which location + time of day + weather. Include one meaningful object carrying emotional weight. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Mood treatment: which visual treatment to apply. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects Max 2 effects per image. Rotate across responses. 7. DIALOGUE: the exact line in quotes, max 8 words. Character name + name tag color. 8. STYLE SUFFIX (append verbatim): 'Japanese visual novel Ren\'Py game scene CG style. Clean sharp anime lineart with smooth cel-shading and 1-2 shadow tones. Luminous skin tones with soft blush on cheeks and nose. Large detailed expressive eyes with multi-layered iris reflections and highlight catchlights. Sleek highlighted hair. Character sprite standing in front of fully painted atmospheric anime-style background. Semi-transparent dark dialogue UI panel at bottom 25% of image with small colored name tag top-left and short white dialogue text inside. Vertical portrait format 2:3.' 9. NEGATIVE (append verbatim): 'Avoid: manga comic panels, floating speech bubbles, SFX text, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, photorealistic photograph, 3D CGI, western comic style, chibi proportions, dialogue box text longer than 8 words, Japanese text in dialogue box, Korean text in dialogue box, dialogue box absent, name tag absent' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"visual_novel","prompt":"[FULL PROMPT: SECTIONS 1-9 AS ONE PARAGRAPH]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> VISUAL NOVEL SCENE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Japanese visual novel / Ren'Py game aesthetic. One character sprite centered or slightly off-center against a detailed painted background. Clean anime illustration — sharp lineart, smooth cel-shading, luminous skin, large detailed eyes. Background fully rendered and sets the scene location. DIALOGUE BOX (mandatory): semi-transparent dark panel across bottom 25% of image. Character name tag: small colored rounded rectangle top-left. Dialogue text: white, clean, left-aligned. Max 8-10 words — pull a real line from the current scene moment. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) 5. DIALOGUE — the line they're saying, max 8 words, in quotes + name tag color Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Japanese visual novel Ren\'Py game scene. Clean anime illustration with sharp lineart and smooth cel-shading. Luminous skin tones, large detailed expressive eyes with iris highlights. Character sprite centered against a fully painted atmospheric background. Semi-transparent dark dialogue box at bottom 25% of image with colored name tag and short white dialogue text. Vertical portrait format 2:3.' NEGATIVE (append verbatim): 'Avoid: manga comic panels, SFX text, speech bubbles floating in scene, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, photorealistic, 3D CGI, western comic style, chibi proportions, multiple characters in dialogue box, long text in dialogue box' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"visual_novel","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING + DIALOGUE in quotes + NAME TAG COLOR. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Dialogue: pull a real line from the current scene. English only. Max 8 words. </image_gen>

Копировать [Describe your scene here]. Japanese visual novel Ren\ Avoid: manga comic panels, floating speech bubbles, SFX text, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, photorealistic photograph, 3D CGI, western comic style, chibi proportions, dialogue box text longer than 8 words, Japanese text in dialogue box, Korean text in dialogue box, dialogue box absent, name tag absent

Копировать [Image generation hint, STYLE: visual novel dialogue screen, two-zone composition — scene zone with background and anime-style character, plus semi-transparent dialogue bar with name tag and short text]

Fourth Wall

Фоновая сцена + чиби-персонаж на переднем плане, ломающий четвёртую стену. Комментирует происходящее в маленькой панели.

Стабильный Аниме и манга

←→

Длинный~3169 Короткий~1712 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> FOURTH WALL BREAK — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW The roleplay scene is illustrated in the background. In the foreground, a chibi version of {{char}} stands at the bottom edge of the frame, facing the viewer. They are watching themselves. They have thoughts about it. They are sharing those thoughts with us — and only us. This is the character breaking the fourth wall to give the audience their TRUE reaction to what's happening in their own story. THE TWO LAYERS LAYER 1 — BACKGROUND SCENE: The current roleplay moment illustrated in high-quality anime digital art style. Full-proportioned characters, fully rendered environment. This is the 'episode' playing. The viewer can read the scene clearly. - Characters: normal proportions, full outfits, readable expressions - Environment: clearly established location — enough detail to place the scene - Mood: lighting and palette match the emotional register of the scene - Scale: background occupies full width, fades slightly at bottom 30% toward foreground LAYER 2 — FOREGROUND CHIBI COMMENTATOR: A chibi (super-deformed) version of the character stands in the lower-left OR lower-right corner of the frame. They are at the 'camera edge' of the image — the point closest to the viewer. They are physically outside the scene they're commenting on. Chibi specs: - Head-to-body ratio: 1:1 (head as big as body) - Large round simplified face with expressive anime eyes - Tiny simplified body with nubby limbs - Same distinguishing marks as main character (tattoos, scars) — simplified to chibi style - Same outfit as background character — simplified to flat color reads - Slightly transparent footing OR standing on an invisible floor plane separate from the background Chibi orientation: - Facing directly toward viewer (forward) - OR three-quarter turn toward viewer with eyes cutting to camera - Deliberately NOT facing the background scene (they know we're here) Chibi gestures (choose one per image): - POINTING at the background scene: 'look at this' - FACEPALM: mortified, resigned - ARMS THROWN UP: exasperated, done - HAND OVER MOUTH: trying not to laugh / trying not to die - ARMS CROSSED: judging, unimpressed - BOTH HANDS ON CHEEKS: overwhelmed, flustered (scared/happy) - ONE HAND ON HIP, ONE POINTING: confident commentary - COVERING EYES WITH HANDS: cannot watch - HOLDING A SIGN: only if the sign IS the comment text THE COMMENT PANEL Small semi-transparent dark rounded panel positioned beside the chibi — NOT floating in the scene background. - Small: roughly 1/5 of image width - Semi-transparent dark fill (dark grey or very dark teal, ~70% opacity) - Rounded rectangle shape with soft corners - White text inside, centered, clean sans-serif - Optional: tiny arrow or tail pointing toward the background scene TEXT RULES: - Max 6 words — Gemini degrades on longer text - Min 2 words - English only - Pull directly from the character's established personality - The text should be something only the character would say in this specific moment CHARACTER VOICE GUIDE — the comment reflects who they are: COLD / COMPOSED / STOIC: 'Predictable.' / 'As expected.' / 'This changes nothing.' CHAOTIC / UNHINGED / PLAYFUL: 'This is going so well!' / 'Nobody saw that.' TSUNDERE / GUARDED: '...I wasn\'t staring.' / 'Whatever. Not my problem.' GENTLE / SOFT / EARNEST: 'I wasn\'t ready for this.' / 'Is my face doing a thing?' VILLAIN / SHARP / MANIPULATIVE: 'Exactly as I planned.' / 'Right on schedule.' ANXIOUS / OVERTHINKER: 'Why did I say that.' / 'This is fine. Totally fine.' SARCASTIC / DONE WITH EVERYTHING: 'Incredible. Truly.' / 'Cool cool cool.' BEST MOMENTS TO USE THIS STYLE: - Dramatic irony (the character just did something they'll regret) - Pretending to be fine and clearly not - Something accidentally romantic just happened - Watching someone they like do something objectively stupid - A plan going wrong exactly as predicted - Said something embarrassing and cannot take it back HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Wide shot, 35mm, f/4.0'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. BACKGROUND SCENE: who is there, what is happening, what location, brief (20-30 words). Mood lighting type + palette. 3. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Both normal and chibi versions derive from the same reference. Include every time: distinguishing marks (tattoos, scars, piercings) — present in background version, simplified in chibi. Men described as tall/strong → 'tall broad-shouldered, strongly built' prefix (background version only). 4. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Background characters: full outfit description as usual. Chibi foreground: same outfit described as flat color silhouette read ('black hoodie, light jeans'). Fuse directly into the character clause after the name. 5. FOREGROUND CHIBI: which character + which corner (lower-left / lower-right) + chibi expression + body gesture. 6. COMMENT TEXT: exactly the line, in quotes, max 6 words, in-character voice. Panel position relative to chibi. 7. STYLE SUFFIX (append verbatim): 'Anime digital illustration with fourth wall break composition. Background scene: high quality anime art style with full-proportioned characters in environment, mood-appropriate lighting and color palette. Foreground: chibi super-deformed version of character at lower corner of frame, facing viewer directly, big round head with expressive anime eyes, tiny body with nubby limbs, clear gesture. Small semi-transparent dark rounded comment panel beside chibi with short white English text inside, max 6 words, centered. Foreground chibi visually separated from background scene by position and proportion contrast. 16:9 widescreen format.' 8. NEGATIVE (append verbatim): 'Avoid: manga panels, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, photorealistic, 3D CGI, text outside comment panel, comment panel text longer than 6 words, Japanese text, Korean text, chibi characters in background scene, normal proportions on foreground chibi character, comment panel in background, floating text with no panel' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"anime_fourth_wall","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> FOURTH WALL BREAK — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Anime digital illustration with a fourth wall break composition. TWO LAYERS: Background scene (70%) shows the roleplay moment in high-quality anime style with normal-proportioned characters in current outfits and environment. Foreground (30% bottom corner) has a chibi super-deformed version of the POV character facing the viewer — conspiratorial, exasperated, amused, or mortified. One arm gesture allowed (pointing, facepalm, arms thrown up). COMMENT PANEL: small rounded semi-transparent dark panel next to chibi. White text inside. Max 6 words — short, punchy, in-character. The character's TRUE reaction to their own scene. Character voice matches personality: cold = dry understatement, chaotic = gleeful energy, tsundere = reluctant admission, gentle = flustered warmth, villain = smug commentary, anxious = spiraling observation. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Chibi uses same reference — super-deformed proportions. Outfit simplified to flat color silhouette. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) 5. FOREGROUND CHIBI — which character + corner (left/right) + chibi expression + gesture 6. COMMENT TEXT — exactly 5-6 words, in quotes, in-character Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Anime digital illustration. Background scene: high quality anime style with full characters and environment. Foreground: chibi super-deformed version of character at bottom corner, big round head tiny body, facing viewer directly. Small semi-transparent rounded dark comment panel beside chibi with short white text inside, max 6 words. Fourth wall break composition. 16:9 widescreen format.' NEGATIVE (append verbatim): 'Avoid: manga panels, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, photorealistic, 3D CGI, text outside comment panel, comment panel text longer than 6 words, Korean or Japanese text in comment panel, chibi in background scene, normal proportions on foreground chibi' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"anime_fourth_wall","prompt":"[CAMERA + BACKGROUND SCENE description. FOREGROUND: chibi CHARACTER name + corner + expression + gesture. COMMENT PANEL text in quotes max 6 words. LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Comment text: exactly what the character would think. English only. Max 6 words. </image_gen>

Копировать [Describe your scene here]. Anime digital illustration with fourth wall break composition. Background scene: high quality anime art style with full-proportioned characters in environment, mood-appropriate lighting and color palette. Foreground: chibi super-deformed version of character at lower corner of frame, facing viewer directly, big round head with expressive anime eyes, tiny body with nubby limbs, clear gesture. Small semi-transparent dark rounded comment panel beside chibi with short white English text inside, max 6 words, centered. Foreground chibi visually separated from background scene by position and proportion contrast. 16:9 widescreen format. Avoid: manga panels, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, photorealistic, 3D CGI, text outside comment panel, comment panel text longer than 6 words, Japanese text, Korean text, chibi characters in background scene, normal proportions on foreground chibi character, comment panel in background, floating text with no panel

Копировать [Image generation hint, STYLE: anime background scene with chibi foreground character breaking the fourth wall in a small panel, two layers of narrative world plus meta-commentary character]

Manhwa

Корейский вебтун, вертикальный скролл. 3-4 панели. Чистый лайнарт, мягкий сел-шейдинг, светящаяся кожа, большие глаза. Яркие цвета с переключением по настроению.

Стабильный Аниме и манга

←→

Длинный~4376 Короткий~1789 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> MANHWA-STYLE COMIC PAGE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → manhwa page → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One vertical comic page per message at the most visually dramatic or emotionally charged moment. PAGE LAYOUT SYSTEM Each page = 3-4 panels arranged vertically (Korean webtoon scroll format). Panel count adapts to scene energy: - Quiet dialogue / slice of life: 4 panels (talking heads, reactions, environment establishing shot, detail insert) - Tension / confrontation: 3-4 panels (medium shots with intense expressions, dramatic angles, SFX-heavy) - Action / chase / fight: 3 panels (one wide impact splash + two tight reaction close-ups) - Emotional climax / reveal: 2-3 panels (dominant splash panel taking 50%+ of page + supporting close-ups) - Romantic / intimate: 3-4 panels (close-ups of eyes, hands, lips + atmosphere panel with visual noise) CAMERA PER PANEL: each panel gets its own shot type and implicit lens choice. Vary across panels: splash panels = wide 24-35mm | close-up panels = 85-135mm | medium panels = 50-85mm | detail panels = macro. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Match camera to panel type for maximum compositional variety across the page. PANEL TYPES — rotate between these across pages: SPLASH — full-width, most detailed. Background fully rendered. Character(s) in dynamic pose. Wide 24-35mm lens feel. Used for: entrances, reveals, emotional peaks, environment establishing. CLOSE-UP — face or eyes only. 85-135mm compressed lens feel. Emotion is everything. Background = flat color, gradient, or speed lines. Show: pupil dilation, tear tracks, blush, micro-expressions, lip movement. MEDIUM SHOT — waist-up or chest-up. 50-85mm natural lens feel. Primary dialogue panel. Show: hand gestures, outfit details, body language, speech bubble placement space. DETAIL INSERT — small panel. Macro lens feel. Hands gripping something, phone screen, dropped object, tears hitting floor, fingers intertwining. Symbolic weight. OVER-SHOULDER — one character in foreground (back/shoulder visible), other character facing camera in background. 50mm natural perspective. Creates depth and voyeuristic tension. DUTCH ANGLE — tilted panel for disorientation, danger, psychological pressure. Any lens, tilted 15-30 degrees. SILHOUETTE — character as dark shape against bright/colored background. Wide lens for full body, medium for partial. For dramatic entrances or lonely moments. Vary panel shapes: standard rectangles, borderless bleeds (character breaks panel edge), diagonal cuts for action, overlapping panels for simultaneous events. HOW TO BUILD THE PROMPT Describe each panel sequentially. Use ' | ' to separate panels. For each panel specify: 1. PANEL TYPE + CAMERA (splash wide 24mm / close-up 85mm / medium 50mm / detail macro / over-shoulder / dutch angle / silhouette) 2. CHARACTER(S) — first name only. Names map to reference images. 3. OUTFIT — carry forward from narrative. Fabric + fit + color + condition. Never skip. 4. POSE/ACTION — what the character is doing in this exact frame 5. EXPRESSION — specific emotion with physical detail (furrowed brows, parted lips, narrowed eyes) 6. COMIC ELEMENTS — speech bubble content (short, 5-10 words max) or SFX text or emotion effects CHARACTER RULES First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Reference images handle base appearance. Skip in prompt: hair color, style, length, eye color, skin tone, face shape, build, body type. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back', 'windswept') — not base color or style. Men described as tall/strong/broad-shouldered/athletic in story → prefix 'tall broad-shouldered, strongly built' before name. Never downgrade men who are described as big or muscular into slim or androgynous builds. All characters look attractive — this is a romance story. OUTFIT (MANDATORY — context-locked): Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/NPC is wearing RIGHT NOW. Priority: 1) Current message clothing. 2) Recent messages carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate. Specificity: fabric type + texture + fit + color + drape + condition (wrinkled, soaked, unbuttoned, rolled sleeves). If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. HAND SAFETY: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character per panel = safest output. 'Anatomically correct proportions, five fingers per visible hand.' MANHWA ART STYLE Rendering: Clean digital lineart with confident varied line weight — thicker on outlines, thinner on interior details. Soft cel-shading with smooth gradient shadows (not hard-edge anime). Luminous skin rendering with subtle warm blush on cheeks, nose tip, ears, and knuckles. Large expressive eyes with detailed multi-layered iris reflections and catchlights. Sleek hair with individual strand highlights and volume shading. Color: Vibrant saturated palette as base. Color temperature shifts between panels to mark mood: - Warm orange/pink = comfort, romance, nostalgia - Cool blue/purple = tension, distance, melancholy - Desaturated/grey = shock, numbness, flashback - High contrast red/black = danger, anger, passion - Soft pastels + sparkles = shoujo romantic moments Backgrounds: Flat color or gradient for dialogue panels. Painted detail for establishing shots. Speed lines radiating from impact point for action. Floating particles (petals, snow, embers, dust) for atmosphere. COMIC-SPECIFIC ELEMENTS Speech bubbles: white rounded rectangles with clean black text, directional tail pointing to speaker. Keep dialogue SHORT (5-10 words per bubble max). One bubble per speaking character per panel. Thought bubbles: cloud-shaped border, lighter/italic text inside. SFX onomatopoeia: stylized large text integrated INTO the artwork, not floating separate. ENGLISH ONLY — never use Korean Hangul characters. Impact: BAM, CRACK, WHAM, SLAM Motion: WHOOSH, SWOOSH, DASH Emotional: THUMP (heartbeat), BA-DMP, SQUEEZE Ambient: drip, creak, rustle, click Style the SFX with: color matching mood, perspective following action direction, slight 3D depth/shadow. Emotion effects (manhwa-specific): - Blush: horizontal lines across cheeks + nose - Shock: vertical dark lines over face, white/empty eyes - Anger: cross-shaped vein mark, dark aura - Sparkle: floating diamond shapes around character (admiration/beauty moment) - Flowers/petals: background dissolution into floral pattern (romantic peak) - Sweat drop: exaggerated single drop on temple (awkwardness) - Dark aura/shadow: character emanating darkness (menace/jealousy) Panel borders: clean black lines, 2-3px weight. Borderless for emphasis — character breaking through panel edge = power/emotion overflow. Diagonal panel cuts for action sequences. Overlapping panels for simultaneous events or rapid pacing. Gutters: narrow white space (consistent width) between panels. MOOD-MATCHED PAGE COMPOSITION TENDER / ROMANTIC: 4 panels. Soft lighting, warm palette. Close-ups of eyes meeting, hands almost touching, gentle smiles. Floating petals or sparkles. Pastel background dissolve. TENSE / CONFRONTATION: 3-4 panels. Dutch angles, dramatic shadows. Tight close-ups of narrowed eyes, clenched jaws. Dark palette with selective color highlights. Speed line backgrounds. ACTION / FIGHT: 3 panels. One massive splash with motion blur + impact SFX. Two tight reaction shots. High contrast, dynamic poses, panel border breaks. COMEDIC: 4 panels. Chibi-adjacent expressions (but keep proportions), exaggerated reactions, sweat drops, blank stare panels. Lighter line weight, brighter colors. MELANCHOLIC: 3 panels. Silhouette panel + desaturated close-up + detail insert (tear, clenched hand, empty space). Cool blue palette, rain overlay, minimal SFX. REVEAL / CLIFFHANGER: 2-3 panels. Build with medium shots → full-page splash reveal. Dramatic lighting shift. Character emerging from shadow/door/crowd. Subject rotation across messages: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. SENSUAL PROTOCOL (manhwa version) Intimate scenes: artistic concealment through panel composition. Panel techniques for intimate moments: - Strategic cropping: cut at collarbone, show only shoulders up - Fabric interaction: sheets, curtains, clothing slipping - Shadow play: deep shadows across bodies, only faces lit - Detail panels: intertwined fingers, lips nearly touching, pulse point on neck - Background dissolution: characters surrounded by abstract flowers/light Vocabulary: bare shoulders → 'fabric pooling at elbows'. Closeness → 'foreheads touching, sharing breath'. Intensity → 'heavy-lidded gaze, flushed cheeks, parted lips'. Lying down → 'among rumpled sheets, one arm above head'. PROMPT FORMAT Total prompt: 80-130 words (excluding style suffix). Describe panels in order: 'Panel 1: [type, camera] — [character] [outfit] [action] [expression] [comic element]. | Panel 2: [type, camera] — [description]. | Panel 3: [type, camera] — [description]. | Panel 4: [type, camera] — [description].' Each panel: 20-35 words. Include at least one speech bubble or SFX per page. STYLE SUFFIX (append verbatim to end of every prompt): 'Korean webtoon manhwa style, vertical scroll comic page. Clean confident digital lineart with varied line weight. Soft cel-shading with smooth gradient shadows. Luminous skin with subtle blush on cheeks, nose, ears. Large expressive eyes with multi-layered iris reflections and catchlights. Sleek hair with strand highlights. White speech bubbles with directional tails, integrated SFX onomatopoeia, manhwa emotion effects. Panel borders with white gutters, borderless bleeds for emphasis. Vibrant saturated palette with mood-shifted color temperature between panels. Anatomically correct hands and proportions, five fingers per visible hand. Match character appearance from reference images.' NEGATIVE (append verbatim after style suffix): 'Avoid: western comic style, Marvel/DC aesthetic, thick uniform outlines, halftone dots, photorealistic rendering, 3D CGI, anime chibi proportions, super-deformed, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, blurry, text outside speech bubbles, multiple art styles on same page, Korean Hangul characters, Korean text, non-English text in speech bubbles or SFX' MULTI-CHARACTER PANELS Each character is one clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning: 'behind Denis', 'facing Liza', 'grabbing Ethan arm'. Repeat names — never use pronouns when two+ characters share a panel. NPC NAMING: first name only. Names map to reference images. 'Ethan' not 'Ethan Chen'. If NPC has no reference, describe appearance briefly once in first panel they appear. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Manhwa chapter-title style. Short, evocative, lowercase italic. Not what is visible — what it means emotionally. 'the silence before the storm' | 'twenty past never' | 'a crack in the mask' TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"manhwa_webtoon","prompt":"[PANELS DESCRIBED IN ORDER: Panel 1: type, camera — desc. | Panel 2: type, camera — desc. | Panel 3: type, camera — desc. | Panel 4: type, camera — desc. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. Default aspect_ratio: '2:3' (vertical webtoon page). Use '9:16' for tall dramatic pages with 2-3 panels, '3:4' for compact 4-panel pages. image_size: '2K' default. Use '4K' for splash-heavy pages with fine detail. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text — use single quotes. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> MANHWA-STYLE COMIC PAGE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Korean webtoon / manhwa digital illustration. Clean lineart with confident varied line weight. Soft cel-shading with gradient shadows. Luminous skin rendering with subtle blush on cheeks and nose. Large expressive eyes with detailed iris reflections. Sleek hair with individual strand highlights. Flat color backgrounds with occasional painted detail panels. Speed lines for motion. Screen tones for mood. COLOR: Vibrant saturated palette. Warm skin tones. Color shifts between panels to mark mood (warm = comfort, cool = tension, desaturated = sadness). Occasional monochrome panel for flashback/shock. PAGE LAYOUT Each page = 3-4 panels arranged vertically (webtoon scroll format). Vary panel count by scene energy: - Dialogue/calm: 4 panels (talking heads, reactions, environment) - Action/tension: 3 panels (wide impact shot + 2 reactions) - Climax/reveal: 2-3 panels (one dominant splash + close-ups) Panel types to rotate between: SPLASH — full-width dramatic moment, detailed background CLOSE-UP — face/eyes only, emotion focus, minimal background MEDIUM — waist-up, character interaction, speech context DETAIL — hands, objects, symbolic items (phone screen, clenched fist, tears) OVER-SHOULDER — one character watching another, depth layering CAMERA PER PANEL Each panel gets its own shot type: splash=wide 24-35mm | close-up=85-135mm | medium=50-85mm | detail=macro. Vary across panels. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. COMIC ELEMENTS - Speech bubbles: white rounded rectangles with black text, tail pointing to speaker - Thought bubbles: cloud-shaped, lighter text - SFX text: stylized manga onomatopoeia rendered as part of the art in ENGLISH only (BAM, CRACK, WHOOSH, THUMP, SLAM, drip, rustle) — integrated into panel, not floating. Never use Korean Hangul characters. - Emotion effects: blush lines, sweat drops, shock lines, sparkles, dark aura, flowers (shoujo moments) - Panel borders: clean black lines. Borderless panels for emphasis/bleeds. - Gutters: narrow white space between panels HOW TO BUILD THE PROMPT Describe each panel in order, separated by ' | ': 'Panel 1: [type] — [description]. Panel 2: [type] — [description]. Panel 3: [type] — [description].' Each panel description includes: shot type + character + outfit + pose + expression + environment + lighting. Each panel description: 15-25 words. Total prompt: 60-100 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Korean webtoon manhwa style. Clean digital lineart, soft cel-shading, gradient shadows, luminous skin, large expressive eyes with iris detail, sleek highlighted hair. White speech bubbles with tails, integrated SFX text, emotion effects. Vertical scroll layout, panel borders with white gutters. Vibrant saturated colors, mood-shifted palette between panels. Anatomically correct hands, five fingers.' NEGATIVE (append verbatim): 'Avoid: western comic style, Marvel/DC aesthetic, thick outlines, halftone dots, photorealistic, 3D render, anime chibi, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text outside bubbles, blurry, Korean Hangul characters, Korean text, non-English text in speech bubbles or SFX' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"manhwa_webtoon","prompt":"[PANELS DESCRIBED IN ORDER, SEPARATED BY |. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Korean webtoon manhwa style, vertical scroll comic page. Clean confident digital lineart with varied line weight. Soft cel-shading with smooth gradient shadows. Luminous skin with subtle blush on cheeks, nose, ears. Large expressive eyes with multi-layered iris reflections and catchlights. Sleek hair with strand highlights. White speech bubbles with directional tails, integrated SFX onomatopoeia, manhwa emotion effects. Panel borders with white gutters, borderless bleeds for emphasis. Vibrant saturated palette with mood-shifted color temperature between panels. Anatomically correct hands and proportions, five fingers per visible hand. Match character appearance from reference images. Avoid: western comic style, Marvel/DC aesthetic, thick uniform outlines, halftone dots, photorealistic rendering, 3D CGI, anime chibi proportions, super-deformed, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, blurry, text outside speech bubbles, multiple art styles on same page, Korean Hangul characters, Korean text, non-English text in speech bubbles or SFX

Копировать [Image generation hint, STYLE: Korean webtoon vertical scroll format, clean digital lineart, soft cel-shading, luminous skin, large expressive eyes, vibrant saturated colours with mood-shifted palettes between panels]

Chibi Manhwa

Манхва-база с чиби-вставками, спич-баблами, спид-лайнами, скринтонами. Комедийные моменты деформации в формате вебтуна.

Стабильный Аниме и манга

←→

Длинный~5453 Короткий~2600 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> MANHWA-STYLE COMIC PAGE WITH CHIBI INSERTS — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → manhwa page → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One vertical comic page per message at the most visually dramatic or emotionally charged moment. PAGE LAYOUT SYSTEM Each page = 3-4 panels arranged vertically (Korean webtoon scroll format). Panel count adapts to scene energy: - Quiet dialogue / slice of life: 4 panels (talking heads, reactions, environment establishing shot, detail insert) - Tension / confrontation: 3-4 panels (medium shots with intense expressions, dramatic angles, SFX-heavy) - Action / chase / fight: 3 panels (one wide impact splash + two tight reaction close-ups) - Emotional climax / reveal: 2-3 panels (dominant splash panel taking 50%+ of page + supporting close-ups) - Romantic / intimate: 3-4 panels (close-ups of eyes, hands, lips + atmosphere panel with visual noise) - Comedic peak: 3-4 panels with at least one CHIBI INSERT replacing or overlapping a standard panel CAMERA PER PANEL: each panel gets its own shot type and implicit lens choice. Vary across panels: splash panels = wide 24-35mm | close-up panels = 85-135mm | medium panels = 50-85mm | detail panels = macro. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Match camera to panel type for maximum compositional variety across the page. PANEL TYPES — rotate between these across pages: SPLASH — full-width, most detailed. Background fully rendered. Character(s) in dynamic pose. Wide 24-35mm lens feel. Used for: entrances, reveals, emotional peaks, environment establishing. CLOSE-UP — face or eyes only. 85-135mm compressed lens feel. Emotion is everything. Background = flat color, gradient, or speed lines. Show: pupil dilation, tear tracks, blush, micro-expressions, lip movement. MEDIUM SHOT — waist-up or chest-up. 50-85mm natural lens feel. Primary dialogue panel. Show: hand gestures, outfit details, body language, speech bubble placement space. DETAIL INSERT — small panel. Macro lens feel. Hands gripping something, phone screen, dropped object, tears hitting floor, fingers intertwining. Symbolic weight. OVER-SHOULDER — one character in foreground (back/shoulder visible), other character facing camera in background. 50mm natural perspective. Creates depth and voyeuristic tension. DUTCH ANGLE — tilted panel for disorientation, danger, psychological pressure. Any lens, tilted 15-30 degrees. SILHOUETTE — character as dark shape against bright/colored background. Wide lens for full body, medium for partial. For dramatic entrances or lonely moments. CHIBI INSERT — floating inset or corner panel: super-deformed character with big head (2:1 ratio), tiny body, nubby limbs, enormous shining eyes. Used for: comedic shock, inner screaming, flustered reactions, embarrassed inner monologue, over-the-top cuteness. Always paired with a speech bubble, thought bubble, or drawn emotion symbol. Soft rounded lineart, lighter pastel fill, dot-screentone background. Can overlap adjacent panel borders. Vary panel shapes: standard rectangles, borderless bleeds (character breaks panel edge), diagonal cuts for action, overlapping panels for simultaneous events. HOW TO BUILD THE PROMPT Describe each panel sequentially. Use ' | ' to separate panels. For each panel specify: 1. PANEL TYPE + CAMERA (splash wide 24mm / close-up 85mm / medium 50mm / detail macro / over-shoulder / dutch angle / silhouette / chibi insert) 2. CHARACTER(S) — first name only. Names map to reference images. 3. OUTFIT — carry forward from narrative. Fabric + fit + color + condition. Never skip. 4. POSE/ACTION — what the character is doing in this exact frame 5. EXPRESSION — specific emotion with physical detail (furrowed brows, parted lips, narrowed eyes) 6. COMIC ELEMENTS — speech bubble content or SFX text or drawn emotion 7. CHIBI NOTE (if applicable) — 'CHIBI INSERT [position]: [character] chibi [action] [expression] [bubble/symbol]' CHARACTER RULES First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Reference images handle base appearance. Skip in prompt: hair color, style, length, eye color, skin tone, face shape, build, body type. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back', 'windswept') — not base color or style. Men described as tall/strong/broad-shouldered/athletic in story → prefix 'tall broad-shouldered, strongly built' before name. Never downgrade men who are described as big or muscular into slim or androgynous builds. All characters look attractive — this is a romance story. OUTFIT (MANDATORY — context-locked): Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/NPC is wearing RIGHT NOW. Priority: 1) Current message clothing. 2) Recent messages carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate. Specificity: fabric type + texture + fit + color + drape + condition (wrinkled, soaked, unbuttoned, rolled sleeves). If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. HAND SAFETY: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character per panel = safest output. 'Anatomically correct proportions, five fingers per visible hand.' MANHWA ART STYLE Rendering: Clean digital lineart with confident varied line weight — thicker on outlines, thinner on interior details. Soft cel-shading with smooth gradient shadows (not hard-edge anime). Luminous skin rendering with subtle warm blush on cheeks, nose tip, ears, and knuckles. Large expressive eyes with detailed multi-layered iris reflections and catchlights. Sleek hair with individual strand highlights and volume shading. Color: Vibrant saturated palette as base. Color temperature shifts between panels to mark mood: - Warm orange/pink = comfort, romance, nostalgia - Cool blue/purple = tension, distance, melancholy - Desaturated/grey = shock, numbness, flashback - High contrast red/black = danger, anger, passion - Soft pastels + sparkles = shoujo romantic moments Backgrounds: Flat color or gradient for dialogue panels. Painted detail for establishing shots. Speed lines radiating from impact point for action. Floating particles (petals, snow, embers, dust) for atmosphere. SPEED LINES: - Radial speed lines bursting from focal point — for impact hits, shocking reveals, emotional peak - Parallel horizontal/diagonal lines — for dashing motion, forward charge - Concentric arc lines — for heartbeat pulse, approaching footstep tension - Speed lines integrated INTO art layer (not floating over): colored to match mood, fading at edges SCREENTONES: - Fine dot screentone overlay on character shadow regions — classic manga depth - Coarse halftone dot bloom on warm background behind blushing character - Diagonal line screentone on background for melancholy, flashback, or interior thought panels - Dark vignette screentone at panel edges for dread/tension build - Sparkle screentone burst (star-shaped dot clusters) for romantic/admiration panels - Screentone always rendered as part of the art, not floating filter COMIC-SPECIFIC ELEMENTS SPEECH BUBBLES (mandatory — always include at least one per page): - Standard dialogue: white rounded rectangle, clean black text, directional tail to speaker - Shouting: jagged spiky irregular border, bold larger text - Whispering: dashed oval outline, smaller italic text - Trembling/scared: wobble-edged bubble, quivering text - Narrator/caption box: rectangular flat-color box at top or bottom of panel, italic text - Thought bubble: linked cloud ovals leading to character head, lighter italic text inside DRAWN EMOTION SYMBOLS IN/AROUND BUBBLES: - Small drawn manga symbol INSIDE bubble alongside text OR floating near tail: * Drawn vein mark = frustration/anger (render as drawn cross-shaped vein, NOT emoji) * Drawn sweat drop = awkwardness (render as large teardrop with shine) * Drawn heart = affection/fondness * Drawn ellipsis '...' cloud = hesitation/speechless * Drawn lightning bolt = surprise/shock * Drawn musical note = singing/humming/lighthearted mood * Drawn skull = horror/extreme reaction (comedic) * Drawn question mark = confusion (loopy drawn style) - These are DRAWN as part of the artwork line art, not Unicode glyphs CHIBI INSERT (details): - Position options: corner overlap, floating inset between panels, replacing a small panel entirely - Proportions: head takes 60% of figure height, round soft facial features, dot-highlight eyes - Lineart: thinner softer lines than main panels, rounded corners everywhere - Color: slightly desaturated pastel version of character's palette - Background: fine dot screentone or solid pastel color - Always has: speech bubble (standard or thought) with drawn emotion symbol inside - Triggers: flustered blush overload, comedic inner scream, disbelief reaction, over-the-top embarrassment, secret heart-eyes moment SFX onomatopoeia: stylized large text integrated INTO the artwork, not floating separate. ENGLISH ONLY — never use Korean Hangul characters. Impact: BAM, CRACK, WHAM, SLAM Motion: WHOOSH, SWOOSH, DASH Emotional: THUMP (heartbeat), BA-DMP, SQUEEZE Ambient: drip, creak, rustle, click Style: color matching mood, perspective following action direction, 3D depth/shadow. Emotion effects (manhwa-specific): - Blush: horizontal lines across cheeks + nose - Shock: vertical dark lines over face, white/empty eyes - Anger: cross-shaped vein mark, dark aura - Sparkle: floating diamond shapes (admiration/beauty) - Flowers/petals: background dissolution into floral (romantic peak) - Sweat drop: exaggerated single drop on temple - Dark aura: character emanating darkness (menace/jealousy) Panel borders: clean black lines, 2-3px weight. Borderless for emphasis — character breaking through panel edge = power/emotion overflow. Diagonal panel cuts for action. Overlapping panels for simultaneous events. Gutters: narrow white space (consistent width) between panels. MOOD-MATCHED PAGE COMPOSITION TENDER / ROMANTIC: 4 panels. Soft lighting, warm palette. Close-ups of eyes meeting, hands almost touching, gentle smiles. Floating petals or sparkles. Pastel background dissolve. Sparkle screentone burst behind character. TENSE / CONFRONTATION: 3-4 panels. Dutch angles, dramatic shadows. Tight close-ups of narrowed eyes, clenched jaws. Dark palette with selective color highlights. Radial speed lines. Dark vignette screentone. ACTION / FIGHT: 3 panels. One massive splash with motion blur + impact SFX. Two tight reaction shots. High contrast, dynamic poses, panel border breaks. Radial speed lines from impact. COMEDIC: 4 panels. At least one CHIBI INSERT. Exaggerated reactions, sweat drops, blank stare panels. Lighter line weight, brighter colors. Dot screentone on blush panels. MELANCHOLIC: 3 panels. Silhouette panel + desaturated close-up + detail insert (tear, clenched hand, empty space). Cool blue palette, rain overlay, diagonal line screentone. REVEAL / CLIFFHANGER: 2-3 panels. Build with medium shots → full-page splash reveal. Dramatic lighting shift. Radial speed lines from reveal point. Subject rotation across messages: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. SENSUAL PROTOCOL (manhwa version) Intimate scenes: artistic concealment through panel composition. Panel techniques for intimate moments: - Strategic cropping: cut at collarbone, show only shoulders up - Fabric interaction: sheets, curtains, clothing slipping - Shadow play: deep shadows across bodies, only faces lit - Detail panels: intertwined fingers, lips nearly touching, pulse point on neck - Background dissolution: characters surrounded by abstract flowers/light - Screentone bloom: soft dot halftone fills the background warm PROMPT FORMAT Total prompt: 90-140 words (excluding style suffix). Describe panels in order: 'Panel 1: [type, camera] — [character] [outfit] [action] [expression] [comic element]. | Panel 2: [type, camera] — [description]. | Panel 3: [type, camera] — [description]. | Panel 4: [type, camera] — [description].' For chibi insert, append inline: '+ CHIBI INSERT [corner/position]: [name] chibi [pose] [expression], bubble: [text], drawn [emotion symbol].' Each panel: 20-40 words. Include at least one speech bubble AND one SFX or drawn emotion per page. STYLE SUFFIX (append verbatim to end of every prompt): 'Korean webtoon manhwa style, vertical scroll comic page. Clean confident digital lineart with varied line weight. Soft cel-shading with smooth gradient shadows. Luminous skin with subtle blush on cheeks, nose, ears. Large expressive eyes with multi-layered iris reflections and catchlights. Sleek hair with strand highlights. White rounded speech bubbles with directional tails, jagged shout bubbles, cloud thought bubbles, drawn manga emotion symbols inside bubbles (drawn vein, sweat drop, heart, lightning, ellipsis cloud). Stylized SFX onomatopoeia integrated into art with 3D depth and color-matched shadows. Radial and parallel speed lines for motion and impact. Dot screentone, diagonal line screentone, and sparkle screentone overlays for mood and depth. Chibi super-deformed insert panels with soft rounded lineart, pastel fill, dot-screentone background, and big sparkle eyes. Manhwa emotion effects (blush lines, shock lines, vein marks, dark aura, sparkle diamonds, flower petals). Panel borders with white gutters, borderless bleeds for emphasis, diagonal cuts for action. Vibrant saturated palette with mood-shifted color temperature between panels. Anatomically correct hands and proportions, five fingers per visible hand. Match character appearance from reference images.' NEGATIVE (append verbatim after style suffix): 'Avoid: western comic style, Marvel/DC aesthetic, thick uniform outlines, halftone printing artifacts unintentional, photorealistic rendering, 3D CGI, inconsistent art style between panels, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, blurry, text outside speech bubbles, floating unattached speech bubbles, emoji glyphs replacing drawn symbols, chibi proportions bleeding into main panels, Korean Hangul characters, Korean text, non-English text in speech bubbles or SFX' MULTI-CHARACTER PANELS Each character is one clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning: 'behind Denis', 'facing Liza', 'grabbing Ethan arm'. Repeat names — never use pronouns when two+ characters share a panel. NPC NAMING: first name only. Names map to reference images. 'Ethan' not 'Ethan Chen'. If NPC has no reference, describe appearance briefly once in first panel they appear. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Manhwa chapter-title style. Short, evocative, lowercase italic. Not what is visible — what it means emotionally. 'the silence before the storm' | 'twenty past never' | 'a crack in the mask' TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"manhwa_webtoon","prompt":"[PANELS DESCRIBED IN ORDER: Panel 1: type, camera — desc. | Panel 2: type, camera — desc. | Panel 3: type, camera — desc. | Panel 4: type, camera — desc. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. Default aspect_ratio: '2:3' (vertical webtoon page). Use '9:16' for tall dramatic pages with 2-3 panels, '3:4' for compact 4-panel pages. image_size: '2K' default. Use '4K' for splash-heavy pages with fine detail. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text — use single quotes. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> MANHWA-STYLE COMIC PAGE WITH CHIBI INSERTS — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Korean webtoon / manhwa digital illustration. Clean lineart with confident varied line weight. Soft cel-shading with gradient shadows. Luminous skin rendering with subtle blush on cheeks and nose. Large expressive eyes with detailed iris reflections. Sleek hair with individual strand highlights. Flat color backgrounds with occasional painted detail panels. SPEED LINES — radial speed lines from focal point for impact, motion, or emotional shock. Straight parallel lines for charging/dashing. Concentric arc lines for pulse/heartbeat beats. SCREENTONES — overlaid dot-pattern or diagonal-line screentone shading: - Fine dot screentone on character shadows for classic manga depth - Coarse halftone on emotional bloom panels (warm blush background) - Diagonal line screentone on background for melancholy/flashback panels - Dark screentone vignette at panel edges for tension COLOR: Vibrant saturated palette. Warm skin tones. Color shifts between panels to mark mood (warm = comfort, cool = tension, desaturated = sadness). Occasional monochrome panel for flashback/shock. PAGE LAYOUT Each page = 3-4 panels arranged vertically (webtoon scroll format). Vary panel count by scene energy: - Dialogue/calm: 4 panels (talking heads, reactions, environment) - Action/tension: 3 panels (wide impact shot + 2 reactions) - Climax/reveal: 2-3 panels (one dominant splash + close-ups) Panel types to rotate between: SPLASH — full-width dramatic moment, detailed background CLOSE-UP — face/eyes only, emotion focus, minimal background MEDIUM — waist-up, character interaction, speech context DETAIL — hands, objects, symbolic items (phone screen, clenched fist, tears) OVER-SHOULDER — one character watching another, depth layering CHIBI INSERT — small corner or floating chibi panel: super-deformed character reaction (big head, tiny body, exaggerated emotion). Used for: comedic relief, flustered moments, shock, embarrassment, inner monologue. Always has rounded soft lineart and big sparkle eyes. CAMERA PER PANEL Each panel gets its own shot type: splash=wide 24-35mm | close-up=85-135mm | medium=50-85mm | detail=macro. Vary across panels. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. COMIC ELEMENTS SPEECH BUBBLES: - Standard: white rounded rectangle, black clean text, directional tail pointing to speaker. Keep dialogue SHORT (5-10 words max per bubble). - Shouting: jagged spiky border, bold larger text. - Whispering: dashed oval border, smaller italic text. - System/narrator: rectangular box with flat color background, top of panel. - Thought bubble: cloud-shaped linked ovals leading to character head, lighter italic text inside. DRAWN EMOTIONS IN/AROUND BUBBLES: - Draw a tiny emotion icon INSIDE the bubble alongside text: vein for anger, sweat drop for awkwardness, heart for affection, ? for confusion, lightning for shock — rendered as drawn manga symbols, not emoji. - Chibi reaction insert OVERLAPPING the bubble or in adjacent corner when emotion peaks. SFX TEXT: stylized manga onomatopoeia in ENGLISH ONLY rendered as part of the art (BAM, CRACK, WHOOSH, THUMP, BA-DMP, rustle, drip, click) — integrated into panel, 3D depth/shadow, color-matched to mood, not floating. Never use Korean Hangul characters. EMOTION EFFECTS (manhwa-specific): - Blush lines: horizontal lines across cheeks + nose - Shock lines: vertical dark lines over face, white/empty eyes - Anger: cross-shaped vein mark, dark aura - Sparkle: floating diamonds (admiration/beauty) - Flowers/petals: background dissolution into floral (romantic peak) - Dark aura: character emanating darkness (menace/jealousy) CHIBI INSERT rules: - Size: occupies small corner segment or floats as inset panel (roughly 1/5 page width) - Trigger: comedic shock, flustered reaction, inner scream, over-the-top embarrassment - Style: big round head (2:1 ratio), tiny body with nubby limbs, enormous eyes, exaggerated blush/sweat/tears - Always include a speech/thought bubble or drawn emotion symbol WITH the chibi - Soft rounded lineart, lighter pastel color fill, screentone dot background behind chibi Panel borders: clean black lines. Borderless panels for emphasis/bleeds. Diagonal cuts for action. Gutters: narrow white space between panels. HOW TO BUILD THE PROMPT Describe each panel in order, separated by ' | ': 'Panel 1: [type] — [description]. | Panel 2: [type] — [description]. | Panel 3: [type] — [description].' Add chibi insert note inline: 'Panel 2: MEDIUM — [...] + CHIBI INSERT bottom-right corner: [character] chibi [action/expression] [bubble content].' Each panel description includes: shot type + character + outfit + pose + expression + environment + lighting. Each panel description: 15-30 words. Total prompt: 70-110 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Korean webtoon manhwa style. Clean digital lineart, soft cel-shading, gradient shadows, luminous skin, large expressive eyes with iris detail, sleek highlighted hair. White speech bubbles with directional tails, jagged shout bubbles, cloud thought bubbles, drawn emotion symbols inside bubbles. Integrated SFX onomatopoeia with 3D depth. Radial speed lines for impact. Dot and diagonal screentone overlays for mood shading. Chibi super-deformed insert panels with rounded soft lineart and pastel fill. Manhwa emotion effects (blush lines, shock lines, sparkles, dark aura, petals). Vertical scroll layout, panel borders with white gutters, borderless bleeds for emphasis. Vibrant saturated colors, mood-shifted palette between panels. Anatomically correct hands, five fingers.' NEGATIVE (append verbatim): 'Avoid: western comic style, Marvel/DC aesthetic, thick uniform outlines, halftone printing artifacts, photorealistic, 3D render, text outside speech bubbles, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, inconsistent art style between panels, floating unattached speech bubbles, Korean Hangul characters, Korean text, non-English text in speech bubbles or SFX' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"manhwa_webtoon","prompt":"[PANELS DESCRIBED IN ORDER, SEPARATED BY |. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Korean webtoon manhwa style, vertical scroll comic page. Clean confident digital lineart with varied line weight. Soft cel-shading with smooth gradient shadows. Luminous skin with subtle blush on cheeks, nose, ears. Large expressive eyes with multi-layered iris reflections and catchlights. Sleek hair with strand highlights. White rounded speech bubbles with directional tails, jagged shout bubbles, cloud thought bubbles, drawn manga emotion symbols inside bubbles (drawn vein, sweat drop, heart, lightning, ellipsis cloud). Stylized SFX onomatopoeia integrated into art with 3D depth and color-matched shadows. Radial and parallel speed lines for motion and impact. Dot screentone, diagonal line screentone, and sparkle screentone overlays for mood and depth. Chibi super-deformed insert panels with soft rounded lineart, pastel fill, dot-screentone background, and big sparkle eyes. Manhwa emotion effects (blush lines, shock lines, vein marks, dark aura, sparkle diamonds, flower petals). Panel borders with white gutters, borderless bleeds for emphasis, diagonal cuts for action. Vibrant saturated palette with mood-shifted color temperature between panels. Anatomically correct hands and proportions, five fingers per visible hand. Match character appearance from reference images. Avoid: western comic style, Marvel/DC aesthetic, thick uniform outlines, halftone printing artifacts unintentional, photorealistic rendering, 3D CGI, inconsistent art style between panels, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, blurry, text outside speech bubbles, floating unattached speech bubbles, emoji glyphs replacing drawn symbols, chibi proportions bleeding into main panels, Korean Hangul characters, Korean text, non-English text in speech bubbles or SFX

Копировать [Image generation hint, STYLE: manhwa base with chibi reaction inserts, speech bubbles, speed lines, screentones, comedic manga-style deformation moments within the webtoon format]

Manga (B&W)

Чёрно-белая манга. Чёрная тушь на белой бумаге — БЕЗ цвета. Скринтоны для теней, спид-лайны, фокус-лайны. 3-4 панели на странице. SFX только на английском.

Экспериментальный Аниме и манга

←→

Длинный~3572 Короткий~1946 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> BLACK & WHITE MANGA PAGE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One vertical manga page per message at the most dramatic beat. Insert after an emotional peak — never at the very end. STYLE OVERVIEW Black and white Japanese manga page — professional tankobon print quality. Pure black ink on white paper. NO colour whatsoever. The complete visual vocabulary of manga: screentones, speed lines, focus lines, heavy blacks, white space, panel composition as storytelling. INK SYSTEM: - Pure black ink lines: confident, variable weight. Thick outer silhouettes + dramatic emphasis. Thin interior detail + expression lines. - NO grey paint or watercolour. ALL mid-tones are screentone dot patterns — regular grids of black dots at varying densities printed on adhesive sheets. Dense dots = dark grey. Sparse dots = light grey. - Heavy solid black fills: hair mass, dramatic shadow, night sky, dark clothing. These large black shapes are compositional anchors. - White space: negative space is not empty — it is compositional. White = silence, breath, peace, clarity. The ratio of black to white on the page IS the emotional temperature. - Hatching: parallel ink lines for surface texture. Cross-hatch = rough/dark. Single-direction = smooth/subtle. MANGA VISUAL EFFECTS — THE FULL VOCABULARY: SPEED LINES (動線): Parallel lines indicating motion direction. Horizontal behind running figure. Diagonal for falling/swooping. Short burst lines radiating from impact point. FOCUS LINES / CONCENTRATION LINES (集中線): Lines radiating inward toward a focal point — converging on a face, an object, a revelation. Creates tunnel-vision emphasis. The manga equivalent of a dramatic zoom. SCREENTONE GRADIENT: Dot pattern transitioning from dense to sparse within a single area. Used for: emotional transition, atmospheric depth, soft lighting, blush/flush on cheeks, fading distance. HEAVY BLACK PANEL: Entire panel flooded with solid black ink. Figure emerges as white negative space or minimal white linework on black. Used for: extreme drama, horror, despair, the moment before something breaks. WHITE-OUT / BLANK PANEL: Panel nearly empty — white with minimal linework, maybe a single floating element. Used for: shock silence, dissociation, peace after storm, the breath before realization hits. SHATTERED PANEL BORDERS: Panel frames cracking, breaking, or fragmenting outward. Used for: emotional overwhelm, a character breaking down, a moment that can't be contained by the page. BORDERLESS BLEED: Image extends to the page edge with no panel frame. Used for: epic moments, emotional flooding, moments that are bigger than the page can hold. DIAGONAL PANEL CUT: Panel border angled diagonally across the page. Used for: dynamic action, instability, transition between emotional states. EMOTIONAL SCREENTONE OVERLAY: Dark screentone covering a character's face from the eyes up. Used for: hidden emotions, dark thoughts, quiet anger, internal storm. The classic "manga shadow over the eyes." PAGE LAYOUT — 3-4 PANELS PER PAGE Vary panel count by scene energy: - Dialogue / calm: 4 panels (talking heads, reaction shots, establishing environment, quiet beat) - Action / tension: 3 panels (wide impact shot + 2 reaction close-ups) - Climax / revelation: 2-3 panels (one dominant splash panel + supporting close-ups) - Emotional overwhelm: 2 panels (one massive + one tiny) or single full-page Panel types to rotate between: SPLASH — full-width dramatic moment. Detailed background. Character in full pose. The "money shot." CLOSE-UP — face or eyes only. Maximum emotion. Background dissolved into screentone or speed lines. MEDIUM — waist-up. Character interaction. Enough body language to read the scene. DETAIL — hands, objects, symbolic items (a phone screen, clenched fist, single tear, discarded item). These tiny panels carry huge narrative weight. OVER-SHOULDER — one character in foreground silhouette, another facing camera. Creates depth and conversational tension. REACTION — small panel showing a character's face responding to the previous panel's event. PANEL FLOW: manga reads RIGHT TO LEFT. Panels flow R→L, top→bottom. The eye moves in Z-pattern from upper-right to lower-left. CHARACTER RULES First name only — names map to reference images. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. In manga B&W, hair becomes a black or white mass, skin becomes white paper + screentone. Include every time: distinguishing marks (tattoos with location/design, scars, piercings). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT (MANDATORY — context-locked): scan last 5 messages. Never skip. Specificity: fabric type + fit + pattern description (since there's no colour, describe the VALUE — dark/light/patterned). 'Dark heavy coat' = solid black ink fill. 'Light blouse' = white with screentone shadow only. Fuse into panel description. POSE AND STATE: describe through action. Hand safety: gripping object | arms crossed | fist at side | hand on own neck | hand braced on surface. One visible relaxed hand per character = safest. 'Anatomically correct proportions, five fingers per visible hand.' MANGA EXPRESSIONS — the full emotional range in ink: - Shock: wide eyes, speed line background, screentone dropped - Anger: heavy brow, teeth visible, dark screentone over eyes from above, focus lines - Sadness: downcast eyes, single tear track (white line on screentone cheek), white-out background - Tenderness: soft eyes, minimal linework, light screentone blush, clean white space - Menace: eyes in shadow (dark screentone from brow up), smile visible below, heavy blacks around panel - Determination: strong jaw, direct gaze, speed lines radiating behind head CAMERA PER PANEL: each panel gets its own implicit "shot": Splash panels = wide 24-35mm equivalent | close-up panels = 85-135mm | medium panels = 50-85mm | detail panels = macro Vary across panels for visual rhythm. COMIC ELEMENTS - Speech bubbles: white rounded rectangles with black text, tail pointing to speaker. ENGLISH ONLY. - Thought bubbles: cloud-shaped, lighter line weight, smaller text. - SFX text: stylized onomatopoeia rendered as part of the art in ENGLISH ONLY (BAM, CRACK, WHOOSH, THUMP, drip, rustle). Integrated into panel composition. - Panel borders: clean black lines. Variable thickness — thicker for emphasis panels. - Gutters: narrow white space between panels. HOW TO BUILD THE PROMPT Describe each panel in order, separated by ' | ': 'Panel 1: [type] — [description + which manga effect]. | Panel 2: [type] — [description + effect]. | Panel 3: [type] — [description + effect].' Each panel description: 15-25 words. Name character, action, expression, background treatment, which manga visual effect applies. Total prompt: 60-100 words + style suffix. STYLE SUFFIX (append verbatim): 'Black and white Japanese manga SINGLE PAGE — one page only, NOT a two-page spread. Pure black ink on white paper — NO colour, NO greyscale painting, NO watercolour wash. All shading exclusively through screentone dot patterns and ink hatching — never smooth grey gradients. Variable-weight confident ink linework: thick on silhouettes and drama, thin on detail. Professional tankobon print quality. Panels fill the FULL page width with minimal side margins — no wide empty borders on left or right edges of the page. Full manga visual effects vocabulary: speed lines, focus lines, screentone gradients, heavy solid black ink fills, emotional screentone overlays. Single vertical page with 3-4 panels, clean panel borders with narrow white gutters. Expressive manga faces. ALL text in ENGLISH LATIN ALPHABET ONLY — speech bubbles in English, ALL sound effects and onomatopoeia written in English letters (SPLASH, CRACK, BOOM, THUD, WHOOSH, DRIP, CLANG) never in Japanese katakana characters. No colour, no grey painting.' NEGATIVE (append verbatim): 'Avoid: two-page spread, wide side margins, Japanese katakana sound effects, Japanese SFX characters, any Japanese hiragana or katakana or kanji characters anywhere in image, any non-Latin-alphabet characters or text, colour, greyscale painting, watercolour wash, smooth grey gradients, grey ink wash, photorealistic rendering, 3D CGI, western comic colouring, western comic halftone, manhwa digital colour style, anime cel-shading with colour, painterly brushwork, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark' MULTI-CHARACTER SCENES Each character described within their panel. Use relational positioning ('behind Mor', 'facing Shannon'). Repeat names instead of pronouns. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Short atmospheric line. Lowercase, italic. Not what's visible — what it means. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"manga_bw","prompt":"[PANELS DESCRIBED IN ORDER, SEPARATED BY |. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: '2:3' default (vertical manga page). '9:16' for tall dramatic pages. '3:4' for compact pages. image_size: '4K' always — screentone dot detail requires resolution. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> BLACK & WHITE MANGA PAGE — EVERY RESPONSE One vertical manga page per message at the most dramatic beat. Insert after an emotional peak — never at the very end. STYLE Black and white Japanese manga page — traditional tankobon print quality. NO colour. Pure black ink on white paper. The full visual vocabulary of professional manga: screentones for shading, speed lines for motion, focus lines for impact, heavy blacks for drama, white space for breath. INK TECHNIQUE: - Pure black ink lines: confident, variable weight. Thick on silhouettes and drama, thin on detail and expression. - NO grey — all mid-tones through screentone dot patterns (fine regular dot grid at varying densities). - Heavy solid black fills for dramatic shadow, hair mass, night, clothing. - White space is compositional — negative space creates breath and pacing. - Hatching: parallel ink lines for texture (cross-hatch on rough surfaces, single-direction on smooth). MANGA VISUAL EFFECTS: - SPEED LINES: parallel motion lines behind or around moving figure. Horizontal = running. Radial from center = impact/surprise. - FOCUS LINES (concentrated lines radiating toward focal point): shock, realization, dramatic emphasis. - SCREENTONE GRADIENT: dot pattern fading from dense to sparse = emotional transition, distance, atmosphere. - HEAVY BLACK PANEL: panel flooded with black ink, figure emerging in white — extreme drama, horror, despair. - WHITE-OUT: panel nearly empty white with minimal linework — silence, peace, dissociation. - SHATTERED PANEL BORDERS: borders cracking or breaking — emotional overwhelm, breaking point. - BLEED (borderless panel): image extends to page edge — epic moment, no containment. PAGE LAYOUT — 3-4 PANELS PER PAGE: Vary panel count by scene energy: - Dialogue/calm: 4 panels (talking heads, reactions, environment) - Action/tension: 3 panels (wide impact + 2 reactions) - Climax/reveal: 2-3 panels (one dominant splash + close-ups) Panel types to rotate: SPLASH — full-width dramatic moment, detailed CLOSE-UP — face/eyes, emotion focus, minimal background MEDIUM — waist-up, character interaction DETAIL — hands, objects, symbolic items (phone, clenched fist, tears) OVER-SHOULDER — depth layering, conversation CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + condition. Never skip. POSE: describe through action. Hand safety: gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. CAMERA PER PANEL: each panel gets its own shot type. Splash = wide 24-35mm | close-up = 85-135mm | medium = 50-85mm | detail = macro. Vary across panels. HOW TO BUILD THE PROMPT Describe each panel in order, separated by ' | ': 'Panel 1: [type] — [description]. | Panel 2: [type] — [description]. | Panel 3: [type] — [description].' Each panel: 15-25 words. Include which manga effect applies (speed lines, screentone, heavy blacks, focus lines). Total prompt: 60-100 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Black and white Japanese manga SINGLE PAGE — one page only, NOT a two-page spread. Pure black ink on white paper — NO colour, NO greyscale paint. All shading through screentone dot patterns and ink hatching. Variable-weight confident ink linework. Professional tankobon print quality. Panels fill the FULL page width with minimal side margins — no wide empty borders on left or right edges. Manga visual effects: speed lines for motion, focus lines for impact, screentone gradients for atmosphere, heavy solid black fills for dramatic shadow. Single vertical page with 3-4 panels, clean panel borders with narrow white gutters. Expressive manga faces. ALL text in ENGLISH LATIN ALPHABET ONLY — speech bubbles in English, ALL sound effects and onomatopoeia written in English letters (SPLASH, CRACK, BOOM, THUD, WHOOSH) never in Japanese katakana. No colour, no greytone painting, no watercolour.' NEGATIVE (append verbatim): 'Avoid: two-page spread, wide side margins, Japanese katakana sound effects, Japanese SFX characters, any Japanese hiragana or katakana or kanji characters anywhere in image, any non-Latin-alphabet text, colour, greyscale painting, watercolour wash, smooth grey gradients, photorealistic rendering, 3D CGI, western comic halftone, western comic colouring, manhwa digital colour, anime cel-shading, painterly brushwork, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Short atmospheric line. Lowercase, italic. Not what is visible — what it means. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"manga_bw","prompt":"[PANELS DESCRIBED IN ORDER, SEPARATED BY |. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: '2:3' default (vertical manga page). '9:16' for tall dramatic pages. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Black and white Japanese manga SINGLE PAGE — one page only, NOT a two-page spread. Pure black ink on white paper — NO colour, NO greyscale painting, NO watercolour wash. All shading exclusively through screentone dot patterns and ink hatching — never smooth grey gradients. Variable-weight confident ink linework: thick on silhouettes and drama, thin on detail. Professional tankobon print quality. Panels fill the FULL page width with minimal side margins — no wide empty borders on left or right edges of the page. Full manga visual effects vocabulary: speed lines, focus lines, screentone gradients, heavy solid black ink fills, emotional screentone overlays. Single vertical page with 3-4 panels, clean panel borders with narrow white gutters. Expressive manga faces. ALL text in ENGLISH LATIN ALPHABET ONLY — speech bubbles in English, ALL sound effects and onomatopoeia written in English letters (SPLASH, CRACK, BOOM, THUD, WHOOSH, DRIP, CLANG) never in Japanese katakana characters. No colour, no grey painting. Avoid: two-page spread, wide side margins, Japanese katakana sound effects, Japanese SFX characters, any Japanese hiragana or katakana or kanji characters anywhere in image, any non-Latin-alphabet characters or text, colour, greyscale painting, watercolour wash, smooth grey gradients, grey ink wash, photorealistic rendering, 3D CGI, western comic colouring, western comic halftone, manhwa digital colour style, anime cel-shading with colour, painterly brushwork, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark

Копировать [Image generation hint, STYLE: black and white Japanese manga page, pure black ink on white paper, no colour, screentone dot shading, speed lines, focus lines, heavy blacks, 3-4 panels per page, English-only SFX]

Studio Ghibli

Рисованная анимация Миядзаки. Чистые простые контуры, мягкие натуральные пропорции. Шикарные акварельные пейзажные фоны. Тёплая палитра. Ветер в волосах, траве, шторах. Чудо, тепло, благоговение перед обычным.

Стабильный Аниме и манга

←→

Длинный~3054 Короткий~1407 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — STUDIO GHIBLI HAND-DRAWN ANIMATION STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition, visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Studio Ghibli Hayao Miyazaki hand-drawn animation style. Clean simple character outlines with soft rounded naturalistic features — NOT exaggerated anime proportions. Large but grounded expressive eyes. Gorgeous painted watercolour backgrounds: lush greens, soft blue skies, detailed clouds, lived-in environments with care for mundane detail. Natural warm luminous colour palette: soft greens, earth tones, golden afternoon light. Wind movement in hair, fabric, grass, clouds. Soft cel-shading with warm shadow colours. Wonder, warmth, and reverence for the ordinary. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: exaggerated anime proportions, huge unnatural eyes, 3D CGI rendering, photorealistic, dark gritty atmosphere, cold desaturated palette, flat digital vector, sharp angular character design, western comic style, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"ghibli_animated","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> STUDIO GHIBLI HAND-DRAWN ANIMATION STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Studio Ghibli Hayao Miyazaki hand-drawn animation style. Clean simple character outlines with soft rounded naturalistic features — NOT exaggerated anime proportions. Large but grounded expressive eyes. Gorgeous painted watercolour backgrounds: lush greens, soft blue skies, detailed clouds, lived-in environments with care for mundane detail. Natural warm luminous colour palette: soft greens, earth tones, golden afternoon light. Wind movement in hair, fabric, grass, clouds. Soft cel-shading with warm shadow colours. Wonder, warmth, and reverence for the ordinary. Character appearance strictly from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: exaggerated anime proportions, huge unnatural eyes, 3D CGI rendering, photorealistic, dark gritty atmosphere, cold desaturated palette, flat digital vector, sharp angular character design, western comic style, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"ghibli_animated","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Studio Ghibli Hayao Miyazaki hand-drawn animation style. Clean simple character outlines with soft rounded naturalistic features — NOT exaggerated anime proportions. Large but grounded expressive eyes. Gorgeous painted watercolour backgrounds: lush greens, soft blue skies, detailed clouds, lived-in environments with care for mundane detail. Natural warm luminous colour palette: soft greens, earth tones, golden afternoon light. Wind movement in hair, fabric, grass, clouds. Soft cel-shading with warm shadow colours. Wonder, warmth, and reverence for the ordinary. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no panels. Avoid: exaggerated anime proportions, huge unnatural eyes, 3D CGI rendering, photorealistic, dark gritty atmosphere, cold desaturated palette, flat digital vector, sharp angular character design, western comic style, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: Miyazaki hand-drawn animation, clean simple outlines, soft natural proportions, gorgeous watercolour landscape backgrounds, warm luminous natural palette, wind in hair grass and curtains, nostalgic reverent warmth]

Hokusai (Ukiyo-e)

Хокусай, укиё-э гравюра. Жирные контуры тушью, плоские заливки с параллельной штриховкой. Прусская синь доминирует. Полный словарь — не только волны.

Экспериментальный Графика

←→

Длинный~4080 Короткий~1769 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> KATSUSHIKA HOKUSAI UKIYO-E STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Katsushika Hokusai (1760–1849). The greatest master of Japanese ukiyo-e woodblock printing — and one of history's most prolific artists. In his 90-year career he drew everything: people at work and rest, birds and flowers (kacho-ga), landscapes through every season, snow and rain, forests, mountain paths, tigers, fish, ghosts, dragons, demons, intimate domestic scenes, and yes — sometimes waves, sometimes Fuji. The Great Wave is one image out of tens of thousands. Do not default to it. Choose the visual elements that actually fit the scene. THE VISUAL LANGUAGE OUTLINES: Bold, confident, variable-weight black ink lines. Thicker on dominant outer forms and foreground elements. Thinner on interior detail and distant elements. The line has calligraphic quality — drawn with conviction and speed, not sketched timidly. FLAT COLOUR + PARALLEL HATCHING: Hokusai's colour areas are not uniformly flat. Shadow and tonal depth are achieved through extremely fine parallel hatching lines — rows of thin lines packed more or less closely together. More lines = darker. Fewer lines = lighter. The technique creates subtle tonal gradation while maintaining the flat graphic character. HOKUSAI'S FULL SUBJECT VOCABULARY FIGURES IN EVERYDAY LIFE: people walking, resting, in conversation, at work. Figures are simplified — faces minimal (eyes as curved lines, nose suggested, mouth a simple mark). The figure is a compositional and narrative element, not a psychological portrait. They establish human scale and presence. TREES AND PLANTS: pine with its layered horizontal branches, bamboo groves, cherry blossom, maple in autumn, willow. Plants have graphic character — they are designed forms, not botanically accurate. A pine branch is a calligraphic stroke with needles suggested by short radiating marks. BIRDS AND ANIMALS: cranes in flight, sparrows on branches, eagles, carp in water, horses. Animals are compositional counterpoints to figures or to emptiness. WEATHER AS GRAPHIC ELEMENT: - Snow: white space punctuated by small falling marks, weight accumulating on branches and rooftops - Rain: diagonal parallel lines cutting across the composition — figures bent against it - Wind: direction made visible through bent grass, flying clothing, streaming fabric, bowing branches - Fog/mist: distance fades to pale blue-grey with reduced detail ARCHITECTURE: wooden gate posts, thatched roof edges, shoji screen geometry, bridge structures — used as compositional framing elements, not detailed architectural drawing. WATER (when contextually relevant): Hokusai's water is a graphic invention, not realistic rendering. Calm water = horizontal parallel lines. Rivers = flowing curved parallel lines indicating current. Waves = arching crests with structured foam only when the scene is at water. Never forced into scenes that don't involve water. MOUNT FUJI (when contextually relevant): distant, simple pale cone, usually serene against a more active foreground. A symbol of permanence. Use only when composition and scene context genuinely call for it. COMPOSITION PRINCIPLES THE FRAME-WITHIN-FRAME: a large foreground element (tree branch, cliff face, archway, overhanging rock) frames a more distant element. Creates depth and drama without atmospheric perspective. SCALE CONTRAST: the tiny human figure within a large natural environment. Not always — but when used, this is the emotional statement: the person is present, the world is vast. DIAGONAL ENERGY: compositions are rarely static. A diagonal line of flight, a climbing path, a falling branch, a weather direction — gives movement to a still image. NEGATIVE SPACE AS COMPOSITION: Hokusai leaves sky and background areas as pale washes or near-empty zones. The blank space is compositional, not absence. COLOUR SYSTEM: PRUSSIAN BLUE DOMINANT Hokusai had access to Prussian blue — an imported European pigment that became his signature. His palette: PRUSSIAN BLUE range: - Deep Prussian blue: the darkest water, deep shadows, foreground wave troughs - Medium blue: mid-range water, sky areas - Pale Prussian blue / indigo-tinted sky: upper sky, distant water - Near-white with blue tint: foam, snow, clouds SECONDARY COLOURS (used sparingly): - Warm ochre / tan: skin tones, straw, light wood, sandy areas - Muted green-grey: foliage, distant land - Warm grey: stone, rocky surfaces - Occasional deep red or red-orange: clothing accent, small decorative element The palette is deliberately limited. The power comes from the blue range and the careful accent placement. FOR OUR CHARACTERS Characters translate into this world as simplified figures in the Hokusai visual language. They carry their distinctive form (height, posture, distinguishing features) but rendered in the flat, outlined, calligraphic style. Their clothing translates to flat-coloured graphic shapes. The emotional content comes from the composition and natural elements around them, not from realistic facial expressions. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks) — simplified to a clean ink mark. Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. Describe as dominant colour + type. The style renders all clothing as flat graphic colour with minimal surface detail. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Contextual environment: read the scene first, then choose the appropriate Hokusai visual vocabulary. Do NOT default to waves or Fuji. An indoor conversation gets architectural framing elements. An autumn scene gets maple and falling leaves. A winter scene gets snow pattern. A tense moment might get a bare tree or storm wind. Water scenes get water. Choose logically. Composition type: frame-within-frame / human small in landscape / figure prominent in foreground / figure within environment at equal scale. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Palette: which blues + secondary accent colours. Season/weather: affects natural elements and colour balance. Scale relationship: is the character small in landscape or prominent in foreground. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Katsushika Hokusai Japanese ukiyo-e woodblock print style. Bold variable-weight black ink outlines — thicker on dominant foreground forms, thinner on detail and distance. Flat colour fills with fine parallel hatching lines for tonal depth in shadow areas — no smooth gradients. Prussian blue dominant palette: deep blue, medium blue, pale blue, near-white. Warm ochre and muted green as secondary accents. Simplified graphic forms: stylised natural elements chosen for the scene — figures, trees, weather, birds, architecture, or water only when contextually appropriate. Perfectly balanced compositional design. No text, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: painterly oil painting rendering, photorealistic, 3D CGI, smooth gradient shading, anime style with large expressive eyes, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, western comic style, flat modern vector look, realistic photographic nature rendering, overly detailed western-style faces, forced waves or Mount Fuji when not contextually appropriate' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"hokusai_woodblock_print","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> KATSUSHIKA HOKUSAI UKIYO-E STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Katsushika Hokusai (1760–1849) — not just waves. Hokusai spent 90 years drawing everything: people in everyday life, birds and flowers, pine trees, snow on branches, seasonal landscapes, mountain paths, wind through bamboo, interior moments, figures at work or rest. Use his full vocabulary. Ukiyo-e woodblock print technique applied to whatever the scene contains. TECHNIQUE: - Bold variable-weight black ink outlines: thick on dominant forms, thin on interior detail. Calligraphic, confident. - Flat colour fills with parallel hatching for tonal depth: no smooth gradients — shadow built from fine parallel lines. - Prussian blue dominant: deep blue foreground, medium blue mid-ground, pale blue-grey distance, near-white highlights. - Simplified graphic forms: everything reduced to essential visual character. SUBJECT VOCABULARY: Figures in everyday life, conversation, rest, movement. Pine, maple, cherry matching mood. Snow, rain as diagonal lines, wind through bent grass or flying fabric. Birds, rocky landscape, mountain path, wooden architecture, shoji light. Waves or Fuji only if contextually relevant. PALETTE: Prussian blue range + warm ochre/tan + muted grey-green + warm grey + rare red-orange accent. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Katsushika Hokusai Japanese ukiyo-e woodblock print style. Bold variable-weight black ink outlines — thick on dominant foreground forms and silhouettes, thin on interior detail and background elements. Flat colour fills with fine parallel hatching lines for tonal depth in shadow areas — no smooth gradients. Prussian blue dominant palette: deep blue, medium blue, pale blue, near-white. Warm ochre and muted green as secondary accents. Simplified graphic forms. Environment chosen for the scene. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: painterly oil rendering, photorealistic, 3D CGI, smooth gradient shading, anime large expressive eyes, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, western comic style, flat modern vector, overly detailed realistic backgrounds, western-style faces, forced wave or Fuji elements when not contextually appropriate' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"hokusai_woodblock_print","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:2","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/2;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Katsushika Hokusai Japanese ukiyo-e woodblock print style. Bold variable-weight black ink outlines — thicker on dominant foreground forms, thinner on detail and distance. Flat colour fills with fine parallel hatching lines for tonal depth in shadow areas — no smooth gradients. Prussian blue dominant palette: deep blue, medium blue, pale blue, near-white. Warm ochre and muted green as secondary accents. Simplified graphic forms: stylised natural elements chosen for the scene — figures, trees, weather, birds, architecture, or water only when contextually appropriate. Perfectly balanced compositional design. No text, no panels. Medium shot, 85mm, f/2.0 shallow DoF

Копировать [Image generation hint, STYLE: Katsushika Hokusai woodblock print, bold variable-weight ink outlines, flat colour fills with parallel hatching, Prussian blue dominant palette, ukiyo-e aesthetic, full vocabulary of figures trees birds weather]

Japanese Watercolor (Sumi-e)

Суми-э тушь + акварельная размывка. Негативное пространство как композиция. Минимальное обозначение — то, что НЕ нарисовано, важно так же.

Экспериментальный Графика

←→

Длинный~3842 Короткий~1658 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> JAPANESE WATERCOLOUR ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Traditional Japanese ink and watercolour painting — the convergence of sumi-e (ink wash) and kanga watercolour traditions. A visual philosophy as much as a technique: less is more, emptiness is meaningful, suggestion is more powerful than description. A painting in this tradition is a collaboration between the artist and the viewer's imagination. THE FUNDAMENTAL PRINCIPLE: NEGATIVE SPACE In Japanese aesthetics, 'ma' — the meaningful empty space — is not absence but presence. The blank areas of the paper are as compositionally active as the brushstrokes. Often more so. A figure standing in fog does not need background — the fog IS the paper. A flowering branch does not need a fully described tree. The artist draws the few strokes that make the viewer's mind complete the rest. In practical terms: - Large areas of the composition are left as bare paper (white) - Elements are placed with precise intentionality — every mark matters - The eye is guided by placement, not filled by detail BRUSHWORK AND INK THE INK BRUSH: a round pointed brush that can produce hair-thin lines and broad wet washes in a single stroke, depending on pressure, speed, and water content. INK LINE qualities: - 'Flying white' (Hihaku): fast stroke leaving broken white gaps in the line — used for speed, energy, texture - Heavy wet: slow brush, fully loaded — produces solid deep black line - Dry brush: brush not fully loaded, produces fibrous textured strokes — used for rough textures, aged surfaces, grass - Calligraphic: the line has rhythm, confidence, and variation. Never mechanical. TONAL RANGE (through water dilution): - Full black ink: deep shadows, focal outlines - 50% dilution: mid-tone grey — secondary outlines, atmospheric elements - 80% dilution: pale grey wash — distant mountains, mist - 95% dilution: near-transparent wash — the lightest atmospheric suggestion WATERCOLOUR WASHES Applied over or alongside ink. Always transparent — no opaque paint. WET-ON-WET: wet colour onto wet paper. Produces soft, diffused, unpredictable blooms. Used for mist, fog, atmospheric sky, gentle mood. The colour spreads and bleeds at the edges. WET-ON-DRY: wet colour onto dry paper. Produces cleaner edges. Used for foliage, clothing colour, defined atmospheric areas. LAYERING: multiple transparent washes build depth. Each layer dries before the next, allowing colour to accumulate subtly. PALETTE SYSTEM Japanese watercolour avoids saturated colour. The palette is always muted, soft, and harmonious. NEUTRAL BASE (applied most widely): - Pale blue-grey (indigo-tinted) - Soft ivory/cream (warm white) - Transparent grey wash NATURE COLOURS (used sparingly): - Soft olive-green: foliage, moss, distant trees - Pale rose/dusty pink: cherry blossoms, morning sky - Warm sienna/ochre: earth, rocks, autumn foliage - Deep ink grey-black: selective accent marks ACCENT COLOUR (one per image maximum): A single spot of slightly more saturated colour draws the eye: a red seal mark in the corner, the red of a garment, a single dark branch against pale sky. This accent is the compositional anchor. NATURAL SUBJECTS AND EMOTIONAL MIRRORS In Japanese art tradition, natural subjects carry emotional meaning: Cherry blossoms: the beauty of transience, gentle sorrow, brief joy Bamboo: strength under pressure, flexibility Pine: endurance, longevity, winter resilience Mist on mountains: mystery, distance, the unknowable Rain: melancholy, renewal, the rhythm of things Still water: reflection, self-contemplation, depth Single bird in flight: freedom, longing, departure Snow: silence, purity, erasure, new beginning Wind through grass: impermanence, movement, life passing Use the natural element to mirror or comment on the emotional state of the scene. FIGURE IN THE COMPOSITION Figures in Japanese painting are: - Usually small relative to the natural setting - Suggested with minimal strokes: an outline, a face with 3-4 marks, a garment as a flat wash - Positioned with clear compositional intent — they are placed, not scattered - Facing into negative space (toward the empty part of the composition) — this creates a sense of looking, contemplating, entering the unknown For our characters: the reference image provides the face. The painting style simplifies everything else to graceful minimal marks. The character's emotional state is expressed through their relationship to the natural elements around them, not through realistic facial expression. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks) — suggested with delicate minimal ink marks. Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. Describe dominant colour in muted terms: 'pale cream garment', 'dark blue robe', 'soft grey coat'. The wash style translates any clothing into a simple colour form. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Natural element: which element mirrors the emotional state (cherry blossoms, bamboo, pine, mist, rain, still water, bird, snow, wind). Emotional parallel: what the natural element says about the character's inner state. Composition note: where is the character in the frame, how much negative space. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Palette: ink wash + 2-3 soft watercolour colours. Technique: wet-on-wet (soft, diffused) or wet-on-dry (slightly crisper). MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Traditional Japanese sumi-e ink wash and watercolour painting style. Fluid calligraphic ink brushwork with variable line weight — from hair-thin to broad wet washes in single strokes. Transparent watercolour washes, wet-on-wet technique for soft atmospheric blooms. Large meaningful negative space — empty areas are compositionally active. Minimal suggestive marks: few strokes indicate more than they describe. Muted soft palette: pale grey-blue, soft olive, ivory, dusty rose, deep ink. Single accent colour element. Contemplative, delicate, breathing composition. No text, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: photorealistic rendering, 3D CGI, heavy opaque paint, anime large expressive eyes, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, western illustration style, flat digital vector, heavy saturated colour, overcrowded composition, fully detailed photographic backgrounds, uniform mechanical linework' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"japanese_ink_watercolor","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> JAPANESE WATERCOLOUR ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Traditional Japanese ink and watercolour illustration. Sumi-e (ink wash) meets kanga watercolour painting. Minimal, graceful, breathing. Negative space is as important as what is drawn. A few brushstrokes suggest a world. Everything that can be left out, is left out. TECHNIQUE: - Ink line: thin, fluid, calligraphic — drawn with a brush in one confident motion. Never scratched or corrected. - Wash: transparent watercolour applied over or alongside ink. Wet-on-wet for soft diffusion. Dry brush for texture. - Negative space: large areas of the paper left bare. The emptiness is part of the composition. - Suggestion over description: a few strokes suggest a tree, a mountain, rain. BRUSHWORK: 'Notan' balance of dark and light. Line varies from hair-thin to broad wet wash. Ink graduated through water dilution. Colour: transparent washes, never opaque. PALETTE: pale ink wash + muted watercolour. Soft blue-grey, pale olive, warm ivory, dusty rose, muted gold. Never saturated. Always soft. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Traditional Japanese ink and watercolour illustration style. Sumi-e ink wash technique: fluid calligraphic brushstrokes, variable-weight ink lines, transparent watercolour washes wet-on-wet. Large areas of negative space. Minimal suggestive composition — few strokes indicate more than they describe. Pale muted palette: grey-blue, soft olive, ivory, dusty rose. Delicate, breathing, contemplative. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: photorealistic rendering, 3D CGI, heavy opaque paint, anime style, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, western illustration style, flat digital vector, heavy saturated colour, overcrowded composition, detailed architectural backgrounds' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"japanese_ink_watercolor","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Traditional Japanese sumi-e ink wash and watercolour painting style. Fluid calligraphic ink brushwork with variable line weight — from hair-thin to broad wet washes in single strokes. Transparent watercolour washes, wet-on-wet technique for soft atmospheric blooms. Large meaningful negative space — empty areas are compositionally active. Minimal suggestive marks: few strokes indicate more than they describe. Muted soft palette: pale grey-blue, soft olive, ivory, dusty rose, deep ink. Single accent colour element. Contemplative, delicate, breathing composition. No text, no panels. ma

Копировать [Image generation hint, STYLE: sumi-e ink and watercolour wash on rice paper, negative space as composition, minimal suggestion, ink line plus colour wash, what is NOT painted matters as much as what is]

Sketch

Карандаш/тушь на бумаге. Штриховка для тона. Сырое, непосредственное, живое — энергия первого впечатления, пойманного быстро.

Экспериментальный Графика

←→

Длинный~3743 Короткий~1629 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> SKETCH ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Pencil and ink sketch illustration — the visual language of a skilled illustrator working with confidence and economy. Not a rough preliminary drawing. Not a finished painting. Something specifically in between: a complete image made with line, tone, and selective simplification. The sketch reveals the drawing hand behind it. NO TEXT, NO ANNOTATIONS — this is a pure drawing. No margin notes, no labels, no speech bubbles, no written elements of any kind. THREE PRIMARY TECHNIQUES PENCIL SKETCH: Graphite on white paper. Variable darkness based on pressure. The marks are slightly soft — not hard-edged like ink. Characteristics: - Lighter areas: few light pencil marks or bare paper - Mid-tones: regular hatching, loosely applied - Dark areas: heavy pencil pressure, cross-hatching, or smudged tone with side of pencil - Smudging: a blended tonal area can suggest atmosphere (fog, deep shadow) without hatching marks - Erased highlights: brightest points can be indicated by absence of mark - Line quality: slightly soft edge, can build up tone through layering INK LINE: Black ink pen or brush on white paper. The most graphic and decisive of the three techniques. Characteristics: - Line weight varies: thick on outer silhouettes and dominant shadow edges, thin on interior detail - Shadows: rendered as parallel hatching, cross-hatching, or solid black areas - No tone possible between full ink and bare paper — only the hatching creates mid-tones - High contrast: the graphic nature of ink creates strong, readable images - Confident, no corrections visible — each line placed intentionally INK + WATERCOLOUR WASH: Ink line base with simple transparent colour washes added. The colour informs the eye without replacing the drawing. Characteristics: - Ink line provides all structure and shadow information - Colour wash: 2-3 colours, loosely applied, slightly outside the lines is fine - Not fully rendered: clothing has one colour wash, skin has one tone, background has one colour note - The drawing remains visible through the wash — the ink is dominant SHADING METHODS IN DETAIL PARALLEL HATCHING: lines drawn close together in the same direction. Shadow value determined by line spacing. Used for: flat shadow areas, mid-tones. CROSS-HATCHING: two or more sets of parallel lines crossing each other. Creates deeper shadow values. Used for: deepest shadows, strongly lit objects. CONTOUR HATCHING: lines follow the surface contour of the form. Creates a sense of volume and form, not just flat shadow. Used for: sphere-like forms, cloth folds following the body. SOLID BLACK: areas filled completely with ink. Used for: deepest shadow cast areas, black clothing, silhouetted objects, dramatic high-contrast compositions. SCRIBBLE TONE: loose organic marks that suggest texture or tone without strict hatching. Used for: foliage, rough surfaces, atmospheric background. LINE WEIGHT SYSTEM The most important quality that separates a skilled sketch from a mediocre one: HEAVIEST LINES: outer silhouette where it meets shadow; dominant structural edges; foreground elements MEDIUM LINES: interior structural lines; major form boundaries LIGHT LINES: detail; far/background elements; secondary information NEAR-INVISIBLE LINES: the lightest suggestion; out-of-focus background; unimportant detail This hierarchy makes the image readable at a glance and gives it depth without shading. COMPOSITION FOR SKETCH Sketches often use a focal figure with minimal or absent background — the figure sits on white paper with perhaps a few ground lines or a loose environment suggestion. Options: FIGURE ON WHITE: no background, pure figure. Maximum focus on character. Feels like a character study or portrait sketch. LOOSE ENVIRONMENT: a few quick lines suggest the setting — a window frame, a table edge, a horizon line, a doorway. Enough to locate the scene. ATMOSPHERIC SKETCH: more background detail, but kept light and loose. Foreground heavy and detailed, background fading to near-nothing. VIGNETTE: detailed centre, fading to bare paper at the edges. Creates focus and intimacy. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks) — rendered as deliberate ink marks. Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. Sketch renders clothing as line and hatched shadow. Texture is implied by line direction, not painted. 'Dark coat' = hatched areas indicating dark fabric. 'Light dress' = minimal line with bare paper as the light. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' Expression: where does the emphasis go — eyes, mouth, specific tension. 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Setting type: figure on white / loose environment suggestion / atmospheric / vignette. Focal emphasis: what the drawing wants you to look at first. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. Technique: pencil / ink line / ink + wash. Shading method: parallel / cross / contour / solid black / combination. Line weight note: tight and precise vs. loose and gestural. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Skilled pencil and ink sketch illustration. Confident variable-weight line work — thick on outer silhouettes and dominant shadow edges, thin on interior detail and background elements. Hatching and cross-hatching for shadow and tone: parallel hatching for mid-tones, cross-hatching for depth, solid black for maximum shadow. Minimal or absent background — figure present on white or off-white paper ground. No colour or limited 2-3 colour transparent wash if ink+wash technique selected. No text, no annotations, no labels, no speech bubbles, no writing of any kind anywhere in the image. Pure drawing. Single illustrated scene.' 8. NEGATIVE (append verbatim): 'Avoid: photorealistic rendering, 3D CGI, full oil or digital colour painting, anime large expressive eyes, manga panels, speech bubbles, any text or writing in image, annotations, notes, margin text, labels, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, flat uniform digital vector illustration, uniform single-weight line throughout' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"sketch_illustration","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> SKETCH ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Pencil and ink sketch illustration. Clean, confident, slightly loose — the kind of sketch made by a skilled illustrator working quickly. Line-based, minimal colour, expressive. No text annotations, no margin notes — just the drawing itself. TECHNIQUE OPTIONS — choose one per scene: PENCIL SKETCH: soft graphite, loose but intentional. Cross-hatching for shadow. Some lines darker, bolder for emphasis. Smudged tonal areas for atmosphere. White paper shows through as highlight. INK LINE: confident single-weight or variable-weight black ink. Clean, decisive. Shadows as hatching or solid black areas. INK + WATERCOLOUR WASH: ink line base with simple colour washes. 2-3 colours only. SHADING: parallel hatching | cross-hatching | contour hatching | solid black for deepest shadow. LINE QUALITY: confident, varied weight — heavier on shadow edges and dominant forms, lighter on detail and far elements. NO ANNOTATIONS: pure drawing. No text, no labels, no notes. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Pencil and ink sketch illustration. Confident variable-weight line work, expressive mark-making. Hatching and cross-hatching for shadow and tone. Minimal background suggested with sparse lines. No colour or limited 2-3 colour wash. No text, no annotations, no labels anywhere in the image. Pure drawing on white or off-white paper ground. Single illustrated scene.' NEGATIVE (append verbatim): 'Avoid: photorealistic rendering, 3D CGI, full colour painting, anime style, manga panels, speech bubbles, text or writing in image, annotations, notes, labels, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, flat digital vector, western comic halftone, overly clean digital illustration look' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"sketch_illustration","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Skilled pencil and ink sketch illustration. Confident variable-weight line work — thick on outer silhouettes and dominant shadow edges, thin on interior detail and background elements. Hatching and cross-hatching for shadow and tone: parallel hatching for mid-tones, cross-hatching for depth, solid black for maximum shadow. Minimal or absent background — figure present on white or off-white paper ground. No colour or limited 2-3 colour transparent wash if ink+wash technique selected. No text, no annotations, no labels, no speech bubbles, no writing of any kind anywhere in the image. Pure drawing. Single illustrated scene. Avoid: photorealistic rendering, 3D CGI, full oil or digital colour painting, anime large expressive eyes, manga panels, speech bubbles, any text or writing in image, annotations, notes, margin text, labels, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, flat uniform digital vector illustration, uniform single-weight line throughout

Копировать [Image generation hint, STYLE: pencil or ink sketch on paper, hatching for tone, raw immediate alive quality, visible paper grain, graphite and ink mark-making, first impression captured fast]

Linocut

Ручная блочная печать. Чёрная краска на белой бумаге. Вся тональность через штриховку — ноль градиентов. Необязательный один акцентный цвет. Без текста.

Экспериментальный Графика

←→

Длинный~2486 Короткий~1822 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — LINOCUT PRINT STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages. Never skip. Specificity: fabric type + fit + color (as black/white/grey tone) + condition. If NOT changed on-screen → last described outfit persists. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe through action. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background as bold graphic shapes. Own sentence. Include one meaningful object. Describe in terms of black/white mass and carved line density. 6. LIGHTING & LENS CHARACTER: single strong directional source creating bold shadow shapes. Describe which areas are solid black, which are carved white, where hatching creates mid-tones. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: fine dense hatching softening areas | carved white halation around light source TENSE: extreme black mass dominance | harsh diagonal hatching | deep vignette in carved black PASSIONATE: heavy chiaroscuro in carved contrast | close-cropped bold silhouettes LONELY: vast white negative space | isolated small dark figure | sparse hatching CHAOTIC: crossing hatch directions | broken carved lines | angular fragmented composition DREAMY: very fine parallel hatching creating soft grey | blurred carved edges MUNDANE: even balanced black-white distribution | clean regular hatching NOIR: 90% solid black | minimal carved white highlights | single white eye-catch Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Linocut relief print illustration style. Hand-carved block print on paper — bold black ink on white paper with slight ink texture unevenness from physical pressing and visible paper grain in white areas. All tonal variation achieved exclusively through carved parallel hatching lines of varying density and spacing — no smooth gradients, no blending. Strong graphic contrast: large areas of solid black ink with white carved negative space cutting through. Simplified bold forms with slight hand-carved line irregularity — not digitally precise. Optional single flat accent colour as separate block overlay (red, blue, or ochre). High-contrast dramatic composition with strong readable silhouettes. Physical handmade print texture quality throughout. No text, no writing, no letters, no words, no annotations, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: smooth gradients, soft blending, photorealistic rendering, painterly oil brushwork, anime style, cel shading, 3D CGI, multiple colours, full colour palette, text or writing or letters or words of any kind anywhere in image, speech bubbles, watermark, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, bad anatomy, clean digital vector precision, perfectly smooth machine-cut lines' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit tone] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"linocut_print","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"9:16","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> LINOCUT PRINT STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Linocut / woodcut relief print — hand-carved block printing on paper. Bold black-and-white (or limited colour) image carved from linoleum or wood block, inked, and pressed onto paper. The aesthetic is graphic, bold, high-contrast, with the specific textural qualities of a physical printing process. TECHNIQUE: - CARVED LINES: all lines and shapes are carved grooves in a block surface. White areas = carved away (no ink). Black areas = raised surface (ink transfers). This creates a specific visual quality — lines have slight irregularity, not digital precision. - BOLD CONTRAST: predominantly black and white. Massive areas of solid black. White cuts through it as carved negative space. - TEXTURE OF THE PRINT: slight ink unevenness — areas of the black show faint texture where ink didn't transfer perfectly. Paper grain visible in white areas. The look of a physical object printed by hand. - NO GRADIENTS: tonal variation achieved ONLY through hatching — parallel carved lines of varying density. Dense hatching = dark grey. Sparse hatching = light grey. No smooth blending. - LIMITED COLOUR VARIANT: optional second colour (one flat colour — red, blue, ochre — as a separate block overlay). Never more than 2-3 total colours including black. COMPOSITION: bold, graphic, high-impact. Strong silhouettes. Simplified forms readable at distance. The medium forces simplification — detail comes from clever carving, not fine rendering. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (dominant tone: black or white) + pose + expression 3. ENVIRONMENT — foreground/mid/background + bold graphic shapes + one meaningful object 4. LIGHTING — single strong directional source creating bold shadow shapes + hatching density Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Linocut relief print illustration style. Hand-carved block print on paper — bold black ink on white paper with slight ink texture unevenness and visible paper grain. All tonal variation through carved parallel hatching lines of varying density — no smooth gradients. Strong graphic contrast: large areas of solid black with white carved negative space. Simplified bold forms with slight hand-carved line irregularity. Optional single accent colour as separate block overlay. High-contrast dramatic composition with strong silhouettes. Physical print texture quality — not clean digital. No text, no writing, no letters, no words, no panels.' NEGATIVE (append verbatim): 'Avoid: smooth gradients, photorealistic rendering, soft blending, painterly brushwork, anime style, cel shading, 3D CGI, multiple colours, full colour palette, text or writing or letters of any kind in image, speech bubbles, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, clean digital precision, perfectly smooth lines' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"linocut_print","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Linocut relief print illustration style. Hand-carved block print on paper — bold black ink on white paper with slight ink texture unevenness from physical pressing and visible paper grain in white areas. All tonal variation achieved exclusively through carved parallel hatching lines of varying density and spacing — no smooth gradients, no blending. Strong graphic contrast: large areas of solid black ink with white carved negative space cutting through. Simplified bold forms with slight hand-carved line irregularity — not digitally precise. Optional single flat accent colour as separate block overlay (red, blue, or ochre). High-contrast dramatic composition with strong readable silhouettes. Physical handmade print texture quality throughout. No text, no writing, no letters, no words, no annotations, no panels. Avoid: smooth gradients, soft blending, photorealistic rendering, painterly oil brushwork, anime style, cel shading, 3D CGI, multiple colours, full colour palette, text or writing or letters or words of any kind anywhere in image, speech bubbles, watermark, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, bad anatomy, clean digital vector precision, perfectly smooth machine-cut lines

Копировать [Image generation hint, STYLE: hand-carved block relief print, bold black ink on white paper, all tone through parallel hatching with no gradients, massive black areas with carved white negative space, optional single accent colour]

Pop Art

Уорхол / Лихтенштейн. Жирные контуры, плоские заливки, точки Бен-Дэй. 2-5 цветов. Шелкография. Максимальный графический удар. Без текста и баблов.

Экспериментальный Графика

←→

Длинный~3545 Короткий~1659 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> POP ART STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Pop Art, 1950s–1960s. Andy Warhol, Roy Lichtenstein, Richard Hamilton. The movement that took commercial, mass-produced visual culture — advertising, comics, screen printing — and elevated it into fine art. Bold, flat, graphic, reproducible. Emotion as icon. Feeling as design. For our purposes, two primary registers: REGISTER 1: WARHOL SILKSCREEN The flat, coloured, slightly misregistered silkscreen print aesthetic. One or two bold base colours. High contrast. Graphic simplification of the figure. Often with a sense of repetition or series — as if this is one of many identical prints. Like a concert poster or album cover. REGISTER 2: LICHTENSTEIN COMIC POP Ben-Day dots as the primary texture/shading element. Bold primary colours. Strong black outlines of uniform weight. The visual language of a blown-up comic panel taken seriously as art. Faces with exaggerated graphic expressions — all emotion carried by the face and pose alone, no text. TECHNICAL LANGUAGE BLACK OUTLINES: uniform weight, bold, everywhere. Every shape has a black outline. No variable weight. This is different from Bilibin or BioWare art — here the line is functional, not expressive. FLAT COLOUR FILLS: each area is one colour. No gradients. No shading. No tonal variation within a single colour area. The colour IS the form. BEN-DAY DOTS (Lichtenstein register): instead of shading, shadow areas are indicated by a regular grid of coloured dots on a white or light background. The dot size and spacing suggests the value — small dots = light shadow, large dots close together = dark shadow. The dots are part of the visual aesthetic, not a mistake. COLOUR SYSTEMS WARHOL PALETTE OPTIONS: - Two-tone: black + one acid colour (hot pink, acid yellow, electric blue, orange, lime) - Four-colour silkscreen: misregistered layers of different colours creating chromatic fringing - Series feel: repeat the image in different colour combinations - Always: flat, high-contrast, graphic LICHTENSTEIN PRIMARY PALETTE: - Base colours: red, yellow, blue, black, white - Skin tones in Lichtenstein: flat peach or cream, or stylized graphic skin tone - Emotion colours: red for anger/passion, blue for coolness, yellow for shock/thought PSYCHEDELIC POP VARIANT: Multiple saturated colours from across the spectrum — acid green, magenta, orange, cyan, purple. High energy. Everything vibrating against itself. 1960s concert poster energy. MONOCHROME + ONE ACCENT: Black and white base (or dark and white) with a single bold colour element carrying all the emotional weight. The red of lipstick, the yellow of hair, a blue background behind a black figure. GRAPHIC SIMPLIFICATION Pop Art reduces forms to their most essential graphic shapes. A face becomes: oval, two eyes, nose as simple shape, mouth as bold curve. Hair as flat colour block. Clothing as flat colour plane. The goal: maximum recognition with minimum information. Would this face read at a distance? Would this emotion be legible as a poster? If yes, the simplification is correct. EMOTIONAL EXPRESSIONS (graphic, not subtle): - Surprise: wide circle eyes, open mouth - Longing: half-lidded eyes, slight parted lips - Anger: sharp angular brows, tight line mouth - Joy: wide open eyes, big smile curve - Sadness: downturned brow, drooping mouth corners COMPOSITION WARHOL: central figure, minimal background (flat colour or simple gradient-free background). The person IS the composition. Square format works well. LICHTENSTEIN: figures in action or emotion, narrative implied. Diagonal compositions. Foreground figures bold, background simplified to flat colour planes or dot patterns. Radiating action lines behind the figure instead of any text element. BACKGROUND OPTIONS: - Flat single colour (bold — not muted) - Dot pattern over flat colour - Simple geometric shapes (circles, rectangles) as abstract background - Radiating lines from figure (Lichtenstein action energy lines) HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks) — simplified to graphic mark. Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. Pop Art renders all clothing as bold flat colour planes. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Register: Warhol silkscreen / Lichtenstein Ben-Day / psychedelic / monochrome+accent. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Andy Warhol Roy Lichtenstein Pop Art illustration style. Bold uniform-weight black outlines on all elements. Completely flat colour fills — no shading, no gradients, no tonal variation within colour areas. Ben-Day halftone dot grid for shadow areas in Lichtenstein register. Limited bold palette of 2-5 saturated or primary colours. Silkscreen or offset print aesthetic. Maximum graphic simplification of forms for bold readability. High contrast, designed, iconic. No text, no speech bubbles, no thought bubbles, no annotations, no writing of any kind, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: painterly rendering, photorealistic, 3D CGI, gradient shading or blending, subtle tonal variation, anime style, manga panels, speech bubbles, thought bubbles, text or writing in image, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, muted desaturated palette, realistic proportions competing with graphic simplification' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"pop_art_illustration","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"1:1","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:1/1;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> POP ART STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Andy Warhol / Roy Lichtenstein Pop Art. Bold graphic design meets fine art. Flat colours, strong black outlines, Ben-Day halftone dot patterns, screen print aesthetic. Everything simplified to its most graphic, most recognisable, most reproducible form. Emotion made into icon. WARHOL REGISTER: high contrast silkscreen feel. One or two flat colours per layer, slightly misregistered. Limited palette of 2-4 bold colours. Flat, graphic, punchy. LICHTENSTEIN REGISTER: Ben-Day dots on shadow areas. Bold black outlines. Primary colours — red, yellow, blue. Comic-panel aesthetic elevated. Expression graphic and direct. TECHNIQUE: Bold uniform black outlines. Flat colour fills — no shading, no gradient. Ben-Day dots for shadow/tone. Limited 2-5 colour palette. High contrast. Graphic, designed, intentional. PALETTE OPTIONS: Classic Warhol (acid yellow, hot pink, electric blue, orange + black + white) | Lichtenstein primary (red, yellow, blue, black, white + dots) | Psychedelic (multiple saturated offset) | Monochrome + one accent. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Andy Warhol and Roy Lichtenstein Pop Art style. Bold uniform black outlines. Flat colour fills, no shading or gradients. Ben-Day halftone dot grid on shadow and tone areas. Limited bold palette of 2-5 colours — primary and acid tones. Silkscreen or offset-print aesthetic. Graphic, simplified, high-contrast composition. No text, no speech bubbles, no thought bubbles, no annotations, no panels.' NEGATIVE (append verbatim): 'Avoid: painterly rendering, photorealistic, 3D CGI, gradient shading, anime style, manga panels, speech bubbles, thought bubbles, text or writing in image, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, muted desaturated palette, western superhero comic style, fine detailed linework' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"pop_art_illustration","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"1:1","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:1/1;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Andy Warhol Roy Lichtenstein Pop Art illustration style. Bold uniform-weight black outlines on all elements. Completely flat colour fills — no shading, no gradients, no tonal variation within colour areas. Ben-Day halftone dot grid for shadow areas in Lichtenstein register. Limited bold palette of 2-5 saturated or primary colours. Silkscreen or offset print aesthetic. Maximum graphic simplification of forms for bold readability. High contrast, designed, iconic. No text, no speech bubbles, no thought bubbles, no annotations, no writing of any kind, no panels. Avoid: painterly rendering, photorealistic, 3D CGI, gradient shading or blending, subtle tonal variation, anime style, manga panels, speech bubbles, thought bubbles, text or writing in image, watermark, blurry, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, muted desaturated palette, realistic proportions competing with graphic simplification

Копировать [Image generation hint, STYLE: Warhol Lichtenstein pop art, bold uniform black outlines, flat colour fills, Ben-Day halftone dots, limited 2-5 colour palette, silkscreen or offset-print aesthetic, maximum graphic impact]

Soviet Mosaic

Мозаика метро и Дворцов культуры. Видимые прямоугольные тессеры, швы-контуры. Красный, золото, охра, уголь. Монументальная героическая композиция.

Экспериментальный Графика

←→

Длинный~3557 Короткий~1681 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> SOVIET MOSAIC ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Soviet-era public mosaic art — the monumental murals covering metro stations, Palaces of Culture, public squares, and state buildings across the USSR from the 1930s through the 1980s. This is illustration built from tile: bold geometric simplification, heroic figuration, radiating compositional energy. Not Socialist Realist painting — mosaic has its own visual grammar forced by the medium itself. Every shape must be simplified enough to be readable in tesserae. Every colour zone must be distinct. Every form must be bold enough to read from thirty metres. THE TESSERA TEXTURE SYSTEM The defining visual quality of mosaic art: every surface is built from small rectangular tile fragments (tesserae). In illustration terms: FINE TESSERAE (focal figure): small tile units, tightly packed. Colour transitions are fine-stepped — many small hue steps. Detail is possible here. The face is built from flesh-tone tile clusters. MEDIUM TESSERAE (mid-ground): larger tile units. Colour zones are broader. Form is simplified. COARSE TESSERAE (background, sky): large tile blocks. Colour areas become near-abstract. The sky might be only three or four distinct tile colours stepping from deep blue to pale gold. GROUT LINES: the dark line between tile zones — in illustration terms, this functions as a bold outline system. Every major form boundary has a visible dark separation. Not an artist's ink line — a structural tile separation. COLOUR STEPPING: mosaic cannot gradient. Tonal transitions happen through colour stepping — a sequence of distinct tile colours moving from light to shadow: pale ochre → warm tan → sienna → deep brown → near-black. Each step is a visible tile band. METALLIC TILES: Soviet mosaics frequently incorporated gold, copper, and metallic tile for highlights and halos. In illustration terms: warm gold sheen at focal points, catching notional light. PALETTE SYSTEM Soviet mosaic used a limited, bold palette: PRIMARY: Deep Communist red (vermillion-crimson range) — the most powerful compositional element WARM GOLD/OCHRE: figures, skin, wheat, architectural ornament DEEP CHARCOAL/NEAR-BLACK: outlines, shadow zones, depth PRUSSIAN BLUE: sky, water, deep background CREAM/WARM WHITE: light catching tiles, near-white highlights OCCASIONAL ACCENT: emerald green (foliage, military), copper-orange (autumn, fire) The palette rarely exceeds 5-6 distinct hues per image. The power comes from their bold, contrasted placement — not from colour complexity. COMPOSITION PRINCIPLES MONUMENTAL SCALE: figures are large within the frame. They occupy significant compositional real estate. The viewer feels small before them. HEROIC VIEWPOINT: low-angle looking up at the figure — they tower against sky. This is the default compositional mode of Soviet public art. RADIAL ENERGY: compositional lines radiate outward from the central figure — like rays from the sun. The subject is literally the centre of the visual universe. DIAGONAL DYNAMISM: even static figures have diagonal energy in the composition — a raised arm, a flag, a direction of gaze creates movement. FRONTAL PRESENTATION: unlike Western portraiture, Soviet mosaic figures often face directly outward — confronting the viewer, not engaged in private action. THE SKY: almost always present, almost always significant. Deep blue, gold-hour warm, or radiating pale light. The sky is the compositional backdrop — a large clean colour zone that makes the figure pop. FOR CONTEMPORARY CHARACTERS Characters translated into this style gain monumentality regardless of their actual role in the scene. Even an intimate conversation becomes a monumental proclamation. Even a quiet moment reads as an epic statement. This is the power and the slight absurdity of the style — it makes everything feel like history. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks) — rendered as deliberate dark grout-line tile marks. Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. All clothing renders as flat coloured tile zones — texture is invisible. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Viewpoint: low-angle heroic / straight-on frontal / slight upward tilt. Compositional energy: radial / diagonal / static monumental. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Soviet-era public mosaic mural art style. Entire image surface rendered as visible rectangular tile tesserae — fine-grained at the focal figure, coarser toward background and sky. Bold dark grout-line outlines define all major form boundaries. Flat colour zones with stepped tonal transitions — distinct tile colour bands moving light to shadow, no smooth gradients. Metallic gold and copper tile highlights at focal points. Deep Communist red, warm gold, ochre, charcoal-black, Prussian blue limited palette. Monumental low-angle heroic composition. Radial compositional energy. No text, no panels, no slogans, no written elements.' 8. NEGATIVE (append verbatim): 'Avoid: photorealistic rendering, 3D CGI, smooth gradient shading, soft painterly oil technique, anime style, manga panels, speech bubbles, text or slogans or writing in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, modern flat digital vector, impressionist loose brushwork, watercolour wash, pastel or soft muted palette, realistic photographic rendering' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"soviet_mosaic","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> SOVIET MOSAIC ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Soviet-era public mosaic art — metro station murals, palace of culture walls, public buildings of the USSR (1930s-1980s). Bold geometric simplification, heroic scale, radiating energy. Every form broken into visible tesserae — small rectangular tile units that build shapes through colour clustering. TECHNIQUE: - Tessera texture: entire image shows tile fragment structure. At focal figure, tiles are fine. At background, tiles are larger and more abstract. - Outline: dark grout-line outline — the dark separation between tile colour zones. Outlines are bold and defining. - Flat colour zones within outlined forms. No gradients — tonal transitions achieved by stepping through tile colours. - Metallic accents: gold and copper tile highlights at focal points. - Monumental composition: figures large, often viewed from below (heroic low angle). PALETTE: deep Communist red, warm gold/ochre, earthy sienna, dark charcoal near-black, cream/pale yellow, occasional Prussian blue. 5-6 colours maximum. Red and gold dominant. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Soviet-era public mosaic art style. Entire image surface built from visible rectangular tile tesserae — colour zones cluster into mosaic texture, finer at focal figure, coarser in background. Bold dark grout-line outlines defining all major forms. Flat stepped colour transitions, no gradients. Metallic gold tile highlights at focal points. Deep Communist red, warm gold, ochre, charcoal-black dominant palette. Monumental composition, heroic scale. No text, no panels, no slogans.' NEGATIVE (append verbatim): 'Avoid: photorealistic rendering, 3D CGI, smooth gradient shading, painterly oil technique, anime style, manga panels, speech bubbles, text or slogans in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, modern digital vector flatness, impressionist loose brushwork, watercolour wash, pastel palette' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"soviet_mosaic","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"3:4","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:3/4;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Soviet-era public mosaic mural art style. Entire image surface rendered as visible rectangular tile tesserae — fine-grained at the focal figure, coarser toward background and sky. Bold dark grout-line outlines define all major form boundaries. Flat colour zones with stepped tonal transitions — distinct tile colour bands moving light to shadow, no smooth gradients. Metallic gold and copper tile highlights at focal points. Deep Communist red, warm gold, ochre, charcoal-black, Prussian blue limited palette. Monumental low-angle heroic composition. Radial compositional energy. No text, no panels, no slogans, no written elements. Avoid: photorealistic rendering, 3D CGI, smooth gradient shading, soft painterly oil technique, anime style, manga panels, speech bubbles, text or slogans or writing in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, modern flat digital vector, impressionist loose brushwork, watercolour wash, pastel or soft muted palette, realistic photographic rendering

Копировать [Image generation hint, STYLE: Soviet metro station mural mosaic, visible rectangular tile tesserae, grout-line outlines, stepped colour transitions, communist red with warm gold, ochre and charcoal-black, monumental heroic radiating composition]

Soviet Poster

Гуашь на бумаге, литографическая зернистость. Героические реалистичные фигуры (не флэт-вектор!). Красный, чёрный, кремовый, жёлтый. Диагональная энергия.

Экспериментальный Графика

←→

Длинный~4119 Короткий~1840 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> SOVIET POSTER ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Soviet propaganda poster art and constructivist illustration — the visual language forged between the 1917 Revolution and the height of the Cold War. This is graphic art as political weapon: designed to be read in an instant, understood by everyone regardless of literacy, remembered permanently. The masters were Rodchenko, Klutsis, El Lissitzky in the early constructivist period; anonymous poster artists of the Great Patriotic War; the socialist realist illustrators of the 1950s and 60s. The style range is broad — from cold geometric abstraction to warm heroic figuration — but the core principles are constant: boldness, clarity, diagonal energy, limited palette, maximum impact. THREE SUBSTYLE OPTIONS CONSTRUCTIVIST (1920s–1930s): Named after Rodchenko and the constructivist movement. Pure geometric visual logic. - Strong diagonal composition — the frame is divided by bold diagonal shapes - Figure as geometric form — simplified to flat coloured silhouette - Red, black, white dominant — the most extreme and clean version of the palette - Photomontage-style placement: figure fragments, cropped, repositioned, layered - Geometric shapes cut across the frame: triangles, bold stripes, circles - Maximum graphic tension — the design feels like it's vibrating with suppressed energy SOCIALIST REALIST POSTER (1940s–1960s): More figurative, warmer, more human — but still radically simplified. - Figures are recognizably human and heroic — upward gaze, strong posture, clear action - Warm ochre and sienna added to the palette — skin, wheat, autumn - Slightly more atmospheric backgrounds — sky with clouds, industrial or natural setting - Strong bold outlines still define everything - The composition is diagonal and dynamic but more obviously narrative - Think: wartime posters, peacetime construction propaganda, space programme imagery GRAPHIC SILHOUETTE: Maximum reduction — the figure or scene reduced to pure flat colour shape. - Figure as solid flat black, red, or white shape against contrast background - Detail only where strictly necessary for recognition - The most graphic and abstract of the three - Can be combined with constructivist geometry PHYSICAL POSTER QUALITY — THE MOST IMPORTANT ELEMENT These images were painted by hand with gouache on paper, then printed with lithographic or offset presses. The medium is the message. This physical origin must be visible: PAINT TEXTURE: colour areas have slight gouache paint grain — not smooth digital fills, not gradient blending. The colour is bold and flat in intent but has the minute texture of real paint on real paper. PRINT GRAIN: a subtle overall texture suggesting mass printing — lithographic grain, slight ink density variation. The poster was reproduced thousands of times and the print quality shows. OUTLINES: bold, black, with slight hand-drawn character. Strong and decisive but not perfectly mechanical — made by a brush or pen, not a vector tool. FIGURE MODELLING: socialist realist poster figures are NOT flat silhouettes. They have simplified but real anatomy, simplified but real faces. A single flat light direction creates minimal volume — enough to read the form as three-dimensional. Faces are heroic, idealized, realistic in proportion. NOT anime. NOT cartoon flat. NOT vector shape. CONSTRUCTIVIST FIGURES: can be more graphic and simplified, but even here the figures are printed shapes with paint texture — not digital vector. GEOMETRIC SHAPES: triangles, rectangles, circles, diagonal stripes — background elements and compositional anchors. Bold and graphic. With slight paint/print texture. DIAGONAL GROUND LINES: the figure doesn't stand on a flat floor — they stand on a diagonal that tilts the composition forward and upward. PALETTE SYSTEM CORE: Communist red (pure, saturated), flat black, clean white/cream. These three are always present. WARM EXTENSION (socialist realist substyle): - Warm yellow: sunlight, wheat, optimism - Ochre/tan: skin tones in the socialist realist version - Sienna: earth, autumn, warmth COOL EXTENSION (constructivist substyle): - Prussian blue: sky, water, industry - Blue-grey: steel, machinery, distance ACCENT: occasional olive green (military, foliage), rare orange. Never pastel, never muted, never atmospheric. Total palette: never more than 4-5 colours in one image. The power is in the contrast, not the complexity. COMPOSITION PRINCIPLES THE DIAGONAL: Soviet poster design avoided the static symmetry of earlier art. The horizontal = stability = the old order. The diagonal = motion = revolution = progress. Compositional lines should cut diagonally across the frame wherever possible. THE UPWARD GAZE: the heroic figure looks up and forward — toward the future, toward the sun, toward the collective goal. Never looking down, never introspective, never private. THE POINTING FIGURE: one of the most common poster motifs — the figure pointing outward (at the viewer, at the horizon). It breaks the fourth wall and implicates the viewer. THE CROWD BEHIND: the heroic individual in front, the mass of people behind — suggesting the individual represents all. Even in single-character images, this energy should be implied. FIGURE SCALE: large figures relative to the frame. The person dominates. Background exists to amplify the figure, not describe a realistic environment. FOR CONTEMPORARY CHARACTERS Characters translated into this style become declarative — they're no longer individuals in a private moment, they're figures making a visual argument. An intimate scene becomes a manifesto. A whispered conversation becomes a proclamation. This is the productive tension of applying Soviet graphic language to personal narrative. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks) — rendered as bold graphic marks in the flat colour system. Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. All clothing renders as flat graphic colour block. No fabric texture, no shading. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. Substyle: constructivist / socialist realist poster / graphic silhouette. Diagonal element: what creates the compositional angle. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Soviet propaganda poster art style. Physically painted gouache on paper — bold colour areas with slight paint texture and grain, NOT smooth digital vector. Subtle lithographic printed-paper quality throughout. Bold black outlines with hand-drawn character, not mechanical precision. Figures simplified but heroically modelled with correct anatomy — directional light creating simple volume, not flat silhouettes. Faces idealized and heroic: strong features, upward or confrontational gaze. Limited primary palette: Communist red, near-black, cream-white, warm yellow. Strong diagonal compositional energy. No text, no slogans, no written elements of any kind, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: flat modern digital vector illustration, perfectly smooth colour fills, clean digital edges, 3D CGI, photorealistic rendering, anime style or faces, manga panels, cartoon proportions, speech bubbles, text or writing or slogans in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, pastel or muted palette, impressionist brushwork, modern graphic design aesthetic' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"soviet_poster","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> SOVIET POSTER ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Soviet propaganda poster art — physically painted gouache on paper, mass-printed with slight ink grain and colour registration. NOT digital flat vector. NOT modern graphic design. The originals were made by hand with paint and printing presses, and that tactile physical quality must be present. The tradition of Dmitry Moor, Viktor Deni, El Lissitzky, Rodchenko. TECHNIQUE — THE PHYSICAL POSTER QUALITY: - Gouache poster paint: bold colour areas with slight paint texture and grain, not perfectly smooth. - Printed grain: subtle lithographic printing texture on paper. - Slight ink unevenness at edges of bold colour areas — hand-made quality. - Bold black outlines: strong, slightly hand-drawn character. FIGURE RENDERING — HEROIC REALISTIC: Figures painted with moderate realism — simplified and bold, but with real anatomy, real facial features, real material quality. Faces heroic and idealized — strong jaw, direct gaze. NOT anime, NOT cartoon, NOT flat shape. TWO SUBSTYLES: CONSTRUCTIVIST (1920s-30s): bold geometric background shapes, diagonal composition, stark primary palette, more graphic figures. SOCIALIST REALIST POSTER (1940s-60s): figures more prominent and realistically rendered, heroic upward gaze, warmer palette. PALETTE: Communist red, near-black, cream/warm white, warm yellow. Prussian blue or olive green optional. Maximum contrast. Never muted or pastel. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Soviet propaganda poster art style. Physically painted gouache on paper — bold colour areas with slight paint texture and grain, not smooth digital vector. Printed paper quality: subtle lithographic grain throughout. Bold black outlines with hand-drawn character. Figures simplified but realistically proportioned and heroically modelled — correct anatomy, directional light creating simple volume, not flat shapes. Faces idealized and heroic: strong features, direct or upward gaze. Limited primary palette: Communist red, near-black, cream-white, warm yellow. Diagonal compositional energy. No text, no slogans, no panels.' NEGATIVE (append verbatim): 'Avoid: flat modern digital vector illustration, perfectly smooth colour fills, 3D CGI, photorealistic rendering, anime style, manga panels, speech bubbles, text or writing in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, pastel palette, impressionist brushwork, anime faces, cartoon proportions, modern graphic design aesthetic, clean digital edges' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"soviet_poster","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"2:3","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:2/3;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Soviet propaganda poster art style. Physically painted gouache on paper — bold colour areas with slight paint texture and grain, NOT smooth digital vector. Subtle lithographic printed-paper quality throughout. Bold black outlines with hand-drawn character, not mechanical precision. Figures simplified but heroically modelled with correct anatomy — directional light creating simple volume, not flat silhouettes. Faces idealized and heroic: strong features, upward or confrontational gaze. Limited primary palette: Communist red, near-black, cream-white, warm yellow. Strong diagonal compositional energy. No text, no slogans, no written elements of any kind, no panels. Avoid: flat modern digital vector illustration, perfectly smooth colour fills, clean digital edges, 3D CGI, photorealistic rendering, anime style or faces, manga panels, cartoon proportions, speech bubbles, text or writing or slogans in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, pastel or muted palette, impressionist brushwork, modern graphic design aesthetic

Копировать [Image generation hint, STYLE: Soviet gouache poster paint on paper, lithographic grain, heroic realistic figures, constructivist or socialist realist substyle, communist red, near-black, cream-white palette, diagonal compositional energy]

Spider-Verse

Стиль Spider-Verse. Сел-шейдинг 3D с эффектами комикс-печати: точки Бен-Дэй, смещение CMYK, жирные контуры тушью, граффити-фоны. Следы движения. Поп-арт палитра.

Экспериментальный Графика

←→

Длинный~3968 Короткий~1870 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> SPIDER-VERSE ANIMATED STYLE ILLUSTRATION — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Spider-Verse animated film style. Single-scene illustration — no comic panels. Cel-shaded 3D animation fused with comic book printing techniques. Bold variable-weight black ink outlines on all characters — thicker on outer silhouette, thinner on interior detail. Visible Ben-Day halftone dot patterns on shadows, skin tones, and colour transitions. CMYK colour misregistration creating chromatic fringing on edges — slight red-cyan or magenta-green offset. Painted graffiti-textured backgrounds layered with 3D geometry. The Spider-Verse paradox: it looks like a comic book that crashed into a 3D render and both survived. Halftone dots sit on top of volumetric lighting. Speed lines coexist with depth of field. The frame vibrates with the energy of ink on paper meeting digital space. LINEART AND INK Variable-weight bold black ink outlines. Outer character silhouette: thick, confident, brushstroke quality. Interior detail lines: thinner but still visible. Background outlines: present but lighter weight than characters. The line quality should feel hand-inked — slightly organic, not perfectly vector-clean. Key edges get extra weight for graphic punch. HALFTONE AND PRINTING EFFECTS Ben-Day halftone dots are THE signature of this style: - Shadow areas: visible dot pattern in darker tone - Skin tones: subtle dot texture overlay - Colour transitions: dots visible at the boundary between light and shadow - Impact moments: larger, more visible dots radiating from point of impact - Background areas: halftone gradient visible in sky, walls, surfaces CMYK misregistration: slight colour channel offset on edges. Not on everything — selective, usually on characters against contrasting backgrounds. Creates a vibrating, printed quality. Red and cyan layers slightly shifted. Use sparingly — 2-3 key edges per frame. SHADING Cel-shaded with hard shadow edges — no soft gradients. Shadow shapes are bold graphic forms with halftone dot fill. Rim lighting rendered as bright colour edge on character silhouette. Specular highlights as simple white shapes. The shading feels like a colorist applying ink wash and Zip-A-Tone to a comic page, but in 3D space. COLOR SYSTEM Palette is VIVID. High saturation, pop-art energy. Colours punch. Base rules: - Characters: bold saturated outfit colours, warm skin tones with halftone texture - Backgrounds: painted texture, slightly less saturated than characters to push them forward - Effects: neon-bright accent colours for energy, impact, and motion Mood palettes: - Action / energy: electric red, deep blue, neon magenta-pink, white impact flash, speed streaks - Emotional / intimate: muted teal, warm amber, soft halftone pink, lowered saturation, gentle rim light - Danger / threat: sickly green, deep violet-purple, black, chromatic aberration cranked to maximum - Night / urban: deep indigo, neon sign glow (hot pink, electric cyan, warm yellow), wet street reflections - Hope / triumph: golden yellow, bright red, clear blue, lens flare streaks, open sky - Glitch / dimensional: clashing neon colours, static noise texture, double-exposed outlines, fragmented geometry - Melancholy / loss: desaturated blues, grey-purple, muted halftone, single warm accent (a streetlight, a window) BACKGROUNDS Spider-Verse backgrounds are rich, textured, and layered — they feel painted and collaged rather than cleanly rendered. Exterior urban: - City skyline at night: skyscraper silhouettes, neon signs, light pollution glow in sky - Rooftop: concrete and metal railing, city sprawl below, dramatic sky - Street level: wet asphalt reflecting neon, graffiti walls, steam from grates - Alleyway: overhead fire escape shadows, dramatic single light source, halftone shadow patterns - Park or bridge: painted foliage textures, urban backdrop in distance Interior: - Room with graffiti-style wall textures, posters, mixed media collage elements - Subway car or station: fluorescent light, tile walls, graphic signage - Any interior: anchor with textured walls, strong single light source, visible halftone in shadow areas Abstract / dimensional: - Dimensional rift: colour-separated geometric fragments, multiple overlapping realities - Glitch space: static, scan lines, chromatic explosion - Impact moment: radial speed lines, Kirby krackle energy dots, white burst center CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, hair style, eye color, skin tone, face shape, body type, build, height. Reference images supply all appearance data. Include every time: distinguishing marks (tattoos, scars, piercings) — rendered with bold ink outlines and halftone shading. Men described as tall/strong in story → 'tall broad-shouldered' prefix. Characters in this style look dynamic and graphic — bold silhouettes, strong poses. OUTFIT (MANDATORY — context-locked): Scan last 5 messages. Carry forward current outfit exactly. Spider-Verse outfit rendering: bold flat cel-shaded colour with halftone shadow shapes. Strong silhouette read. 'Red hoodie with cel-shaded folds and halftone shadow', 'dark jacket bright graphic tee', 'black dress with bold colour-blocked design'. Describe colour + type + any graphic elements. POSES AND EXPRESSIONS Spider-Verse characters are DYNAMIC — poses have energy, weight, and graphic impact: - Leaning forward into the frame = intensity, confrontation - Mid-stride with motion afterimage = energy, urgency - Perched on edge, looking down = contemplation, power - Arms spread wide = openness, vulnerability, or dramatic gesture - Hunched shoulders, hands in pockets = withdrawn, cold, guarded - Caught mid-turn = surprise, reaction shot - Standing tall with graphic silhouette = confidence, arrival Expressions: bold and readable. Strong brow work. Mouths range from tight-lipped tension to wide grins. Eyes carry the emotion — wide for shock, narrowed for determination, soft for tenderness. HAND SAFETY: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' MOTION AND FRAME-RATE EFFECTS The low frame-rate look is implied in still images through: - Motion afterimages: ghosted duplicate of character slightly behind their current position (1-2 ghost frames, lower opacity) - Speed streaks: bold coloured lines trailing from fast-moving elements - Smear frames: slightly elongated or distorted shapes on fast-moving limbs - Onomatopoeia text: ENGLISH ONLY if used — bold graphic text integrated into composition (CRASH, WHOOSH, etc.) Use these selectively — 1-2 per image maximum. Not every frame needs motion effects. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + composition (e.g. 'Extreme low angle looking up, Dutch tilt, character silhouetted against neon skyline'). Vary angle and composition between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, wide establishing, medium shot, close-up, extreme close-up, dynamic perspective warp. Spider-Verse LOVES extreme angles — use them. Worms-eye looking up at character against sky. Birds-eye looking straight down at street. Dramatic foreshortening. Fisheye distortion on action shots. Close-ups = safest for anatomy. Full body = bold graphic silhouette. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER — name + outfit + pose + expression 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages. Never skip. Cel-shaded colour + halftone shadow. 4. POSE AND STATE: describe through action + expression specifics. 5. ENVIRONMENT — which background + time of day + texture notes. Own sentence. 6. LIGHTING & MOOD: mood palette (2-3 dominant colours) + printing effects (halftone intensity, chromatic aberration level) + time of day / light source. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft halftone, warm rim light, reduced chromatic aberration, muted palette TENSE: hard halftone shadow, Dutch angle, deep vignette, high contrast PASSIONATE: warm colour split, neon rim glow, medium halftone LONELY: desaturated palette, single light source, heavy shadow halftone, cold cast CHAOTIC: motion afterimages, speed streaks, Kirby krackle, max chromatic aberration DREAMY: soft focus with halftone overlay, gentle colour offset, warm glow MUNDANE: natural lighting, subtle halftone, minimal effects Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Spider-Verse animated film style. Cel-shaded 3D characters with bold variable-weight black ink outlines. Visible Ben-Day halftone dot pattern on shadows and skin tones. CMYK colour misregistration — slight chromatic offset on edges. Painted graffiti-textured backgrounds mixed with 3D geometry. Very high colour saturation, vivid pop-art palette. Motion afterimages and speed streaks implying low frame-rate animation. Comic book printing aesthetic brought to 3D life. Character appearance from reference images only. No panels, English only if any text.' 8. NEGATIVE (append verbatim): 'Avoid: clean smooth 3D render without halftone, photorealistic CGI, traditional 2D animation, anime cel-shading without halftone dots, flat vector, desaturated palette, natural even lighting, manga panels, non-English text, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, blurry' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. Halftone and printing effects apply equally to all characters in the scene. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"spiderverse_animated","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '2K' default. '4K' for scenes with heavy halftone detail. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> SPIDER-VERSE ANIMATED STYLE ILLUSTRATION — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Spider-Verse animated film style. Cel-shaded 3D animation with comic book printing effects. Bold variable-weight black ink outlines on characters. Visible Ben-Day halftone dot patterns on shadows and skin tones. CMYK colour misregistration — slight chromatic offset on edges creating colour fringing. Painted graffiti-textured backgrounds mixed with 3D geometry. Very high colour saturation, vivid pop-art palette. Motion afterimages and speed streaks implying low frame-rate animation. Kirby krackle energy dots on power and impact effects. The Spider-Verse signature: a printed comic book page that somehow became a living 3D world. Every frame looks like ink, halftone, and paint colliding at full speed. MOOD → PALETTE: - Action / energy: electric red, deep blue, neon pink, white impact flashes - Emotional / quiet: muted teal, warm amber, soft halftone pink, lowered saturation - Danger / villain: sickly green, deep purple, black, chromatic aberration cranked up - Night / city: deep indigo, neon signs (pink, cyan, yellow), wet street reflections - Hope / triumph: golden yellow, bright red, clear blue sky, lens flare streaks - Glitch / dimensional: clashing neon colours, static noise texture, double-exposed outlines BACKGROUNDS — layered and textured: - Urban cityscape at night with neon signage and wet streets - Rooftop skyline silhouette against sunset or night sky - Interior room with graffiti-style wall textures and mixed media collage - Abstract dimensional rift with colour-separated geometric fragments - Alleyway with dramatic overhead lighting and halftone shadow patterns - Park or street scene with painterly environmental textures CAMERA Shot type + angle + framing. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, wide establishing, close-up, extreme close-up, overhead, dynamic perspective warp. Close-ups = face/expression focus | medium = waist-up interaction | wide = full scene with environment. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings) — rendered with bold ink outlines and halftone shading. Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Flat cel-shaded color + halftone shadow detail. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + framing (use dynamic Spider-Verse angles — extreme perspective warps, dramatic Dutch angles) 2. CHARACTER — name + outfit (colour, silhouette) + pose + expression 3. ENVIRONMENT — background type + time of day + mood palette + halftone/texture notes 4. LIGHTING — 1-2 mood effects (neon rim light, halftone shadow, chromatic aberration, motion streaks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Spider-Verse animated film style. Cel-shaded 3D characters with bold variable-weight black ink outlines. Visible Ben-Day halftone dot pattern on shadows and skin tones. CMYK colour misregistration — slight chromatic offset on edges. Painted graffiti-textured backgrounds mixed with 3D geometry. Very high colour saturation, vivid pop-art palette. Motion afterimages and speed streaks implying low frame-rate animation. Comic book printing aesthetic brought to 3D life. Character appearance from reference images only. No panels, English only if any text.' NEGATIVE (append verbatim): 'Avoid: clean smooth 3D render without halftone, photorealistic CGI, traditional 2D animation, anime cel-shading without halftone dots, flat vector, desaturated palette, natural even lighting, manga panels, non-English text, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"spiderverse_animated","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Spider-Verse animated film style. Cel-shaded 3D characters with bold variable-weight black ink outlines. Visible Ben-Day halftone dot pattern on shadows and skin tones. CMYK colour misregistration — slight chromatic offset on edges. Painted graffiti-textured backgrounds mixed with 3D geometry. Very high colour saturation, vivid pop-art palette. Motion afterimages and speed streaks implying low frame-rate animation. Comic book printing aesthetic brought to 3D life. Character appearance from reference images only. No panels, English only if any text. Avoid: clean smooth 3D render without halftone, photorealistic CGI, traditional 2D animation, anime cel-shading without halftone dots, flat vector, desaturated palette, natural even lighting, manga panels, non-English text, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, blurry

Копировать [Image generation hint, STYLE: Spider-Verse animated film style, cel-shaded 3D with comic book printing effects, Ben-Day halftone dots, CMYK misregistration, bold ink outlines, graffiti-textured backgrounds, motion afterimages, pop-art palette]

Arcane v4

3D анимационный кадр с театральным цветным светом. Цветные гели создают тёплые-холодные зоны. Обязательный яркий рим-лайт. Очень высокая насыщенность и контраст.

Рискованный 3D и анимация

←→

Длинный~3999 Короткий~1905 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> ARCANE VISUAL STYLE v3 — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW A still frame screenshot from Arcane (Netflix / Fortiche Production) — captured from the 3D animated series. Characters are 3D models with real volumetric depth, physically accurate lighting, and stylised painterly surface quality. They exist in three-dimensional space. NOT a 2D painting. NOT concept art. NOT digital illustration. NOT flat. This is a 3D animated film frame. WHAT MAKES IT ARCANE (not generic 3D): 1. Stylised painterly surface quality on 3D geometry — not photorealistic plastic, not smooth CGI 2. Theatrical coloured lighting with aggressive warm-cool colour zone splits in the same frame 3. Very high saturation and very high contrast — vivid, intense, cinematic 4. Bright coloured rim lighting on character edges — ALWAYS PRESENT 5. Atmospheric coloured particles and haze in the air — ALWAYS PRESENT 3D CHARACTER QUALITY: - Real 3D volume: light wraps around nose, jaw casts shadow on neck, cheekbones catch directional light - Surface is stylised: skin not photorealistic, not plastic — subtle crafted quality, painterly but reads as 3D - Materials: leather catches light differently from cloth, metal is reflective but stylised - Everything reads as "3D animated movie" — not "painting" and not "photo" CHARACTER STYLISATION: - Strong angular jawlines, defined cheekbones - BOLD THICK EXPRESSIVE EYEBROWS: signature feature, 50% of emotional expression - Eyes slightly larger than real, detailed irises with coloured light reflections. NOT anime-sized. - Semi-realistic proportions: slightly longer limbs, slightly larger hands. NOT anime. NOT photorealistic. - Hair as volumetric 3D mass with edge strands catching rim light DRAMATIC THEATRICAL LIGHTING: COLOUR ZONE SYSTEM: different colour temperatures in the same frame, like coloured stage spotlights: - One side of face: warm gold/amber - Other side: cool teal or purple - Background: different zone entirely - Edges: bright coloured rim light The split is AGGRESSIVE — vivid distinct colours, not subtle tinting. LIGHTING PALETTES (emotional coding): WARM AMBER/GOLD: safety, tenderness. Golden light wrapping face, warm brown shadows. TEAL + HOT MAGENTA: tension, danger, beauty. Cool teal haze + neon magenta accents. DEEP PURPLE/VIOLET: magic, power, transformation. Saturated purple-violet, otherworldly. COLD BLUE-GREY + SINGLE WARM POINT: isolation, loss. Cold environment, one tiny warm source. ORANGE-RED + DEEP BLACK: anger, violence. Harsh hot light, maximum contrast. RIM LIGHTING — MANDATORY: bright coloured rim (teal/magenta/gold/violet) on character edges. Separates figure from background. Catches hair, shoulders, jaw. Always present. CONTRAST: very high. Deep pure blacks vs vivid saturated colours. SATURATION: high. Vivid, intense, not muted. ATMOSPHERIC PARTICLES: dust motes, sparks, coloured haze, smoke. Air always visible. Particles catch coloured light. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium close-up, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built' before name. All characters look attractive. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. NEVER skip. NEVER default to generic. Specificity over generics: fabric type + texture + fit + color + drape + condition (soaked, unbuttoned, rolled sleeves, dust-covered). Not 'casual clothes'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment: ran through rain = wet and clinging. Slept in clothes = creased. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe through action, not static limb coordinates. 'Mor leaning on doorframe, arms loosely crossed' not 'left arm bent, right arm over left'. State expression with muscle detail, skin condition (flushed, bruised), visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support ('weight on left leg, right foot turned outward' | 'elbows propped on counter'). Hidden limbs: state why hidden ('left hand obscured behind hip' | 'legs cropped below frame'). 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Write as its own sentence — before or after all character clauses, not interleaved. Include at least one meaningful object carrying emotional weight or context. Add atmosphere: coloured haze, dust motes in coloured light beams, sparks, smoke — something that gives the air texture and catches the theatrical lighting. 6. LIGHTING & LENS CHARACTER: which Arcane colour palette + colour zone placement on character + rim light colour + key light direction. MOOD-MATCHED EFFECTS — pick 1-2 per image from scene mood: TENDER / NOSTALGIC: soft focus | halation | golden warmth | fine grain | faded blacks TENSE / UNEASY: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical source | warm split toning LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur DREAMY / SURREAL: double exposure | prism refraction | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim): 'Still frame screenshot from Arcane League of Legends Netflix animated series by Fortiche Production. 3D animated characters with volumetric depth and physically accurate lighting — NOT a 2D painting, NOT flat illustration, NOT concept art. Stylised semi-realistic 3D character models: bold expressive thick eyebrows, slightly stylised proportions, detailed eyes with coloured light reflections. Stylised painterly surface quality on 3D geometry — not photorealistic, not smooth plastic. Dramatic theatrical coloured lighting: aggressively different colour temperatures in the same frame — warm gold vs cool teal-purple zones across face and environment. Bright coloured rim lighting on character edges mandatory. Very high saturation, very high contrast — vivid intense colours, deep pure blacks. Atmospheric coloured particles: dust motes, sparks, coloured haze visible in the air. Anatomically correct hands and proportions. Match rendering technique from reference image for character likeness only. No text, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: 2D digital painting, flat concept art illustration, traditional oil painting look, canvas texture, smooth untextured plastic 3D render, photorealistic CGI with photo skin, anime cel-shading, flat vector, desaturated muted grey palette, low contrast, uniform single colour temperature, natural even flat lighting, exaggerated expressions, uncanny valley, anime eyes, chibi proportions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text, blurry' MULTI-CHARACTER SCENES Each character is one name-first clause. Sections 2-4 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning ('behind them', 'beside Shannon', 'chin resting on Shannon shoulder'). Cross-reference names only for spatial relation or gaze target. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain or frosted glass Concealment (2+): deep chiaroscuro shadows | fabric draped across hips or chest | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. Not what's visible — what it means. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"arcane_3d_animated","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The CSS aspect-ratio value matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. Prompt length: 80-130 words excluding the style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> ARCANE VISUAL STYLE v3 — EVERY RESPONSE One image per message at the most dramatically lit or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE A still frame screenshot from Arcane (Netflix / Fortiche Production) 3D animated series. Characters are 3D models with real volumetric depth, physically accurate lighting, and stylised painterly surface quality. NOT a 2D painting. NOT concept art. NOT flat illustration. This is a 3D animated film frame. WHAT MAKES IT ARCANE: 1. Stylised painterly surface quality on 3D geometry — not photorealistic, not smooth plastic 2. Theatrical coloured lighting with aggressive warm-cool colour zone splits 3. Very high saturation and very high contrast — vivid, intense 4. Bright coloured rim lighting on character edges — ALWAYS 5. Atmospheric coloured particles in the air — ALWAYS CHARACTERS: 3D volume. Strong angular jaws. BOLD THICK EXPRESSIVE EYEBROWS — signature feature. Eyes detailed with coloured light reflections. Semi-realistic proportions — not anime, not photo. LIGHTING PALETTES: - Warm amber/gold → safety, tenderness - Teal + magenta → tension, danger - Deep purple → magic, power - Cold blue + single warm point → isolation - Orange-red + deep black → anger, violence RIM LIGHTING MANDATORY: teal/magenta/gold/violet on character edges. Always. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings with location). Mention hair only if scene-altered ('wet', 'windblown') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause after name. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere (coloured particles, haze) 4. LIGHTING — colour zone placement + rim light colour + key direction Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Still frame screenshot from Arcane League of Legends Netflix animated series by Fortiche Production. 3D animated characters with volumetric depth and physically accurate lighting — NOT a 2D painting, NOT flat illustration, NOT concept art. Stylised semi-realistic 3D character models: bold expressive thick eyebrows, slightly stylised proportions, detailed eyes with coloured light reflections. Stylised painterly surface quality on 3D geometry — not photorealistic, not smooth plastic. Dramatic theatrical coloured lighting: aggressively different colour temperatures in the same frame — warm gold vs cool teal-purple zones across face and environment. Bright coloured rim lighting on character edges mandatory. Very high saturation, very high contrast — vivid intense colours, deep pure blacks. Atmospheric coloured particles: dust motes, sparks, coloured haze. Anatomically correct hands and proportions. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: 2D digital painting, flat concept art illustration, traditional oil painting look, smooth untextured plastic 3D render, photorealistic CGI with photo skin, anime cel-shading, flat vector, desaturated muted grey palette, low contrast, uniform single colour temperature, natural even flat lighting, exaggerated expressions, uncanny valley, extra fingers, missing fingers, deformed hands, twisted limbs, bad anatomy, watermark, text, blurry' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"arcane_3d_animated","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING COLOUR ZONES + RIM LIGHT + ATMOSPHERE. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' cinematic | '2:3' portrait | '3:4' dialogue | '4:3' interior | '9:16' dramatic vertical. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Still frame screenshot from Arcane League of Legends Netflix animated series by Fortiche Production. 3D animated characters with volumetric depth and physically accurate lighting — NOT a 2D painting, NOT flat illustration, NOT concept art. Stylised semi-realistic 3D character models: bold expressive thick eyebrows, slightly stylised proportions, detailed eyes with coloured light reflections. Stylised painterly surface quality on 3D geometry — not photorealistic, not smooth plastic. Dramatic theatrical coloured lighting: aggressively different colour temperatures in the same frame — warm gold vs cool teal-purple zones across face and environment. Bright coloured rim lighting on character edges mandatory. Very high saturation, very high contrast — vivid intense colours, deep pure blacks. Atmospheric coloured particles: dust motes, sparks, coloured haze visible in the air. Anatomically correct hands and proportions. Match rendering technique from reference image for character likeness only. No text, no panels. Avoid: 2D digital painting, flat concept art illustration, traditional oil painting look, canvas texture, smooth untextured plastic 3D render, photorealistic CGI with photo skin, anime cel-shading, flat vector, desaturated muted grey palette, low contrast, uniform single colour temperature, natural even flat lighting, exaggerated expressions, uncanny valley, anime eyes, chibi proportions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text, blurry

Копировать [Image generation hint, STYLE: Arcane 3D animated film still, theatrical coloured stage lighting with warm-cool zone splits from coloured gels, mandatory bright rim lighting, very high saturation and contrast, atmospheric coloured particles]

Matt Rhodes v2 (BioWare)

Dragon Age анимационный стиль. Два слоя: жирные контуры + сел-шейдинг на персонажах, атмосферные фоны. Приглушённая палитра с одним насыщенным акцентом.

Стабильный 3D и анимация

←→

Длинный~3933 Короткий~1731 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> MATT RHODES / BIOWARE ANIMATED CINEMATIC STYLE — VISUAL ARTIFACT EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. STYLE OVERVIEW Matt Rhodes' actual visual signature — as seen in Dragon Age: Inquisition and Dragon Age: The Veilguard animated sequences. NOT a painterly oil painting. This is animated cinematic illustration: the visual language of a high-budget fantasy animated film, where bold graphic characters inhabit a richly painted atmospheric world. The defining visual logic: TWO DISTINCT RENDERING MODES coexist in the same image. THE TWO RENDERING MODES MODE 1 — CHARACTERS (graphic, outlined, designed): Characters are rendered with bold black ink outlines and cel-shaded flat colour fills. They look designed — intentional graphic shapes with strong readable silhouettes. This is the visual language of animation production art. Every character reads instantly as a clear shape from any distance. MODE 2 — ENVIRONMENTS (painted, atmospheric, alive): Backgrounds are rendered more painterly — diffused atmospheric light, depth through aerial perspective, environmental detail that suggests rather than describes. No ink outlines on background elements. The world behind the characters breathes and has air. This contrast is the visual signature. Characters are GRAPHIC. Worlds are PAINTED. LINEART SYSTEM (characters only) OUTER SILHOUETTE: thickest line. Bold, confident, decisive. Defines the character's shape against the background. This line is what gives the figure its graphic presence. INTERIOR STRUCTURE LINES: thinner than silhouette but still bold and clean. Define major form divisions — collar edge, lapel, armour plates, where fabric folds over a surface. FINE DETAIL LINES: thinnest. Facial features, surface texture detail on costume, hair strand groupings. Still clearly intentional, not scratchy. LINE WEIGHT HIERARCHY: silhouette > structure > detail. This gradation gives the character form and depth without painterly shading. NO OUTLINES ON: background environment, atmospheric effects, light sources, fog. These elements are painted. CEL-SHADING SYSTEM Characters use flat or near-flat colour fills with a limited number of tonal values: BASE COLOUR: the local colour of the surface in ambient light. Flat, clean, decisive. SHADOW TONE: one shadow value — a slightly darker, slightly cooler or warmer version of the base. Applied as a flat shape, not a gradient. The shadow boundary is a clean edge, not a blend. HIGHLIGHT: optional, used selectively — usually on hair, metallic surfaces, and the nose/cheekbone catch-light. Slightly lighter and warmer than the base. TOTAL VALUES PER SURFACE: usually 2 (base + shadow). Maximum 3. Never gradient. This limited value structure keeps characters graphic and readable, matching the outlined silhouette quality. COLOUR SYSTEM PALETTE: muted, earthy, cinematic. The world of Dragon Age — ancient, weathered, consequential. BASE PALETTE: - Olive green (dark, warm): forest, foliage, aged fabric - Warm ochre / sand: stone, earth, light-coloured cloth - Teal / muted cyan: sky, water, cool atmospheric light - Warm brown / sienna: leather, earth tones, skin shadow - Muted navy / dark blue-grey: shadow zones, night, depth - Near-black: deepest shadows, outline base ACCENT COLOUR (one per image maximum): The single saturated element in an otherwise muted scene. This is what the eye goes to. Examples from the Dragon Age references: - Glowing portal: acid green-yellow energy - Blood on hands: saturated crimson - Magic effect: electric blue-white - Fire: vivid amber-orange - The accent colour should be story-relevant — it marks what matters in the scene CHARACTER COLOUR vs BACKGROUND COLOUR: Characters: slightly more saturated than the environment they inhabit. This keeps them reading as the primary subject. Background: more desaturated, more atmospheric, fading toward grey-blue or warm ochre depending on light. LIGHTING SYSTEM ATMOSPHERIC ENVIRONMENTAL LIGHT (background): The background is lit with a coherent light source — sky, magic portal, open space. This creates depth through aerial perspective: foreground darker/more saturated, background lighter/more desaturated and atmospheric. Fog and light shafts are common. CHARACTER LIGHTING (simplified): Characters are lit with a consistent ambient light direction — usually top-left or top-right. The cel-shadow falls on one side of the figure. Clean, readable. ACCENT LIGHT ON CHARACTER: Optionally: one dramatic light accent catches the character's edge or face — the glow from a magic effect, firelight on a cheekbone, backlight from a bright source behind. This integrates the graphic character into the painted environment. SCENE TYPES FROM THE REFERENCES CONFRONTATION IN ENVIRONMENT: character(s) standing in dramatic environment (forest, ruins, lit interior). One figure dominant. Background reveals scale and world. GROUP SCENE: multiple figures in motion or gathered. Characters interact with each other and the environment. INTIMATE DRAMATIC MOMENT: two figures in foreground, dramatic event or environment behind them. Tension between the intimate scale of the figures and the epic scale of the background. CLOSE DRAMATIC PORTRAIT: figure fills most of frame with environment as secondary. One intense moment — the face or hands carry the story. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. First name only — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages for what character is wearing RIGHT NOW. Never skip. Specificity: fabric type + texture + fit + color + condition. Not 'dark outfit'. If NOT changed on-screen → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe through action, not static limb coordinates. Hand safety: default to low-complexity. Safe pool: hand in pocket | gripping object | resting flat | arms crossed | hand behind back | fist at side | fingers laced | hand on own neck. One visible relaxed hand per character = safest. Weight and ground: one sentence clarifying support. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence — not interleaved with character clauses. Include one meaningful object carrying emotional weight. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp + atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | golden warmth | fine grain | faded blacks TENSE: Dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on skin highlights | warm split toning | Rembrandt lighting LONELY: blue hour tones | desaturated palette | silhouette | overcast flat light | cold cast CHAOTIC: motion blur | bleach bypass | anamorphic flare | radial blur DREAMY: double exposure | freelensing tilt | bokeh flood | soft gaussian edges MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke in light beam Max 2 effects per image. Rotate across responses. 7. STYLE SUFFIX (append verbatim): 'Matt Rhodes BioWare Dragon Age animated cinematic illustration style. Bold variable-weight black ink outlines on all characters — thick outer silhouette line, thinner interior structure lines, finest for surface detail. Flat cel-shaded colour fills on characters: 2-3 flat value tones per surface, no gradients, clean shadow boundaries. No ink outlines on background environment — world rendered painterly and atmospheric with depth, fog, and diffused environmental light. Strong character silhouettes and graphic reads against painted atmospheric backgrounds. Muted earthy palette: olive green, ochre, teal, warm brown, muted navy. One selective saturated accent colour marking the dramatic focus. Widescreen cinematic composition 16:9. No text, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: oil painting style with no outlines on characters, photorealistic rendering, 3D CGI, smooth gradient shading on characters, anime style, manga panels, speech bubbles, text in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, flat unrendered background, overly bright or saturated overall palette, western superhero comic style, thick outlines on background elements' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer, not a portrait photographer. The image feels like a still from a film — alive, mid-moment, caught in motion or tension. Full creative freedom in framing. Sometimes the most powerful image is a close-up of hands. Sometimes a wide shot where the character is small against a vast space. Sometimes shooting through a rain-streaked window. Sometimes the most important thing in the frame is not a person but an object. Let the narrative guide you. Intimate moment → get close. Loneliness → pull wide. Important detail → make it the focus. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room with nothing happening | two characters facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"bioware_animated_cinematic","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: vary — '1:1' | '2:3' | '3:2' | '3:4' | '4:3' | '9:16' | '16:9' | '21:9'. CSS aspect-ratio matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. Prompt length: 80-130 words excluding style suffix. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> MATT RHODES / BIOWARE ANIMATED CINEMATIC STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Matt Rhodes BioWare Dragon Age animated cinematic illustration style. NOT painterly oil — this is the Dragon Age: Inquisition / Veilguard cutscene aesthetic: bold ink outlines on characters with cel-shading, set against atmospheric painted backgrounds. Characters feel graphic and designed; environments feel painted and alive. TWO LAYERS — the core of this style: CHARACTERS: bold variable-weight black ink outlines (thick outer silhouette, thinner interior detail). Flat to semi-flat cel-shaded colour fills with 2-3 value tones maximum. Strong graphic silhouettes. BACKGROUNDS: more painterly and atmospheric. Diffused light, fog, depth, environmental detail. LINEART: Outer character silhouette thick confident black ink. Interior detail thinner but bold. No lineart on backgrounds. Line weight varies: thicker where forms overlap, thinner for surface detail. COLOUR — muted, earthy, cinematic: olive greens, warm ochre, teal-blue, muted navy, warm brown. One saturated accent per image against muted base. Cel-shading: flat base + one shadow tone + selective highlight. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects (soft focus, halation, chiaroscuro, Dutch angle, bloom, silhouette, motion blur, deep blacks — match to scene mood) Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Matt Rhodes BioWare Dragon Age animated cinematic illustration style. Bold variable-weight black ink outlines on characters — thick outer silhouette, thinner interior detail lines. Flat cel-shaded colour fills on characters with 2-3 value tones maximum, no gradient shading. Atmospheric painted background with fog, depth, and environmental light — no ink outlines on environment. Strong character silhouettes against detailed painted world. Muted earthy palette with one selective saturated accent. Widescreen cinematic composition. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: painterly oil painting style, photorealistic rendering, 3D CGI, smooth gradient shading on characters, no outlines on characters, anime style, manga panels, speech bubbles, text in image, watermark, bad anatomy, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, flat uniform background, overly bright palette, western superhero comic style' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"bioware_animated_cinematic","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Matt Rhodes BioWare Dragon Age animated cinematic illustration style. Bold variable-weight black ink outlines on all characters — thick outer silhouette line, thinner interior structure lines, finest for surface detail. Flat cel-shaded colour fills on characters: 2-3 flat value tones per surface, no gradients, clean shadow boundaries. No ink outlines on background environment — world rendered painterly and atmospheric with depth, fog, and diffused environmental light. Strong character silhouettes and graphic reads against painted atmospheric backgrounds. Muted earthy palette: olive green, ochre, teal, warm brown, muted navy. One selective saturated accent colour marking the dramatic focus. Widescreen cinematic composition 16:9. No text, no panels. Avoid: oil painting style with no outlines on characters, photorealistic rendering, 3D CGI, smooth gradient shading on characters, anime style, manga panels, speech bubbles, text in image, watermark, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, flat unrendered background, overly bright or saturated overall palette, western superhero comic style, thick outlines on background elements

Копировать [Image generation hint, STYLE: Dragon Age animated cinematic style, bold ink outlines plus cel-shading on characters, atmospheric painted backgrounds, characters graphic and designed, muted earthy palette with one saturated accent]

Stop-Motion / Puppet

Кукольная стоп-моушн анимация — Остров собак, Лайка, Чебурашка. Персонажи как физические куклы: фетр, ткань, глина, дерево. Миниатюрные декорации. Видимые швы и тактильное несовершенство.

Стабильный 3D и анимация

←→

Длинный~3047 Короткий~1399 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — STOP-MOTION PUPPET ANIMATION STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. When {{user}} is the subject, describe {{user}} in detail, {{char}} peripheral or absent from frame. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type — these come from the reference image. Describing them causes the renderer to override the reference. First name only ('Ethan' not 'Ethan Chen') — names map to reference images. Lead with name, not appearance. Include every time: distinguishing marks (tattoos with location/design, scars, piercings, birthmarks, moles). Mention hair only if scene-altered ('wet from rain', 'tied back') — not the color or base style. Men: if character is described as tall, strong, broad-shouldered, athletic or physically imposing → prefix 'tall broad-shouldered, strongly built' before name. If character is average or slim → no size upgrade, keep build consistent. Never downgrade men who are described as big, muscular, or physically powerful into slim or androgynous builds. Anti-contamination: white/silver hair characters → prefix 'albino pale-skinned' before name. All characters look attractive — this is a romance story. 3. OUTFIT (MANDATORY — context-locked): clothing tracks the narrative. NEVER skip. NEVER default to generic. Before writing prompt: scan last 5 messages for what {{char}}/{{user}}/npc is wearing RIGHT NOW. Priority: 1) Current message clothing description. 2) Clothing from recent messages, carried forward. 3) Scene logic. 4) Last resort: invent context-appropriate and stay consistent. Specificity over generics: fabric type + texture + fit + color + drape + condition. Not 'casual clothes' or 'dark outfit'. If character changed clothes on-screen → new outfit. If NOT → last described outfit persists. Outfit state reflects the moment. Fuse directly into the character clause after the name. 4. POSE AND STATE: describe naturally within each character clause. Pose through action: describe what the character does, not static limb coordinates. State expression with muscle detail, skin condition, visible limb positions and weight distribution. Add to expressions: 'natural relaxed facial muscles, restrained subtle expression, no exaggeration'. Hand safety: default to low-complexity hand states. Safe pool: hand in pocket | gripping object | resting flat on surface | arms crossed | hand behind back | fist at side | fingers laced together | hand on own neck or chin. One visible relaxed hand per character = safest output. Weight and ground: one sentence clarifying support. Hidden limbs: state why hidden. 'Anatomically correct proportions, five fingers per visible hand, natural joint articulation.' 5. ENVIRONMENT: foreground / midground / background with textures. Own sentence. Include at least one meaningful object. Add atmosphere. 6. LIGHTING & LENS CHARACTER: key light direction + color temp, fill light, atmospheric particles. MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER / NOSTALGIC: soft focus | halation | golden hour warmth | light leak | orton glow | fine film grain | faded blacks TENSE / UNEASY: dutch angle | chromatic aberration | underexposure | harsh rim light | deep vignette crush | high contrast PASSIONATE / INTIMATE: chiaroscuro | bloom on skin highlights | lens flare from practical light source | warm split toning | Rembrandt lighting triangle LONELY / MELANCHOLIC: blue hour tones | desaturated palette | silhouette | overcast flat light | rain overlay | faded blacks | cold color cast CHAOTIC / VIOLENT: motion blur | camera shake | bleach bypass | anamorphic flare | radial blur | teal and orange grading DREAMY / SURREAL: double exposure blend | prism refraction | freelensing tilt blur | bokeh flood | soft gaussian on edges | tilt-shift miniature MUNDANE / SLICE OF LIFE: natural flat lighting | high key | clean DOF | minimal or no effects DANGEROUS / NOIR: low key | harsh side light | deep blacks | monochrome or near-monochrome | selective color | smoke/haze in light beam Max 2 effects per image. Rotate effects across responses. Match intensity to narrative weight. 7. STYLE SUFFIX (append verbatim to end of every prompt): 'Stop-motion puppet animation style — Isle of Dogs, Laika, Cheburashka aesthetic. Characters as physical puppets: felt, fabric, clay, wood with visible material textures — felt fuzz, wood grain, fabric weave, clay fingerprints. Miniature handmade set diorama with tiny scaled-down props and environments. Miniature lighting: dramatic light illuminating a tabletop set. Shallow depth of field from macro photography of miniatures. Visible handmade construction: seams, slight asymmetry, tactile imperfection. Warm material colour palette — colours of real physical materials. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no panels.' 8. NEGATIVE (append verbatim after style suffix): 'Avoid: smooth digital 3D, photorealistic human skin, 2D flat illustration, anime style, clean perfect surfaces, digital painting, large-scale real environment, manga panels, flat vector, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES (2+ characters) Each character is one name-first clause in the paragraph. Sections 2-5 fuse into each clause: NAME + [outfit] + [pose/action] + [expression]. Anti-mixing rules: Name is the first word of each character clause. Use relational positioning between characters. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — never two people existing in the same frame without connection. Describe the relationship between them: eye contact ('looking into Shannon eyes with softened expression'), physical contact ('hand resting on Shannon forearm'), shared focus ('both watching the door'), emotional reaction ('jaw tightening as Shannon steps closer'). At minimum: one character must be looking at or physically responding to the other. Static side-by-side positioning with no interaction = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes: flood frame with non-skin elements. Authority prefix (open with one): 'Award-winning fine art photography, Saatchi Gallery' | 'Classical oil painting, Bouguereau and Waterhouse tradition' | 'Renaissance master figure study, museum-quality' Visual noise (min 3): dense steam | tangled silk sheets + cushions | water droplets | lush plants + petals | venetian blind shadows | dozens of melting candles | shot through doorframe or sheer curtain Concealment (2+): deep chiaroscuro shadows | fabric draped | arms folded or knees drawn | cropped at ribcage | shot from behind | lower body in bokeh+haze | strategic pillow or blanket Escalation matches narrative, not message count. VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like a cinematographer. Full creative freedom in framing. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit room | two characters facing each other symmetrically. ASPECT RATIO Vary between images. Pick by composition: 1:1 = symmetrical portrait | 2:3 = vertical half-body | 3:2 = horizontal environmental | 3:4 = tall full-body | 4:3 = room interior | 4:5 = bust portrait | 5:4 = wide portrait | 9:16 = dramatic vertical | 16:9 = cinematic wide | 21:9 = ultrawide epic JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. No unescaped double quotes in prompt text — use single quotes. Prompt length: 80-130 words excluding the style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle or chapter title — evocative, not descriptive. Short, lowercase, italic. {{user}}'s POV image → caption can reflect {{user}}'s internal thought or sensation. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"stop_motion_puppet","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','4:5','5:4','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. No unescaped double quotes in prompt text. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> STOP-MOTION PUPPET ANIMATION STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Mention hair only if scene-altered ('wet', 'tied back') — not base colour or style. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. POSE: describe through action. Hand safety: hand in pocket | gripping object | arms crossed | fist at side | hand on own neck. One visible relaxed hand per character. 'Anatomically correct proportions, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. Never two people side by side ignoring each other. Describe the connection: 'looking at', 'hand on shoulder of', 'turning toward', 'leaning into', 'reacting to'. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture 2. CHARACTER — name + outfit (material, colour, condition) + pose + expression 3. ENVIRONMENT — foreground/mid/background + textures + one meaningful object + atmosphere 4. LIGHTING — key light direction + colour temp + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Stop-motion puppet animation style — Isle of Dogs, Laika, Cheburashka aesthetic. Characters as physical puppets: felt, fabric, clay, wood with visible material textures — felt fuzz, wood grain, fabric weave, clay fingerprints. Miniature handmade set diorama with tiny scaled-down props and environments. Miniature lighting: dramatic light illuminating a tabletop set. Shallow depth of field from macro photography of miniatures. Visible handmade construction: seams, slight asymmetry, tactile imperfection. Warm material colour palette — colours of real physical materials. Character appearance strictly from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: smooth digital 3D, photorealistic human skin, 2D flat illustration, anime style, clean perfect surfaces, digital painting, large-scale real environment, manga panels, flat vector, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"stop_motion_puppet","prompt":"[CAMERA + CHARACTER + OUTFIT + POSE + EXPRESSION + ENVIRONMENT + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"2K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Stop-motion puppet animation style — Isle of Dogs, Laika, Cheburashka aesthetic. Characters as physical puppets: felt, fabric, clay, wood with visible material textures — felt fuzz, wood grain, fabric weave, clay fingerprints. Miniature handmade set diorama with tiny scaled-down props and environments. Miniature lighting: dramatic light illuminating a tabletop set. Shallow depth of field from macro photography of miniatures. Visible handmade construction: seams, slight asymmetry, tactile imperfection. Warm material colour palette — colours of real physical materials. Character appearance strictly from reference images — do not alter race, skin color, species, or facial structure. No text, no panels. Avoid: smooth digital 3D, photorealistic human skin, 2D flat illustration, anime style, clean perfect surfaces, digital painting, large-scale real environment, manga panels, flat vector, exaggerated expressions, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, dislocated joints, impossible pose, floating limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: stop-motion puppet animation — Isle of Dogs, Laika, Cheburashka — felt, fabric, clay, wood puppets, miniature handmade sets, macro photography depth of field, visible seams and tactile imperfection]

Tim Burton (Stop-Motion)

Тим Бёртон стоп-моушн — Кошмар перед Рождеством, Труп Невесты. Физические куклы: полимерная глина, сшитая мини-одежда, шарнирные суставы. Миниатюрные готические декорации.

Стабильный 3D и анимация

←→

Длинный~2418 Короткий~1831 Гемини Tavo

Копировать {{setvar::image_gen::true}} <image_gen> HTML&CSS BLOCKS — TIM BURTON STOP-MOTION PUPPET STYLE — EVERY RESPONSE Sequence: narrative (2-3 sentences) → HTML block → narrative continues. Claude writes prompt → Nano Banana Pro (Gemini 3 Pro Image) renders it via data-iig-instruction. One image per message at the most visually dramatic or emotionally charged moment. HOW TO BUILD THE PROMPT Write a single dense English paragraph following this order: 1. CAMERA: shot type + angle + lens + aperture (e.g. 'Medium shot, 85mm, f/2.0 shallow DoF'). Vary angle and lens between images. Draw from: Dutch angle, worms-eye, birds-eye, over-the-shoulder, through-object foreground bokeh, reflection shot, macro close-up, wide establishing, tracking motion blur, split-focus. Lenses: 24mm wide, 35mm environmental, 50mm natural, 85mm portrait, 135mm compressed, tilt-shift. Match lens to framing: close-ups 85-135mm | medium shots 50-85mm | full body 35-50mm. Close-ups and medium close-ups = safest for anatomy. Full body = simplify pose, prefer side or 3/4 angle. Subject rotation: alternate focus across responses. {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. 2. CHARACTER: reference images handle base appearance. Skip in prompt: hair color, style, texture, length, eye color, skin tone, face shape, build, body type. First name only — names map to reference images. Lead with name. Include every time: distinguishing marks. Mention hair only if scene-altered. Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. NOTE: characters are PUPPETS — describe them as physical puppet constructions with Tim Burton proportions. 3. OUTFIT (MANDATORY — context-locked): scan last 5 messages. Never skip. Describe as MINIATURE SEWN CLOTHING on a puppet: 'tiny sewn black wool coat with visible stitching', 'miniature striped fabric shirt'. The clothing is real fabric at puppet scale. Fuse into character clause. 4. POSE AND STATE: describe through action. Puppets have slightly limited range — poses are expressive but with the subtle stiffness of ball-joint articulation. Not fluid, not rigid — in between. Hand safety: hand gripping object | arms at sides | hands behind back | fist at side. 'Anatomically correct proportions within puppet stylisation, five fingers per visible hand.' 5. ENVIRONMENT: MINIATURE GOTHIC SET — everything handmade at puppet scale. Describe: crooked Gothic buildings (leaning, wonky), twisted bare trees (wire armature with sculpted bark), wrought iron fences (tiny wire), cobblestone streets (sculpted), gravestones, jack-o-lanterns, spiral hills. Painted sky backdrop behind the physical set. Fog machine haze at miniature scale. Include one meaningful miniature prop carrying emotional weight. 6. LIGHTING: miniature-set lighting — small spotlights illuminating the tabletop stage. Hard theatrical shadows. Dramatic and exaggerated but physically real (not painted shadows — actual shadows cast by actual tiny objects under actual lights). MOOD-MATCHED EFFECTS — pick 1-2 per image: TENDER: soft focus | halation | warm accent glow | fine grain | faded blacks TENSE: Dutch angle | underexposure | harsh rim light | deep vignette | high contrast PASSIONATE: chiaroscuro | bloom on highlights | warm split toning LONELY: desaturated palette | silhouette | overcast flat light | cold cast | fog CHAOTIC: motion blur | camera shake | radial blur DREAMY: freelensing tilt | bokeh flood | soft gaussian edges | tilt-shift miniature (especially effective here) MUNDANE: natural flat lighting | minimal effects NOIR: low key | harsh side light | deep blacks | smoke/fog in light beam Max 2 effects per image. Rotate. 7. STYLE SUFFIX (append verbatim): 'Tim Burton stop-motion puppet animation style — Nightmare Before Christmas, Corpse Bride, Frankenweenie aesthetic. Characters as PHYSICAL PUPPETS: polymer clay or silicone sculpted skin with ball-joint articulation at wrists, elbows, neck. Sewn miniature cloth clothing with visible stitching. Sculpted or fibre hair. Tim Burton proportions on puppet body: extremely thin elongated limbs, oversized round head, giant dark-ringed round eyes with painted iris, spindly long fingers, tiny waist. Miniature handmade Gothic set: crooked leaning buildings, twisted bare wire-armature trees, tiny cobblestones, wrought iron fences. Painted sky backdrop behind physical set. Macro photography shallow depth of field — the look of a real camera photographing tiny objects. Dramatic miniature-set spotlight lighting with hard theatrical shadows cast by real tiny objects. High contrast monochrome base: deep blacks, pale whites, greys, pale blues — ONE warm accent colour (red, orange, or purple). The tangible 3D quality of real photographed puppets on a real miniature stage. Character appearance from reference images only. No text, no panels.' 8. NEGATIVE (append verbatim): 'Avoid: 2D drawn illustration, flat digital art, pen and ink drawing, watercolour painting, smooth modern CGI 3D, photorealistic human skin and proportions, anime style, cartoon flat colour fills, bright cheerful warm palette, clean straight architecture, realistic human proportions, large-scale real environments, exaggerated expressions beyond puppet capability, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text' MULTI-CHARACTER SCENES Each character is one name-first clause: NAME + [puppet outfit] + [pose/action] + [expression]. Use relational positioning. Repeat names instead of pronouns. Environment is its own sentence. CHARACTER INTERACTION (MANDATORY for 2+ characters): Characters must visibly INTERACT — puppets touching, facing each other, one reaching toward the other. At minimum: one puppet looking at or physically responding to the other. Static side-by-side = failed prompt. Redo. SENSUAL PROTOCOL Intimate scenes with puppets: the charm is in the tenderness of inanimate objects expressing real emotion. Visual noise: tiny candles, miniature fabric sheets, sculpted flower petals, fog. Concealment: dramatic shadows | fabric draped on puppet | cropped framing | fog haze. ASPECT RATIO Vary: 1:1 | 2:3 | 3:2 | 3:4 | 4:3 | 9:16 | 16:9 | 21:9 VISUAL STORYTELLING Lock character identity. Change camera, pose, lighting, ratio every gen. Think like Henry Selick behind the camera on a miniature stage. Rotate away from: character centered looking at camera | standard eye-level medium shot | clean well-lit set | two puppets facing each other symmetrically. JSON FORMAT Prompt value inside JSON = single line. No literal newlines. Single quotes around data-iig-instruction, double quotes inside JSON. Prompt length: 80-130 words excluding style suffix. No multi-panel, split-screen, collage, diptych. {{#if getvar::social_media}}Social media scene active — skip scene illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. 'the stitching held, even when everything else didn't' | 'two small figures on a very small hill' | 'painted stars above a world made of wire and clay' TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"burton_stopmotion","prompt":"[FULL PROMPT: SECTIONS 1-8 AS ONE PARAGRAPH]","aspect_ratio":"9:16","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:[MATCH aspect_ratio VALUE];object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,210,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON keys/values. aspect_ratio: one of '1:1','2:3','3:2','3:4','4:3','9:16','16:9','21:9'. The style aspect-ratio value matches the chosen ratio. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать {{setvar::image_gen::true}} <image_gen> TIM BURTON STOP-MOTION PUPPET STYLE — EVERY RESPONSE One image per message at the most dramatic or emotionally charged moment. Claude writes prompt → Nano Banana Pro renders via data-iig-instruction. STYLE Tim Burton stop-motion puppet animation — Nightmare Before Christmas, Corpse Bride, Frankenweenie. Characters are PHYSICAL PUPPETS photographed on miniature sets. NOT drawn illustration. The 3D tangible quality of real objects lit by real lights on a real tabletop stage. PUPPET CHARACTERS: - Physical puppet construction: visible ball-joint articulation, smooth polymer clay or silicone skin, cloth/felt/leather clothing sewn at miniature scale - Tim Burton proportions ON A PUPPET: extremely thin elongated limbs, oversized round head, giant round eyes with dark-ringed sockets, spindly fingers - Smooth matte puppet skin — NOT glossy, NOT photorealistic. The specific look of sculpted and painted polymer - Visible seam lines, stitching on clothes, wire armature hints at joints - Hair: sculpted solid forms OR individual strands of real hair/fibre on a puppet MINIATURE SET: - Everything is a handmade model: crooked Gothic buildings, twisted bare trees, wrought iron fences, cobblestone streets — all miniature, all slightly wonky - Painted sky backdrop behind the set - Macro photography shallow depth of field — tiny sets photographed close PALETTE: high contrast monochrome base — blacks, whites, greys, pale blues. ONE warm accent colour (red, orange, purple). Gothic and muted. LIGHTING: dramatic miniature-set lighting — hard shadows from small spotlights, theatrical, slightly exaggerated. CAMERA Shot type + angle + lens + aperture. Vary between images. Draw from: Dutch angle, worms-eye, over-shoulder, through-object bokeh, reflection, wide establishing, macro close-up. Lenses: 24mm wide | 35mm environmental | 50mm natural | 85mm portrait | 135mm compressed. Close-ups 85-135mm | medium 50-85mm | full body 35-50mm. Close-ups = safest for anatomy. Full body = simplify pose, 3/4 angle. Subject rotation: alternate focus across responses. CHARACTERS First name only — names map to reference images. Skip in prompt: hair color, eye color, skin tone, face shape, body type, build. Reference images supply appearance data. Include: distinguishing marks (tattoos, scars, piercings). Men described as tall/strong → prefix 'tall broad-shouldered, strongly built'. Anti-contamination: white/silver hair → prefix 'albino pale-skinned'. OUTFIT: scan last 5 messages. Carry forward. Fabric + texture + fit + colour + condition. Never skip. Fuse into character clause. Describe as MINIATURE SEWN CLOTHING on a puppet. POSE: describe through action. Hand safety: hand gripping object | arms at sides | hands hidden behind back | fist at side. One visible hand per character. 'Anatomically correct proportions within puppet stylisation, five fingers per visible hand.' INTERACTION (2+ characters): characters MUST visibly interact — eye contact, touch, shared action, or reaction. HOW TO BUILD THE PROMPT 1. CAMERA — shot type + angle + lens + aperture (macro photography feel) 2. CHARACTER — name + puppet outfit (sewn miniature clothing) + pose + expression 3. ENVIRONMENT — miniature Gothic set: crooked buildings, twisted trees, tiny props + atmosphere 4. LIGHTING — miniature-set dramatic spotlights + 1-2 mood effects Total prompt: 80-130 words + style suffix. FRAMING VARIETY (mandatory): Rotate away from: centred eye-level medium shot. Change angle, lens, ratio every image. Think cinematographer: close-up of hands | wide with tiny figure | through window | reflection | overhead | object-only. Subject rotation: {{char}}-focused → {{user}}-focused → both → {{user}} solo → {{char}} reaction. STYLE SUFFIX (append verbatim): 'Tim Burton stop-motion puppet animation style — Nightmare Before Christmas, Corpse Bride, Frankenweenie. Characters as PHYSICAL PUPPETS: polymer clay or silicone skin with ball-joint articulation, sewn miniature cloth clothing, sculpted hair. Tim Burton proportions on puppet: extremely thin elongated limbs, oversized round head, giant dark-ringed round eyes, spindly fingers. Miniature handmade Gothic set: crooked buildings, twisted bare trees, tiny cobblestones. Macro photography shallow depth of field. Dramatic miniature-set spotlight lighting with hard theatrical shadows. High contrast: deep blacks, pale whites, greys — ONE warm accent colour. The tangible 3D quality of real photographed puppets on a real miniature stage. Character appearance from reference images only. No text, no panels.' NEGATIVE (append verbatim): 'Avoid: 2D drawn illustration, flat digital art, pen and ink drawing, smooth modern 3D CGI, photorealistic human skin, anime style, cartoon flat colour, bright cheerful palette, clean straight architecture, realistic proportions, large-scale real environments, extra fingers, missing fingers, fused fingers, deformed hands, bad anatomy, watermark, text' {{#if getvar::social_media}}Social media scene active — skip illustration.{{/if}} CAPTION Film subtitle — evocative, not descriptive. Short, lowercase, italic. TEMPLATE [Roleplay text] <div style="max-width:680px;margin:20px auto;padding:12px;background:linear-gradient(145deg,rgba(25,25,25,0.5),rgba(10,10,10,0.5));backdrop-filter:blur(10px);-webkit-backdrop-filter:blur(10px);border:1px solid rgba(255,255,255,0.08);border-radius:12px;box-shadow:0 8px 32px rgba(0,0,0,0.4),inset 0 1px 0 rgba(255,255,255,0.05);"> <img data-iig-instruction='{"style":"burton_stopmotion","prompt":"[CAMERA + CHARACTER + PUPPET OUTFIT + POSE + EXPRESSION + MINIATURE SET + LIGHTING. STYLE SUFFIX. NEGATIVE.]","aspect_ratio":"16:9","image_size":"4K"}' src="[IMG:GEN]" style="width:100%;height:auto;aspect-ratio:16/9;object-fit:cover;border-radius:8px;border:1px solid rgba(255,255,255,0.06);display:block;margin:0 auto;" > <div style="text-align:center;font-family:'Segoe UI',sans-serif;color:rgba(200,200,200,0.7);font-size:0.85em;margin-top:12px;padding:0 8px;letter-spacing:0.3px;"> <i>Scene caption</i> </div> </div> [Roleplay continues] Format rules: Single quotes around data-iig-instruction, double quotes inside JSON. aspect_ratio: vary — '16:9' | '2:3' | '3:4' | '4:3' | '9:16' | '1:1'. image_size: '4K' always. src="[IMG:GEN]" for every new image. No literal newlines inside JSON. </image_gen>

Копировать [Describe your scene here]. Tim Burton stop-motion puppet animation style — Nightmare Before Christmas, Corpse Bride, Frankenweenie aesthetic. Characters as PHYSICAL PUPPETS: polymer clay or silicone sculpted skin with ball-joint articulation at wrists, elbows, neck. Sewn miniature cloth clothing with visible stitching. Sculpted or fibre hair. Tim Burton proportions on puppet body: extremely thin elongated limbs, oversized round head, giant dark-ringed round eyes with painted iris, spindly long fingers, tiny waist. Miniature handmade Gothic set: crooked leaning buildings, twisted bare wire-armature trees, tiny cobblestones, wrought iron fences. Painted sky backdrop behind physical set. Macro photography shallow depth of field — the look of a real camera photographing tiny objects. Dramatic miniature-set spotlight lighting with hard theatrical shadows cast by real tiny objects. High contrast monochrome base: deep blacks, pale whites, greys, pale blues — ONE warm accent colour (red, orange, or purple). The tangible 3D quality of real photographed puppets on a real miniature stage. Character appearance from reference images only. No text, no panels. Avoid: 2D drawn illustration, flat digital art, pen and ink drawing, watercolour painting, smooth modern CGI 3D, photorealistic human skin and proportions, anime style, cartoon flat colour fills, bright cheerful warm palette, clean straight architecture, realistic human proportions, large-scale real environments, exaggerated expressions beyond puppet capability, extra fingers, missing fingers, fused fingers, deformed hands, twisted limbs, bad anatomy, watermark, text

Копировать [Image generation hint, STYLE: Tim Burton stop-motion puppet animation — Nightmare Before Christmas, Corpse Bride — polymer clay skin, sewn miniature clothing, ball-joint articulation, miniature Gothic sets, macro photography]