GPT Image 2Prompts

Using REFERENCE_0 as the ancient-art composition source, transform it into a believable, collectible fine-art photograph as if the scene had been captured by a top photographer in the same historical era. Do not simply render the painting style as a photo; instead reverse-engineer the painting as a compressed memory of a real landscape and reconstruct the real scene behind it. Keep the core subject logic: exactly {argument name="rider count" default="3"} ancient women riding exactly {argument name="horse count" default="3"} pale horses, moving together across the frame, with pink-to-coral garments and traditional updo hairstyles. Preserve the feeling of lightness, spring colors, and spaciousness from the reference, but convert the abstract watercolor blobs into a real environment. New photographic scene: place the riders in a wide misty spring meadow with soft green grass, shallow reflective puddles, distant fog, blurred flowering trees in pale pink and fresh yellow-green, and foreground shrubs/branches echoing the reference’s pink and green color fields. The landscape should feel humid, early morning, and atmospheric, with large negative space above the riders and a distant tree line fading into haze. Photographic treatment: long-lens documentary/fine-art photography, natural dawn light, gentle backlit mist, realistic horses and fabric motion, shallow atmospheric depth, muted pastel palette, soft contrast, high dynamic range, no ink outlines, no watercolor texture, no illustration, no mural or religious icon style. Composition constraints: keep the riders small-to-medium in the lower middle of the frame, traveling horizontally; maintain a vertical 4:3 composition with broad sky/fog above and textured meadow below. Avoid modern objects, roads, buildings, visible text, logos, or fantasy elements. Optional customization: set the historical period to {argument name="historical period" default="Tang dynasty"}, the season to {argument name="season" default="early spring"}, and the mood to {argument name="mood" default="misty serene"}.

Create a photorealistic cinematic image of a rustic wooden water trough in a lush shaded forest, filled with clear cold spring water and exactly 25 floating ripe tomatoes. A hollow bamboo spout enters from the upper left, pouring a continuous stream of water into the trough, creating ripples, bubbles, sparkle, and small surface splashes around the tomatoes. The tomatoes should vary slightly in size and ripeness, mostly glossy red with some orange-yellow patches, green stems visible, partially submerged and clustered across the water surface. The trough is made of dark wet aged wood with thick rectangular sides, seen from a close three-quarter overhead angle. Surround it with mossy rocks, green leaves, ferns, tree roots, and a vertical weathered wooden post in the background. Use natural dappled sunlight filtering through foliage, bright highlights on the water and tomato skins, soft green forest shadows, humid summer atmosphere, realistic reflections, shallow depth of field, high dynamic range, Lightroom-style color grading with rich greens and warm reds, no people, no text, no labels, no artificial objects beyond the bamboo spout and wooden trough.

Use my uploaded portrait photo only as the identity reference for the person. Accurately preserve the subject’s real facial identity, face shape, facial features, skin tone, hairstyle, hair volume, and natural overall presence. Only use the uploaded image as reference

Goal: Create a wide comparison sheet showing the same chibi/anime musician scene rendered in exactly 30 different visual styles, arranged as a labeled thumbnail grid. The subject is {argument name="character description" default="a silver-haired chibi anime girl with twin buns and long curls, wearing a pale blue and white futuristic idol outfit, holding an electric guitar, with a bulky steampunk-mechanical backpack and glowing blue circular gear details"}. The setting is {argument name="setting" default="an outdoor music festival with a cheering crowd, stage, tents, blue sky, and a stage sign reading Frost+Beats"}. Canvas: Wide horizontal 16:9 image, like a contact sheet or style sampler. Use 5 rows by 6 columns for exactly 30 rectangular panels. Each panel has a thin border and a small black label box in the top-left corner with white text. Layout: Keep the same core composition in every panel: the character is centered or slightly right of center, holding the guitar diagonally across the body, with the crowd and festival stage behind her. Vary only the visual rendering style per panel. Some panels may crop closer or blur the background, but the subject and guitar should remain recognizable. Panel labels: Use exactly 30 numbered labels, one per panel, in this order from left to right and top to bottom: {argument name="style label set" default="1. 実写風, 2. アニメ風, 3. ドット風, 4. ローポリ風, 5. ペーパークラフト風, 6. 水彩画風, 7. 油絵風, 8. 鉛筆スケッチ風, 9. 線画風, 10. マンガ風, 11. レトロアニメ風, 12. サイバーパンク風, 13. スチームパンク風, 14. ファンタジー風, 15. ミニマル風, 16. ポップアート風, 17. ネオン風, 18. 和風（浮世絵風）, 19. グリッチアート風, 20. 白黒写真風, 21. セピア調, 22. イラストレーション風, 23. カートゥーン風, 24. 3Dリアル風, 25. クレイアート風, 26. 切り絵風, 27. 織物風, 28. ステンドグラス風, 29. ソーシャルゲーム風, 30. ちびキャラ風"}. Style details for the 30 panels: 1 photorealistic festival shot, 2 polished anime key visual, 3 pixel-art blocks, 4 low-poly 3D, 5 layered paper craft, 6 soft watercolor, 7 textured oil painting, 8 pencil sketch, 9 clean monochrome line art, 10 dramatic black-and-white manga with sound effects, 11 aged retro anime cel look, 12 neon cyberpunk concert, 13 brown brass steampunk, 14 icy magical fantasy, 15 simplified minimal illustration, 16 colorful pop-art halftone, 17 glowing neon outline art, 18 traditional Japanese ukiyo-e-inspired print, 19 RGB glitch distortion, 20 black-and-white photograph, 21 sepia vintage photo, 22 clean modern illustration, 23 cartoon style, 24 realistic 3D render with depth of field, 25 clay/miniature figure diorama, 26 blue-and-white paper cutout, 27 woven tapestry texture, 28 stained-glass mosaic, 29 mobile/social-game promotional splash art, 30 extra-small chibi mascot style. Visual style: Bright, colorful, playful, dense but readable. The whole sheet should look like a generated style comparison for one character prompt. Use consistent subject identity across panels, with silver hair, blue accents, guitar, mechanical gear backpack, and festival crowd repeated throughout. Constraints: Include exactly 30 panels, exactly one label per panel, and no extra panels. Do not add captions outside the grid. Preserve the festival sign text {argument name="stage sign text" default="Frost+Beats"} in several backgrounds. Keep labels legible, black rectangles with white text.

Goal: Create a simple chibi game sprite sheet for a desktop pet character, showing exactly 6 full-body sprites of the same anime girl aligned in one horizontal row. Canvas: Wide landscape canvas, about 690 x 613 px, with a flat bright chroma-key green background filling the entire image. Leave large empty green space above and below the sprite row, and place the characters across the upper-middle area. Character design: A petite chibi anime girl named {argument name="character name" default="Codex desktop pet"} with very pale skin, oversized head, short white-silver bob hair, small ahoge curl on top, long side locks, and purple flower hair ornaments on both sides with thin black ribbon tassels. She wears a white gothic-lolita maid-style dress with dark navy-black trim, puff sleeves, a bow at the collar, purple floral embroidery near the hem, a short flared skirt, black garter-like strap details, white knee socks, and chunky white lace-up boots with dark soles. Use clean 2D anime rendering, soft cel shading, crisp outlines, and a cute toy-like proportions style. Sprite count and poses: Include exactly 6 discrete character sprites, evenly spaced left to right, all facing forward and standing upright with small variations in arm and body position. The 6 sprites are: 1) front-facing neutral standing pose with face area covered by a square gray placeholder block, 2) front-facing neutral standing pose with face area covered by a square gray placeholder block, 3) front-facing neutral standing pose with face area covered by a square gray placeholder block, 4) front-facing neutral standing pose with face area covered by a square gray placeholder block, 5) front-facing visible face pose with closed eyes and a calm sleepy expression, no placeholder block, 6) front-facing neutral standing pose with face area covered by a square gray placeholder block. Placeholder blocks: On 5 of the 6 sprites, cover the facial area with a vertical rectangular soft gray censor/placeholder block. Each block should be centered over the face, with a light gray-to-pale lavender gradient and slightly soft edges, hiding facial details while leaving hair, ornaments, dress, legs, and boots visible. Style constraints: Make the sprites small, consistent, and usable as game assets. Keep all characters at the same scale and baseline. Do not add text, UI, shadows, borders, or props. The only background color should be {argument name="background color" default="bright chroma green"}.

Goal: Create a dramatic anime fighting-game character poster for {argument name="character name" default="Yuri Sakazaki"}, showing two dynamic depictions of the same young female martial artist in a gritty urban battle scene. Canvas: Wide 16:9 landscape composition, high-resolution promotional key art, dark cinematic lighting, sharp anime rendering, glossy highlights, heavy motion effects. Layout: Place the main action figure on the left, leaping diagonally forward with one knee raised and one fist clenched, occupying about half the image. Place a second depiction of the same character on the right in a school-uniform fighting pose, turned partly away, with one open palm thrust toward the viewer; her face is obscured by a soft rectangular blur. Center the typography vertically between the two figures, layered over black-and-blue paint strokes and red slash effects. Discrete visible character elements: exactly 2 character depictions: 1) left combat outfit version, airborne kick pose; 2) right school-uniform version, defensive open-palm pose with blurred face. Subject details: The character has {argument name="hair color" default="brown"} hair in short bob-length layers with a side braid, red headband, red hair ribbons, expressive anime eyes on the left figure, athletic build, confident smile, and martial-arts energy. Left outfit: white sleeveless gi-style top with dark trim, brown belt, deep purple leggings, purple fingerless gloves, red-orange high-top sneakers with white laces, and a red headband. Right outfit: white sailor-style school blouse with navy collar, navy pleated skirt, yellow fingerless glove on the forward hand, red scarf or ribbon tied near the braid, and a blue-toned shadowed lower half. Background: Nighttime city skyline with tall skyscrapers, lit windows, tilted perspective, black asphalt-like texture, exploding white debris, rain-like sparks, blue energy streaks, red paint splatters, and diagonal speed lines. Use a gritty black, navy, red, and white palette with high contrast and metallic grunge texture. Text content: Include large distressed Japanese brush-calligraphy text in the center reading {argument name="Japanese headline" default="極限流 空手"}. Add smaller Japanese text reading {argument name="Japanese name text" default="ユリ・サカザキ"}. Add small red English text near the bottom center reading {argument name="English name text" default="YURI SAKAZAKI"}. In the upper right background, include faint oversized weathered letters spelling “YURI.” Typography style: White cracked stone brush lettering with rough edges, black shadows, red underline slashes, and dramatic layered depth; the English name should be narrow uppercase serif or condensed lettering in red. Constraints: Keep exactly 2 character depictions, no extra characters, no watermark, no logos besides the specified name text, preserve the rectangular face blur on the right figure, make the pose energetic and poster-like.

Create a serene surreal landscape illustration at dawn: a single vintage red cable-car gondola hangs from three diagonal black cables running from the upper left toward the center-right, suspended above an endless mirror-smooth flooded plain. The gondola is boxy with large windows, a dark roof frame, and a small metal tower and pulley assembly above it; it sits in the left third of the square composition, slightly above center. The water below creates a clear but softly rippled inverted reflection of the gondola, support tower, and cables. In the misty distance on the right half, show exactly five pale stone ruin arches rising from the water: one large tall arch near the right edge, one medium arch closer to center, two very small faint arches near the horizon, and one thin partial arch far right; all reflected vertically in the water. Use a pastel morning palette of {argument name="sky color" default="soft blue"}, blush pink, lavender haze, and warm peach light, with the horizon nearly dissolved into fog. The sky is vast and minimal with delicate horizontal pink cloud streaks on the upper right. Style should feel like a dreamy cinematic digital painting with subtle painterly brush texture, atmospheric perspective, soft gradients, calm symmetry, and no people, no birds, no text, no watermark. Square 1:1 composition, quiet “good morning” mood, high detail in the gondola and cables, softer detail in the distant ruins.

A melancholic Korean psychological drama poster featuring a beautiful young woman with facial features, expression, and proportions preserved exactly as in the original reference photograph. Do not alter identity or proportions. She has long soft black hair styled in a messy, undone bun with stray strands framing her face, pale skin, and a calm but emotionally exhausted expression while staring directly upward into the camera. She wears a loose, oversized burgundy knit sweater and simple dark grey leggings with worn-out white sneakers. She is clutching a well-loved, slightly battered paperback novel to her chest. The camera angle is positioned from a high overhead perspective, looking down toward her while dozens of commuters blur around her with heavy long-exposure motion trails, creating a feeling of isolation and emotional detachment. The environment features cold gray subway tiles, muted city tones, and cinematic atmospheric blur. At the top of the poster, elegant Korean typography reads: "{argument name="subtitle" default="군중 속의 속삭임 (Gunjung Sogui Soksagim - Whispers in the Crowd)"}". Below, large dramatic Korean title typography dominates the center composition in white textured lettering. The image contains soft cinematic haze, subtle analog grain, realistic motion blur, muted warm-beige grading, emotional K-drama aesthetics, delicate skin texture, and realistic shallow depth of field. Shot on a Sony A7R IV using a 50mm lens with slow shutter speed, soft tungsten subway lighting, cinematic realism, luxury Korean drama poster composition

Create a hyper-realistic exploded vertical infographic composition of {argument name="food item" default="tacos"}. Top → Bottom structure: Fresh Lettuce (crisp green texture with natural folds) → Tomato & Salsa Layer (juicy diced tomatoes and salsa mix) → Melted Cheese (smooth cheddar texture) → Grilled Meat Filling (juicy seasoned meat detail) → Taco Shell Base (crispy golden shell texture) Perfect vertical alignment, rustic background, soft studio lighting, realistic shadows beneath each floating element. Add clean infographic text labels with thin pointer lines using these exact labels: “Lettuce” “Salsa” “Cheese” “Meat” “Shell” Ultra-detailed food textures, premium commercial aesthetic, 8K.

Create an ultra-realistic cinematic house exterior with stunning architectural design and premium visual aesthetics. The house can be {argument name="architectural style" default="modern, luxury, rustic, cottage, gothic, fantasy, royal, or minimalist"} in style. Include highly detailed architecture, large windows, elegant textures, beautiful landscaping, realistic pathways, glowing interior lighting, and immersive outdoor surroundings. The environment should feel like a high-budget movie scene mixed with professional architectural photography and luxury real-estate advertising. Add dramatic cinematic lighting, volumetric sunlight, atmospheric fog, realistic reflections, shadows, {argument name="weather or time" default="rain or sunset mood"}, garden lights, trees, flowers, water elements, and detailed environmental effects for a visually powerful composition. Use wide-angle cinematic camera perspective, depth of field, HDR lighting, ray tracing, photorealistic rendering, Unreal Engine quality, cinematic color grading, hyper-detailed textures, luxury aesthetic, masterpiece composition, ultra-realistic environment design, highly immersive atmosphere, 8K ultra detail.

Generate a breathtaking luxury poster for {argument name="beverage name" default="mountain dew"} drink using proper Fibonacci method (without showing lines) and method s use perfect character and explosion expression and use Fonts that are used by professional graphics designers and be creative craft a unique masterpiece.

Goal: Create a wide promotional collage showing four high-end AI-generated advertisement examples and a call-to-action banner for receiving prompt templates. Canvas: 16:9 horizontal image, approximately 1200×622 px, divided into a clean 2×2 grid of four equal advertising panels, with a full-width red banner along the bottom. Use polished commercial design quality, sharp typography, realistic lighting, premium gradients, and no visible watermarks. Layout: Use exactly 5 discrete sections: 1 top-left luxury skincare ad, 2 top-right SaaS analytics ad, 3 bottom-left summer citrus sale ad, 4 bottom-right black-and-gold prompt giveaway ad, and 5 bottom red call-to-action banner. Thin borders separate the panels. Panel 1, top-left luxury skincare ad: Create a soft beige silk background with warm golden light, a glass cosmetic bottle lying inside or beside a transparent spherical bubble, with elegant Japanese serif typography. Include a small gold label in the upper right reading "LIMITED". Main Japanese headline: "うるおいの革命". Subheadline: "初回限定 50% OFF". Add a black strip along the bottom of this panel reading "LUXURY SKINCARE" in spaced gold letters. Mood: delicate, premium, luminous skincare. Panel 2, top-right AI analytics ad: Create a futuristic nighttime office scene with blue neon holographic dashboard panels, city lights through windows, a glass desk, coffee cup, papers/tablet, and dark corporate atmosphere. Main card title: "AI-POWERED ANALYTICS". Japanese headline: "チームの生産性が、3倍になる。" Supporting Japanese copy in smaller text. Add a gold rounded button reading "14日間 無料トライアル →". Show exactly 2 metric cards on the right: "MONTHLY REVENUE ¥4.2M ↑32%" and "ACTIVE USERS 12,480 ↑18%". Show exactly 3 small pill labels under them: "AI REPORT", "AUTO SYNC", and "REAL-TIME". Panel 3, bottom-left summer sale ad: Create a bright orange citrus splash advertisement with sliced oranges, lime wedges, lemon pieces, sparkling water droplets, ice cubes, and energetic summer lighting. Text: "SUMMER 2026" above a huge white "SALE". Japanese text below: "夏の大特価". Add a cream rounded discount badge reading "最大 60% OFF". Add date range at bottom: "7.1 TUE — 7.31 THU". Mood: fresh, juicy, high-impact retail banner. Panel 4, bottom-right prompt giveaway ad: Create a black luxury background with ornate gold Art Deco borders, brass gears, steampunk clockwork elements, and metallic gold typography. Top text: "SPECIAL RELEASE". Huge center text: "30" and below it "PROMPTS". Japanese line: "広告画像を量産するプロンプト全30選". Add a gold rounded button reading "いいね＆リプで受け取る". Bottom small note: "※ GPT Image-2（ChatGPT Images 2.0）対応". Mood: exclusive, premium, campaign giveaway. Bottom banner: Add a full-width deep red velvet-like strip with ornate gold corner decorations and a thin gold border. Large gold Japanese call-to-action text centered: {argument name="bottom call to action" default="いいね＆リプライで「デザイナー」"}. Make it bold, embossed, and readable. Visual style: Ultra-polished advertising mockup, realistic product photography mixed with digital UI graphics, gold highlights, glossy surfaces, crisp composition, high contrast between panels, professional social media promotional image. Constraints: Include exactly 4 ad panels plus 1 bottom banner. Keep all specified visible text legible and placed as described. Do not add extra panels, logos, QR codes, people, or watermarks.

Goal: Create a dramatic vertical manga page about a supernatural apocalypse in modern Sapporo, where a purple rift opens in the sky, a giant demon descends, and a schoolgirl hero with robotic allies prepares to fight. Canvas: Tall comic page in a 3:4 vertical ratio, full-bleed artwork with thin white gutters and black panel borders. Use a polished high-detail anime/manga style with cinematic lighting, saturated neon colors, dense city detail, and intense action composition. Layout: Use exactly 3 horizontal panels stacked vertically. Panel 1 occupies the top third, Panel 2 the middle third, and Panel 3 the bottom third. Add exactly 4 white jagged manga speech balloons with vertical Japanese text. Panel 1: Nighttime downtown Sapporo cityscape seen from street level, crowded with shocked pedestrians looking upward. The Sapporo TV Tower stands on the left, glowing orange with signage reading “30-24 SAPPORO.” Above the skyline, the sky has split into a massive swirling purple vortex filled with lightning, stars, debris, and a single red reptilian eye at the center. Include exactly 2 speech balloons: one small jagged balloon on the left reading {argument name="left reaction text" default="なんだあれ!?"}, and one tall jagged balloon on the right reading {argument name="sky warning text" default="空が割れてる!!"}. Panel 2: The vortex ruptures over a neon Japanese city intersection. A colossal demonic kaiju emerges from the purple storm, filling most of the frame. It has a muscular black-and-purple body, glowing red eyes, huge curved horns, ornate organic armor, clawed hands reaching toward the street, and a circular glowing sigil embedded in its chest. Cars crash and flip in the foreground, sparks and explosions scatter across the road, people run in panic, and buildings with neon signs frame both sides. Include exactly 1 tall jagged speech balloon on the right reading {argument name="demon proclamation" default="人間界ヲ焼キ払エ・・・!"}. Panel 3: Hero reveal composition under a cherry-blossom-like shower of pink petals and purple cosmic light. Center foreground: a Japanese high school girl hero, {argument name="hero name" default="unnamed schoolgirl"}, standing confidently with long black hair blowing in the wind; her face is softly obscured or not sharply detailed. She wears a navy school blazer, white shirt, red ribbon tie, plaid skirt, and holds a glowing pink energy katana angled downward across the foreground. Around her are exactly 3 mechanical allies: 1 white robotic wolf with blue glowing eyes and blue cybernetic armor at lower left, 1 bulky gorilla-like armored robot with blue eyes and a huge red glowing cannon fist at lower right, and 1 silver-blue winged mecha bird hovering behind her on the upper right. The Sapporo tower is visible again in the background. Include exactly 1 white oval speech balloon on the left reading {argument name="hero line" default="また始まったか・・・"}. Visual style: Hyper-detailed Japanese action manga/anime illustration, glossy digital painting, dramatic perspective, neon purple apocalypse lighting, electric effects, particles, debris, high contrast, intricate linework, cinematic depth, crisp panel art. Constraints: Keep exactly 3 panels, exactly 4 speech balloons, exactly 3 robotic allies, and no extra captions or narration boxes. Preserve the Japanese text exactly as written inside the balloons. Do not add watermarks, artist signatures, UI elements, or English subtitles.

Create a dreamy mythological fantasy illustration in a vertical 2:3 poster format. Use a luminous teal turquoise night-sky background with soft paper grain, tiny white stars, sparkles, and pastel celestial ornaments. In the upper center, depict an ethereal moon goddess floating in the sky beneath a large pale golden full moon; she wears flowing ancient East Asian-inspired robes made of translucent pastel ribbons in pink, lavender, mint, aqua, and pale yellow, trailing dramatically to the right like mist. Her black hair is styled in an elegant high bun with gold floral ornaments, and her face is softly obscured and painterly rather than detailed. Behind her, add a vertical aurora-like beam of watercolor light in blues, violets, greens, and pinks extending from top to bottom. Include exactly 4 large starburst shapes: one pale cyan four-point star near the upper left, one small pink star near the goddess, one large white four-point star to the right of the moon, and one yellow starburst near the middle right. Include exactly 5 round planet-like circles in warm pastel tones scattered through the scene: one peach circle on the left, one small orange circle near the goddess robe, one pale blue circle at lower right, one large translucent pale circle behind the flowering tree, and one peach circle near the lower left tree area. In the lower half, paint a delicate golden flowering tree with thin branches and many tiny yellow blossoms rising from the left side. At the bottom, create a landscape of rounded pastel cloud-hills in pink, cyan, lavender, blue, peach, and mint with watercolor texture and vertical soft streaks. Place a small white rabbit with pink eye and upright ears sitting on top of the central pink dome-shaped hill, gazing upward toward the goddess. Add fine glitter dust, shooting-star lines, and soft magical speckles throughout. Overall style: Japanese fairytale poster, watercolor gouache, pastel gradients, celestial mythology, soft edges, whimsical, serene, high detail, no text, no border, no watermark.

Create a clean anime-style character base portrait for modular facial-part generation: a centered front-facing bust of {argument name="character name" default="an unnamed young woman"} with a deliberately empty face area covered by a large vertical rounded rectangle mask, so the eyes, nose, and mouth are absent and can be added separately later. The character has shoulder-length soft layered {argument name="hair color" default="white hair fading into pale ice blue at the tips"}, airy translucent strands, long side locks, subtle loose curls, and visible ears partially covered by hair. Use a pale skin tone and a calm neutral pose, cropped from the top of the head to the upper chest. Dress her in a futuristic high-collar {argument name="outfit" default="white zip-up jacket"} with light blue accents, a central zipper, a small rectangular collar tab with a blue triangle symbol, and delicate seam lines. The blank face mask should be exactly one large central rounded rectangle, softly filled with a vertical gradient from warm pale peach near the top to cool pale blue near the bottom, aligned over the facial features and extending from the forehead area down past the chin, while still showing hair and ears around it. Background is a simple light gray studio backdrop with soft lighting, thin refined line art, watercolor-like anime rendering, gentle shadows, high resolution, no text, no UI, no watermark, and no extra facial features visible inside the blank mask.

16:9, do this for 4 famous space missions: void main() { string[] subjects = {"{argument name=\"subject one\" default=\"[SUB_1]\"}", "{argument name=\"subject two\" default=\"[SUB_2]\"}", "[SUB_3]", "[SUB_4]"}; // Setup Materials vec3 bg_mat = pure_black_matte(); vec3 ui_ink = unlit_metallic_gold(depth: 0.0); vec3 sculpture_mat = pbr_metal(brass, chrome) + refractive_glass(IOR: 1.5); // Setup Viewports (2x2 Grid) vec4 canvas = clear(bg_mat); for(int i=0; i<4; i++) { vec2 quadrant = get_grid_cell(i, columns: 2); // Render 3D Centerpiece mat4 reliquary = build_intricate_model(subjects[i], sculpture_mat); render_to_cell(quadrant, reliquary, lighting: museum_spotlight); // Render 2D UI Overlays vec3 wireframe = generate_blueprint(subjects[i]); vec3 text_data = infer_specs_and_quotes(subjects[i]); draw_hud(quadrant, wireframe + text_data, material: ui_ink); } // Add Global Text draw_hud(header, "{argument name=\"mission theme\" default=\"[THEME]\"} CORES", material: ui_ink); fragColor = canvas; }

Goal: Create a vertical social-media image where a realistic cafe photo is overlaid with playful hand-drawn imagination doodles, as if emotions and thoughts are spilling out onto the scene. Canvas: Vertical 9:16 composition, close-up perspective, warm shallow-depth-of-field photography. The main subject is {argument name="drink" default="a latte in a brown ceramic cup"} on a dark wooden table, sitting on a gray square coaster. The latte art is a large creamy heart shape in the foam, with golden-brown espresso crema around it. Background is softly blurred with a dark plate and pastry near the top edge. Visual style: Keep the base image photorealistic, cozy, warm, and slightly moody, with natural cafe lighting and visible foam texture. Add energetic mixed-media doodles on top: white marker handwriting, black brush lettering, red and yellow crayon strokes, arrows, sparkles, hearts, underlines, scribbles, and tiny cartoon stick characters. The doodles should feel spontaneous, imperfect, emotional, and layered over the photo, not digitally polished. Doodle text and labels: Include exactly 9 handwritten text callouts around the cup: 1) “why is this so good” in white at upper left with a pink heart and underline, 2) “BRO???” inside a speech bubble above the cup, 3) “LAST DANCE” in large black brush letters at upper right with yellow emphasis marks and a pink underline, 4) “this part tho...” on the left with a yellow arrow pointing to the latte surface, 5) “THIS IS CRAZY” in a speech bubble near the lower-left latte foam, 6) “WE STAYING HERE” in a speech bubble on the right side of the latte art, 7) “wait— look at this” on the right with a pink arrow pointing to the foam, 8) “silky smooth” at lower left with a white arrow pointing to the cup rim, 9) “layers on layers” inside a yellow circle at the bottom center with an arrow up to the cup, and 10) “that shine tho” at lower right with a white arrow pointing to the glossy foam. Tiny character count: Add exactly 5 small doodled cartoon people interacting with the latte: 1) one standing on the upper rim with arms raised and a speech bubble saying “BRO???”, 2) one tiny red-capped character on the left rim pointing toward the foam, 3) one sliding down the latte surface on white drawn slide lines with the speech bubble “THIS IS CRAZY”, 4) one sitting near the right-center latte art with the speech bubble “WE STAYING HERE”, and 5) one on a small ladder at the right rim looking toward the foam. Decorative doodle count: Add exactly 15 extra decorative marks around the scene: a small red star at upper left, two yellow stars near the lower left, one pink crown above the “LAST DANCE” text, one yellow lightning bolt on the right, two blue sparkles at lower right, one pink heart near the bottom, one white spiral scribble at bottom left, one yellow oval swirl at bottom left, one small beige spiral at bottom right, two long pink swoosh lines across the bottom, one long yellow swoosh near the bottom, and one short white scribble near the top left. Constraints: Preserve the latte and table as a normal realistic photograph while making only the surrounding world visually noisy and imaginative. Use {argument name="main lettering phrase" default="LAST DANCE"} as the largest readable text. Keep all handwriting legible, rough, and hand-drawn. No watermark, no border, no extra UI elements.

Goal: Create a wide four-panel lineup of cute collectible chibi AI mascot robots, each standing front-facing in its own vertical slice, like a polished 3D toy render for social media. Canvas: Ultra-wide horizontal banner, 4:1 aspect ratio, divided into exactly 4 equal vertical panels with no visible borders, each panel using a different color theme and lighting mood. Layout: Show exactly 4 discrete mascots, one centered in each panel, all full-body, rounded helmet-like heads, oversized glossy eyes, tiny smiling mouths, short plush proportions, winter/sci-fi clothing, soft studio lighting, high-detail toy materials, shallow depth of field, and magical sparkles. Mascot 1: A warm beige and cream robot mascot inspired by {argument name="first mascot" default="Claude by Anthropic"}, wearing a knit winter beanie with a pom-pom, padded headphones, thick orange scarf, mittens, boots, and a cream coat. Include a simple orange sunburst logo on the beanie and coat, with small readable text “Claude” and “BY ANTHROPIC” on the front patch. The robot is waving with one hand. Background is soft peach beige with subtle star glints. Mascot 2: A green and cream robot mascot inspired by {argument name="second mascot" default="ChatGPT"}, wearing large headphones, a hooded winter jacket, green scarf, shorts or padded pants, sneakers, and small tech badges. Place a green knot-style OpenAI-like emblem on the forehead area and jacket, and small readable text “ChatGPT” on the chest. The character raises one paw-like hand in greeting. Background is warm cream with golden bokeh, and a tiny green sprout accent appears near the helmet. Mascot 3: A magical pastel robot mascot inspired by {argument name="third mascot" default="Grok"}, with a white helmet, big blue-purple glossy eyes, a rainbow star floating above the head, a small star mark on the forehead, lavender headphones, a flowing white cape with pink and violet underside, star charms, glowing bracelets, and white boots. The mascot waves cheerfully while standing inside a glowing rainbow ring. Background is dreamy pink, purple, and blue nebula gradients with many sparkles. Mascot 4: A dark futuristic robot mascot inspired by {argument name="fourth mascot" default="xAI"}, wearing a glossy black cat-eared helmet or hood, black puffer jacket, gloves, boots, and neon blue circular accents. The face is black glass with luminous blue eyes and a tiny glowing mouth. Add subtle xAI-like markings on the jacket sleeve, and make the character wave with one hand. Background is deep navy-black space with electric blue rings, stars, and neon rim lighting. Visual style: High-end cute 3D rendering, toy photography, kawaii collectible figurines, rounded forms, soft vinyl/plush textures mixed with glossy robot visors, cinematic lighting, crisp details, vibrant but harmonious colors, adorable expressive faces. Constraints: Keep exactly 4 panels and exactly 4 mascots; no extra characters; each mascot should be visibly distinct by color palette and branding; use only the specified small text labels; avoid watermarks, captions, UI elements, or photorealistic humans.