GPT Image 2 prompts

Transform the uploaded portrait into an ultra-detailed {argument name="art style" default="scratchboard masterpiece"}. Maintain the exact likeness, facial structure, hairstyle, expression, and identity of the person. Create a high-contrast black-and-white engraving using intricate scratchboard techniques, fine cross-hatching, etching, and razor-sharp white lines on a deep black background. Focus on realistic facial details: expressive eyes, detailed eyebrows, natural skin texture, individual hair strands, beard and mustache texture (if present), and precise facial contours. Use {argument name="lighting" default="dramatic cinematic lighting"} with strong highlights and deep shadows to enhance depth and dimension. Add a {argument name="background" default="dark grunge background"} with subtle scratches, dust particles, distressed textures, and artistic imperfections. The artwork should resemble a premium hand-crafted scratchboard illustration, combining vintage engraving aesthetics with modern graphic novel styling. Professional museum-quality artwork, ultra-sharp focus, highly detailed linework, bold contrast, clean composition, masterpiece quality, 8K resolution, award-winning illustration, visually striking monochrome portrait.

Using the attached image, create a professional industrial packaging design illustration sheet for the packaging of {argument name="product name" default="[PRODUCT NAME]"}

Feature a centered hero 3D render with realistic materials, soft studio lighting, and commercial-grade finish quality.
Surround the hero render with technical views: front, side, top, bottom, angled perspective, and flat layout.

Include structural construction sketches, fold lines, seam details, and dimension arrows with measurements in millimeters.
Show materials and finishes (matte, glossy print, plastic, paper, glass, etc.) using handwritten-style annotations.
Add color swatches, realistic product illustrations, and subtle shadows.

Background should resemble {argument name="background style" default="clean sketchbook paper"}, combining realistic rendering with pencil sketch overlays.
Modern industrial design aesthetic, ultra-detailed, portfolio-ready presentation.

Holding a phone with the flash on, snapping a mirror selfie in a casually lit, slightly lived-in room. Multiple anime-aesthetic characters fill the frame around me, their look inspired by the {argument name="anime characters" default="female cast of Dead or Alive Xtreme Beach Volleyball"}. They're in {argument name="outfit" default="bikinis"}, crowding in close — a few gently touching my cheeks, others leaning in warmly.

Makeup is soft and natural, facial features carry a clear anime influence.

The mood is warm and intimate, soft shadows everywhere, a bright flash catch visible in the mirror. Visual style is semi-realistic with cinematic lighting, a hint of film grain, and that polished TikTok-era look.

The characters feel like real people in flawless cosplay rather than fully rendered anime figures.

Young woman, {argument name="hair style" default="dark brown shoulder-length hair with warm caramel highlights"}, olive-tan skin with natural freckles scattered across nose and cheeks, hazel-green eyes with full arched brows, bright genuine smile showing white teeth, sitting cross-legged on warm parquet hardwood floor with chin resting playfully on hand. Wearing a {argument name="outfit" default="green and yellow athletic crop top"} and a gold name bracelet on wrist. {argument name="pet detail" default="Small white hamster peeking out from the top of her shirt"}. Pink hand dumbbell and keys visible in background. Shot from overhead bird's-eye angle, camera tilted approximately 60-70 degrees down, subject fills the frame with face prominent in upper third, shallow depth of field, background softly blurred. Soft natural indoor daylight, diffused window light from upper left, warm golden-hour interior warmth, no hard shadows. Candid lifestyle photography, authentic UGC aesthetic, editorial fitness influencer style. Photorealistic, subtle film grain, no heavy makeup, no airbrushed skin. 9:16 aspect ratio, 2048x3072.

Using the portrait photo you upload, create a polished formal business headshot poster. Keep the person's real facial features, proportions, face shape, and overall presence intact — do not change who they look like.

Lightly refine the facial contour to look cleaner and more photogenic. Smooth skin texture and reduce blemishes or uneven tone without over-retouching — preserve natural skin detail and realistic lighting.

Give the subject a business hairstyle tailored to their face shape: neat, professional, and natural-looking, not exaggerated. Dress them in formal business attire — dark suit jacket, white or light shirt, optional tie — for a premium, minimal, trustworthy appearance.

Composition: frontal half-body portrait, subject centered, looking directly at the camera with a calm, confident expression. Plain solid white background with soft, even lighting — similar to a professional ID photo or corporate headshot. Style: clean, formal, photorealistic, square 1:1 ratio.

Include a clean info bar at the bottom with modern minimal typography:
Name: {argument name="name" default="[Yuna Koizumi]"}
Title: {argument name="job title" default="[Senior Graphic Designer]"}
Department / Institution: {argument name="institution" default="[International Design Institute]"}

Text rule: if any label text is in Chinese or another language, translate it to formal English before placing it in the image. Do not display Chinese in the image unless explicitly asked.

Typography: Name in dark navy bold large font (first line); Title and Department in black regular weight (second and third lines). Layout should reference university faculty profile pages or professional conference speaker cards.

A premium modern editorial fashion and lifestyle branding poster for {argument name="vibes" default="vibes"}. Contemporary minimalist editorial design, monochromatic green aesthetic, clean luxury composition, Vogue-esque soft studio photography style. A stylish, photorealistic young woman seated prominently in a designer minimalist chair, wearing a fashion-forward outfit color-matched to the lush green monochromatic palette. Relaxed, confident pose, contemporary editorial styling. Asymmetrical foreground placement against a large, oversized abstract letter "A" dominating the background. Spacious negative space, minimal branding details in the corners, editorial magazine-inspired hierarchy, thin modern sans-serif fonts, minimal branding text reading "{argument name="branding text" default="Love"}". Soft cinematic studio lighting, gentle monochromatic shadows, smooth gradient lighting. Shot on Sony A1, 85mm f/1.2 lens. Minimal film grain texture, clean modern gradients, Scandinavian-inspired visual simplicity. 8K Ultra-high resolution, hyper-realistic editorial photography, Octane Render, Behance-quality modern composition. Same exact visual identity and layout as the reference. Same Face as Reference Image. -v 6.0 --ar 3:4 SW

A fun bubbly kids advertisement poster. An excited young boy age {argument name="age" default="5"} in swimming goggles sits inside a giant rubber duck shaped bubble bath bottle 3x his height overflowing with rainbow bubbles everywhere, "{argument name="product name" default="BUBBLEPOP"}" written in big bouncy letters on the bottle. Bright pastel blue bathroom background with floating rubber ducks soap bubbles and rainbow foam. Big bouncy rounded typography "{argument name="product name" default="BUBBLEPOP"}" in bright blue and yellow filling the background. Tagline bottom: "Bath time just got wild." Small text top-right corner reads "Designed with GPT Image 2" in grey. Photorealistic, fun kids bath product commercial, bright soft bathroom lighting.

Create a high-end fashion campaign poster for a fictional brand named {argument name="brand" default="[BRAND]"}. Use a vertical editorial e-commerce layout with a full-body model wearing {argument name="outfit" default="[OUTFIT]"}. Add oversized cropped typography behind the model, structured campaign UI blocks, CTA button, bottom category navigation, seasonal label, and polished magazine-style art direction. Keep all text clean, intentional, and readable.

Create a crisp, clean infographic storyboard poster for {argument name="product name" default="THE CHURRO MAKER"}. Wide 16:9 layout, white background, black borders, bold black typography, premium {argument name="style" default="Pixar 3D stylized rendering"}, bright vivid colors — {argument name="color scheme" default="golden fried dough, sparkling white sugar"}

Create a highly detailed vertical historical illustration of an old Chinese silk and brocade shop, titled conceptually {argument name="shop name" default="Shen Family Silk Shop"}. The scene is viewed from inside the richly carved wooden shop looking out toward a sunlit traditional street. Use a refined painterly style with realistic proportions, intricate linework, warm sepia and muted gold tones, like a late-Qing/Republic-era historical illustration. Canvas is tall portrait, about 9:16. Show exactly 3 prominent human figures: 1 front-left male silk merchant in a dark brown traditional robe, hair tied in a topknot, leaning over a counter and lifting an ornate brocade roll; 1 midground male assistant or customer in a blue robe holding an open ledger and brush; 1 right-side woman outside the doorway in a red-orange robe holding a basket. Their faces should be deliberately obscured by smooth rectangular tan blur blocks with no facial features. In the background street, include a few softly painted pedestrians and traditional white-walled buildings with curved tiled roofs, kept small and atmospheric. The main object is a large unrolled silk brocade on the counter in {argument name="fabric color" default="blue-green and antique gold"}, covered with dense phoenix, cloud, floral, and scrolling patterns, metallic highlights, and embroidered texture. The shop interior should contain carved wooden shelves on the left packed with many visible fabric bolts, stacked folded textiles, rolled silk bundles, lacquered boxes, and small drawers; add hanging lanterns, carved lattice windows, painted wall panels, a bead curtain or tasseled shade near the doorway, and soft sunlight entering from the right. On the counter include exactly 8 types of visible shop objects: an abacus, a ceramic tea cup, a small porcelain bowl, paper tags and receipts, a string-tied bundle of documents, a metal lockbox, a decorative textile chest, and measuring tools. Emphasize antique craftsmanship, layered textiles, dust motes, warm backlighting, and dense historical detail. Avoid modern objects, electric lighting, readable signage, western clothing, and any clean digital UI elements.

Goal: Create a vertical Chinese business infographic poster explaining that AI image generation now achieves high Chinese text accuracy, transforming messy text into clear deliverables.

Canvas: Portrait 3:4 poster, clean white background, playful hand-drawn editorial style with orange, green, black, and gray accents. Use thick sketch outlines, rounded speech bubbles, energetic doodle marks, and a friendly tech-explainer tone.

Layout: Center the composition around one large smartphone mockup showing a clean Chinese report page. On the left, show a gray “before” document panel full of garbled symbols and unreadable Chinese-like text. On the right, show a cheerful cartoon designer sitting behind a laptop, holding a stylus, with an excited fist pose. Add a large bright green check mark overlapping the lower center of the phone and foreground. Add a green circular badge in the upper right and an orange speech bubble below it. Put a large bottom headline inside an orange hand-drawn outline bubble.

Text content: Use exactly 5 main text areas. 1) Left gray speech bubble: “以前：乱码”. 2) Upper-right green badge: “95% 准确率”. 3) Right orange speech bubble: “现在：清晰”. 4) Phone screen title: “项目总结报告”. 5) Bottom headline: “中文准确率95%”.

Phone screen details: Show an iPhone-like black smartphone with notch and status bar time 9:41. Inside the report page, include 4 stacked content sections separated by thin gray dividers. Section 1 has an orange target icon and heading “项目目标”, followed by short Chinese body text about improving user experience, optimizing product functions, and strengthening system stability. Section 2 has a blue bar-chart icon and heading “关键成果”, followed by 3 bullet points: user satisfaction increased 32%, system performance improved 45%, issue response time shortened 50%. Section 3 has a green check icon and heading “主要结论”, followed by body text saying the project achieved expected goals and laid a solid foundation. Section 4 has a yellow lightbulb icon and heading “下一步计划”, followed by body text about continuous optimization and expanding application scenarios.

Left “before” area: Render a gray browser/document card with a top bar and multiple lines of broken characters, question marks, punctuation, and scattered Chinese characters, clearly unreadable. Add messy paper sheets, scribbles, and an envelope icon near the bottom left to emphasize disorganized documents.

Right character details: Create a cute young male cartoon designer with curly brown hair, fair skin, orange sweater, and simple expressive pose; the face may be left blank or softly obscured. He holds a black stylus in one hand and sits behind a gray laptop with a round sticker reading “设计师”. On the desk add exactly 3 foreground accessories: a spiral notebook with simple layout sketches and small color blocks, a black pen, and a white mug with an orange heart.

Visual style: Friendly Chinese social-media explainer poster, semi-flat vector illustration mixed with marker-like hand-drawn lines, soft shadows, rounded shapes, high readability, vibrant green check mark and orange headline emphasis. Keep the composition busy but legible, with no photorealism.

Constraints: Preserve the Chinese text exactly as specified, keep the smartphone report text crisp and readable, use exactly one central phone, one left messy document card, one designer character, one green check mark, one green badge, one orange speech bubble, and one bottom headline. Do not add watermarks, logos, QR codes, or extra main claims.

Create a dark cinematic fantasy battle illustration in a gritty semi-realistic painterly style. The scene is set in a ruined stone corridor at night, with broken masonry, black shadows, and a narrow cobblestone floor. In the foreground, show the back of a large dwarf warrior with long reddish-brown braided hair, heavy engraved metal shoulder armor, leather straps, and a hammer or axe handle gripped at the right edge; keep this foreground figure intentionally out of focus to create depth. In the midground, depict exactly two combatants locked in a dramatic clash: one enormous green-skinned orc warlord with tusks, pointed ears, scarred muscular arms, spiked dark armor, and a massive chipped battle axe raised in his left hand; and one agile young human knight with {argument name="hero hair color" default="windblown blond hair"}, sharp determined expression, ornate dark armor, a torn black cape streaming behind him, and a sword braced against the orc at chest level. Add a bright orange-white spark burst where the sword strikes the orc armor, with flying embers and metal fragments radiating through the darkness. Use high contrast chiaroscuro lighting, warm sparks against cold green-black shadows, intricate armor detail, dynamic motion, dramatic perspective from behind the dwarf observer, shallow depth of field, no modern objects. Include a small elegant signature and date in the bottom-right corner reading {argument name="date text" default="June 8, 2026"} and {argument name="signature text" default="Oyagi"}.

Create a cinematic widescreen anime-style fantasy illustration of a lone {argument name="character type" default="tall adult woman warrior"} standing in the left foreground of a vast open grassland under a deep blue twilight sky. She has extremely long windblown {argument name="hair color" default="dark purple"} hair streaming dramatically to the left, a partially obscured face covered by a soft rectangular blur, and a confident forward-facing stance. Her outfit is a rugged post-apocalyptic tactical ensemble: exactly 7 visible main clothing and gear elements — a torn long dark trench coat, a ripped off-white shirt, black high-cut shorts, a brown belt, thigh straps, a holstered pistol on one thigh, and dark thigh-high stockings/boots. The coat and hair should be pushed by strong wind, with loose strands and torn fabric edges. The background is a sweeping savanna-like plain with golden grass, scattered rocks, distant mesas, and exactly 3 prominent trees: one large twisted ancient tree on the right with a dense rounded canopy, one smaller tree far left, and one tiny distant tree near the horizon. The sky is filled with glowing pink-orange cumulus clouds against rich cobalt blue, with exactly 3 small pale moons or planets visible near the upper center-left. Use highly detailed painterly anime rendering, dramatic sunset rim light, soft atmospheric depth, epic scale, crisp linework blended with oil-paint texture, vibrant colors, and a 16:9 cinematic composition. Avoid text, logos, watermarks, extra characters, and modern buildings.

Goal: Create a dense monochrome pencil-sketch notebook collage page devoted to an obsessive anime-style gothic girl character, like a fan sketchbook spread filled with handwritten Japanese praise notes, hearts, and multiple studies of the same character. Include {argument name="character name" default="a nameless gothic girl"} as the recurring subject.

Canvas: Square image, photographed or scanned from off-white sketchbook paper with visible spiral binding holes along the far left edge. Use black graphite pencil, charcoal-like shading, smudges, crosshatching, and messy hand-drawn linework. Overall tone is grayscale with no color except the warm paper tint.

Layout: Fill the entire page edge-to-edge with overlapping drawings and handwritten notes. The composition should feel crowded, emotional, obsessive, and handmade, with no clean margins. Add gray blurred square censor blocks over the main faces, as if the faces have been intentionally hidden.

Main visible drawings: Use exactly 11 discrete character drawings/studies: 1 large central close-up portrait of the girl’s head and hair, face covered by the largest gray blur square; 1 full-body standing gothic girl on the left wearing a black crop top, short belted skirt, fishnet stockings, and heavy lace-up platform boots, with her face covered by a smaller gray blur square; 1 upper-body standing pose near the upper right with long dark hair and a patterned top, face covered; 1 seated chibi girl near the upper right hugging her knees; 1 partial seated or crouched girl on the right side with face covered; 1 reclining or tilted bust portrait at the lower right with visible eyes and lips; 1 tiny chibi at the far left beside the standing figure; 1 small chibi near the lower center with face covered; 1 angry chibi near the bottom center-right; 1 partial head at the lower left covered by a gray blur square; 1 partial head at the bottom-left edge covered by another gray blur square.

Additional studies and details: Include exactly 3 separate close-up body-detail studies: 1 large realistic eye near the center-right, 1 large realistic eye in the bottom-right corner, and 1 raised hand with long dark fingernails near the top center. Add accessories and gothic details such as chokers, heart motifs, belts, chains, lace, fishnets, skull-like doodles, dark nail polish, and messy strands of black hair.

Text content: Surround the drawings with many handwritten Japanese notes, hearts, exclamation marks, and speech-bubble-like comments. The writing should look spontaneous and fangirl-like, with phrases such as 「天才すぎる」, 「かわいい」, 「好き!!」, 「存在が罪」, 「推し」, 「世界一」, 「ありがとう」, 「好きすぎて」, and 「反則じゃん!!」 scattered around the page. Keep the Japanese handwriting rough, varied in size, and integrated into the pencil sketch.

Visual style: Raw manga sketchbook aesthetic, highly detailed graphite hatching, soft smudged shadows, expressive anime proportions, gothic-kawaii mood, chaotic fan-art composition, slightly tilted photographed-paper perspective. The gray face censor squares should be soft-gradient blurred blocks, not sharp black rectangles.

Constraints: Keep the image entirely monochrome pencil on paper; do not add digital color, clean vector lines, printed typography, or a polished comic-panel layout. Preserve the crowded collage feeling and the exact count of 11 character drawings plus 3 close-up studies.

Create a photorealistic documentary-style image of a quiet student dormitory bedroom in the evening, shot from a low side angle at bed height with natural indoor lighting. A {argument name="student age" default="teenage"} male student is lying face-down across a single wooden bed, fully clothed in a {argument name="school uniform colors" default="white and royal blue"} short-sleeve athletic school uniform with matching blue shorts. His head and upper body face toward the wall side of the bed, his face is intentionally obscured with a rectangular blur, and his lower legs are bent upward behind him with both feet wearing plain white ankle socks. The room feels realistic and lived-in: a blue-gray plaid duvet covers the bed, a pair of white sneakers sits neatly on the tile floor beside the bed, a wooden desk and bookshelf with books, stationery cups, a desk lamp, and a blue office chair appear on the left, while the back wall has a dark wooden door, wall hooks holding two hanging jackets, a large colorful map, and a small orange certificate or notice. Include exactly 1 student, 1 bed, 1 pair of white sneakers, 1 desk, 1 chair, 1 bookshelf, 1 desk lamp, 2 hanging jackets, 1 wall map, and 1 orange wall certificate. Use a realistic camera look with soft shadows, muted dorm-room colors, slight wide-angle perspective, and no stylization, no glamour lighting, no extra people, no visible text emphasis, and no watermark.

Create a vertical dark fantasy nightmare scene in a ruined gothic cathedral: a {argument name="warrior gender" default="female"} holy knight with long tangled {argument name="hair color" default="blonde"} hair is caught mid-struggle in ornate mirror-polished silver plate armor engraved with gold filigree, her face deliberately obscured by a soft square blur with no facial features. She lunges forward while gripping one ornate longsword in her right hand, the blade angled down toward the lower right. Behind her looms one enormous shadow demon fused to her back like a living cloak, with two huge curved black horns, two glowing red eyes, a charred bark-like skull, and smoke spilling from its head and shoulders. Five prominent black tendrils wrap around the knight: one across her chest, one across her waist, one around her sword arm, one sweeping across the lower foreground, and one curling from the left side like a clawed arm. The background is one cavernous, decaying gothic cathedral interior with towering ribbed arches, thorny black roots, red drapery, ember sparks, ash, fog, and faint orange firelight in the shadows. Use a cinematic low-angle composition, ultra-detailed realistic fantasy concept art, high contrast cold blue-gray moonlight against hot red demonic glow, wet metallic reflections on armor, smoky volumetric lighting, dynamic motion, oppressive horror atmosphere, no text, no watermark.

Goal: Create a high-resolution 2.5D photorealistic fashion generator image showing two full-body AI cosplay fashion models side by side on a sunny urban shopping street, like a street-style lookbook comparison.

Canvas: Landscape 4:3 image, approximately 800×640 px, split vertically into exactly 2 equal panels with no border line. Bright daylight, sharp details, shallow-to-medium depth of field, realistic street photography with a polished AI illustration finish.

Layout: The left panel shows one model standing centered on a sidewalk in front of glass storefronts and trees, holding out the sides of her skirt in a cute pose. The right panel shows one model standing centered on a city sidewalk with glass buildings, trees, street signs, and a black hanging banner in the background, posing confidently with one hand near her hip. Add a small white event-style watermark/logo near the lower center overlapping the split, reading “AI COSPLAY EXPO” with smaller tiny unreadable event text below and a simple white mascot/icon above.

Subject count: Exactly 2 full-body female fashion models. Both have intentionally blurred, featureless faces with smooth beige rectangular/oval blur masks, while hair, clothing, body pose, and accessories remain detailed.

Left model: A cute gothic lolita idol outfit on {argument name="left character style" default="a young woman with long ash-blonde silver wavy twin-tail hair tied with dark blue ribbons"}. Outfit count for the left panel: 1 navy-and-cream plaid short dress with a white sailor collar, 1 navy bow at the neckline, 1 fitted corset-like bodice with gold buttons, 1 pleated flared skirt, 1 white lace underskirt, 2 white wrist cuffs with bows, 2 sheer white patterned thigh-high stockings, 2 dark bow garters, and 2 white platform Mary Jane shoes with ankle bows. Add delicate jewelry such as a small necklace and earrings. The pose is shy and cute, knees slightly inward, both hands lifting the skirt edges.

Right model: A punk gyaru streetwear outfit on {argument name="right character style" default="a young woman with long platinum-blonde voluminous wavy hair"}. Outfit count for the right panel: 1 black graphic long-sleeve top reading “GLAMOROUS JANE” with a skull illustration, 2 zebra-striped sleeves, 1 black mini skirt, 1 studded belt with metal rings, 2 hanging silver chains, 1 black shoulder bag, multiple bracelets and rings, 2 mismatched thigh-high socks where one is solid black and one is black-and-white striped, and 2 black platform buckle boots. The pose is edgy and confident, one leg forward, one hand at the waist, the other relaxed.

Environment: Modern Japanese city fashion district sidewalk, bright green trees, sunlit pavement, reflections in glass storefronts, distant pedestrians kept small and unobtrusive. The right panel includes a black vertical street banner with a white abstract X logo and small text resembling “CROSS NIGHT.”

Visual style: 2.5D hybrid of photorealistic street photography and polished AI cosplay illustration, crisp clothing textures, realistic lighting and shadows, high-fashion street snap composition, vibrant but natural colors. Use {argument name="lighting" default="bright sunny midday lighting with dappled tree shadows"}.

Text content: Include exactly 2 visible text areas: the small lower-center watermark “AI COSPLAY EXPO” and the right-side background banner with a white X-like logo and tiny “CROSS NIGHT”-style wording. Do not add any other readable captions.

Constraints: Keep both faces blurred and anonymous, show both characters full body from head to shoes, maintain the exact two-panel split, no extra people in the foreground, no cropped feet, no anime face details, no raw prompt text, no frame border.

Create a wide cinematic Japanese robot-anime illustration of a massive humanoid combat mecha undergoing maintenance and articulation testing inside a dark industrial hangar. The central subject is a towering white and gunmetal-gray armored robot, approximately Gundam-like but original, standing upright in a launch bay with bulky shoulder armor, angular chest plates, segmented waist armor, heavy forearms, large mechanical hands, thick thigh and shin armor, broad blocky feet, a helmet-like head with a narrow visor face, a central forehead crest, and several antenna fins. Add exposed pistons, cables, hydraulic joints, panel seams, scratches, grime, orange warning lights, and small decal markings across the armor. The hangar is huge, vertical, and shadowy, filled with steel gantries, catwalks, cranes, articulated support arms gripping the robot at the torso and legs, dangling cables, maintenance rails, ladders, and overhead strip lights. Include exactly 6 visible human technicians in white helmets and pale maintenance suits for scale: 1 on the left upper catwalk, 1 standing at a lower-left control console, 2 together on the right mid-level catwalk, 1 seated or standing at the foreground-right computer station facing away with “A/1” on the back, and 1 small technician near the central lower platform partially obscured by machinery. Place readable industrial text on the environment: a large crate or gantry label “SC-02” with smaller “M-BLOCK” on the upper left, a wall label “A-60” on the right with smaller text “SUBJECT : A/1” and “ARTICULATION TEST,” and a foreground monitor showing “STATUS,” “ARTICULATION TEST,” large “A/1,” plus a vertical list “E-01,” “E-02,” “E-03,” “E-04,” “E-05.” Use {argument name="mecha identifier" default="A/1"} as the recurring test subject code, {argument name="hangar block label" default="SC-02"} on the upper-left industrial structure, and {argument name="test label" default="ARTICULATION TEST"} on signage and monitor screens. Visual style: highly detailed hand-painted anime concept art, realistic mecha engineering, gritty sci-fi military maintenance bay, teal-gray shadows with warm amber accent lights, dense linework, dramatic low-angle perspective, cinematic 16:9 composition, sharp focus, no logo, no watermark.

Create a vertical photorealistic smartphone-style image of an adult woman sitting on her knees on a cushioned sofa or bed in a warm, softly lit Japanese-style room. She has {argument name="hair color" default="light blonde shoulder-length hair with darker roots"}, slightly tousled and falling around her face, with her face intentionally covered by a large opaque beige-gray square censor block centered over the upper face and nose area. She wears a loose {argument name="robe color and pattern" default="pale pink floral yukata-style robe with black flower prints"}, wide sleeves, and a dark purple obi belt around the waist, with the robe draping naturally and showing the neckline in a realistic fashion. Pose her leaning toward the camera with both arms stretched forward as if reaching out to the viewer; both hands are close to the lens and blurred by perspective, with one hand entering from the lower left foreground and the other from the upper right foreground. Use an intimate low-angle wide-lens perspective from directly in front of her, emphasizing foreshortened arms, knees in the foreground, and a candid snapshot feeling. The background should include beige walls or sliding panels, a warm floor lamp glowing on the left, soft shadows, and muted brown-green upholstery. Style: realistic live-action photography, natural skin texture, shallow depth of field, warm indoor ambient light, slight smartphone compression, vertical 9:16 crop, no horror elements, no extra people, no text, no watermark.

Goal: Create a clean anime-style character pose sheet for a modern office woman, showing the same character in exactly 6 full-body poses on a plain white background.

Canvas: Landscape 4:3 composition, high-resolution digital illustration, plenty of white space, no borders, no title text, no labels, no shadows beyond very subtle grounding.

Character: A young adult Japanese businesswoman with {argument name="hair color" default="dark brown"} chin-length bob hair with soft bangs, slim build, average height, refined professional appearance. Her facial features are intentionally blurred or left indistinct, while the body, hair, and outfit remain sharply drawn.

Outfit: Beige fitted blazer with rolled or slightly ruched sleeves, white pleated blouse, navy ankle-length tapered trousers, black low-heel pumps, and a small wristwatch. Keep the outfit consistent across all poses.

Layout: Arrange exactly 6 separate full-body drawings in a balanced 3-column by 2-row pose sheet, evenly spaced on the white background.

Pose count and descriptions:
1. Top left: Front-facing neutral standing pose, arms relaxed at sides, feet together, calm professional stance.
2. Top center: Seated pose on a simple black chair with thin metal legs, legs crossed, hands resting neatly in the lap, viewed slightly from the front.
3. Top right: Walking forward pose, one foot stepping ahead, one arm bent near the waist, confident businesslike stride.
4. Bottom left: Running or hurried pose, body leaning forward, one knee lifted back, one fist raised near the chest, hair swinging with motion.
5. Bottom center: Standing explanation pose, one arm raised with index finger pointing upward, other arm relaxed, feet apart.
6. Bottom right: Thinking pose, one hand near the chin, opposite arm folded across the body, slight contrapposto stance.

Visual style: Polished manga/anime character design, clean ink outlines, soft cel shading, natural proportions, light beige and navy business color palette, crisp clothing folds, subtle highlights in the hair, professional character-reference-sheet feel.

Constraints: Show exactly the same character in all 6 poses, keep all figures fully visible, avoid extra props except the single chair in the seated pose, no background scenery, no text, no watermark, no additional poses or duplicates.

Create a detailed anime-style group scene inside a bright modern Japanese supermarket aisle. The image shows exactly 6 main characters arranged across the store: 1 blond young man on the far left wearing a green open jacket over a mustard yellow shirt, dark pants, and sneakers, standing casually near produce; 1 white-haired elegant young man in the front center wearing a royal blue blazer, white shirt, white trousers, black dress shoes, and a pocket square, holding a shopping cart; 1 young woman with long wavy purple hair standing behind the cart in a sleeveless dark denim jumpsuit and sneakers; 1 tall dark-haired young man slightly right of center wearing a blue work jacket over a dark shirt, black pants with a chain, boots, and holding a tablet; 1 cyberpunk photographer on the rear right wearing a metallic helmet with round goggles and antennae, a gray tech jacket, backpack, gloves, and holding a professional camera while seated or leaning near a refrigerated counter; and 1 crouching young woman in the lower right wearing a blue athletic jacket with a small black cat patch, shorts with chain straps, black-and-blue chunky sneakers, and earrings, reaching toward jars or bottles on a low shelf. Place them in a glossy supermarket interior with refrigerated shelves on both sides, fruit and vegetables visible on the left, packaged goods and drinks on the right, bright ceiling panels, hanging produce signs with Japanese text including “fresh vegetables,” reflections on the polished tile floor, and daylight from large windows in the back. The shopping cart contains exactly 4 visible grocery groups: leafy green lettuce, red tomatoes, orange carrots, and a small boxed or packaged item. Use polished semi-realistic anime rendering, rich detail, fashionable streetwear, cinematic depth, warm indoor lighting, accurate perspective, and a crowded but readable composition. Leave every character’s face intentionally obscured by a soft rectangular blur or neutral face-covering censor block, while preserving hair, pose, clothing, and body language. No extra characters, no readable brand logos, no watermark.

Goal: Create a two-panel anime redraw comparison of {argument name="character name" default="Raul Creed"} from Ergo Proxy, showing the same office scene twice: the top panel in cool blue color and the bottom panel in monochrome grayscale.

Canvas: Vertical image, approximately 3:4 aspect ratio, with a thick black horizontal divider separating exactly 2 stacked panels. Add narrow dark margins on the left and right edges.

Layout: The image contains exactly 2 panels: 1) top panel, full-color blue cyberpunk version; 2) bottom panel, identical composition in black-and-white grayscale. In both panels, place the character in profile on the left half of the frame, seated in a reclining office chair facing right, with a large floor-to-ceiling window on the right overlooking a glowing futuristic city at night.

Subject details: The character is an adult man with medium-length dark brown hair swept back, wearing a dark formal suit, white shirt, long trousers, and polished black dress shoes. He sits relaxed but serious, leaning back in the chair with one leg crossed over the other, hands resting near the chair arms. His face is intentionally obscured by a soft rectangular blur, preserving the head silhouette but hiding facial features.

Environment: A dim executive office or command-room interior with teal-blue ambient lighting in the top panel. Include a high-backed ergonomic chair with a pale headrest, dark armrests, a visible pedestal base, and a small dark desk or cabinet at the far left. Behind the chair, add a small coat-rack-like fixture with four short horizontal pegs. The right side has tall vertical wall panels, a bright diagonal shaft of light on the wall, and a large window showing a dense futuristic cityscape filled with tiny white and cyan lights. Add dark industrial ceiling or window pipes on the upper right: exactly 2 vertical pipes connected by exactly 3 horizontal rungs, plus one long horizontal pipe running across the window area.

Visual style: Mature 2000s psychological sci-fi anime style, clean cel-shaded linework, moody noir atmosphere, cinematic composition, subdued shadows, crisp outlines, subtle film grain, high contrast between the dark office and luminous city. Top panel palette: deep teal, cyan, navy, black, and cool white. Bottom panel: identical drawing converted to grayscale, with the city lights still bright.

Constraints: Preserve the exact two-panel stacked comparison format, do not add captions or logos, do not add extra characters, keep the blurred face in both panels, and keep both panels aligned so they appear like a color version above a grayscale version of the same frame.

Goal: Create a square Japanese comparison infographic showing the difference between a person who uses AI and a person who does not, in a polished semi-realistic anime business illustration style.

Canvas: 1:1 square social media image, split diagonally from near the top center toward the bottom center into two contrasting halves. Use bright warm colors on the left and dark gray-blue colors on the right. Add a clean white diagonal divider between the two scenes.

Left panel: Show a successful office worker using AI. The main subject is a young Japanese businessperson in a {argument name="shirt color" default="green"} shirt sitting at a wooden desk with a laptop. Place a cute small teal-and-white robot assistant beside the laptop, with “AI” written on its body. Add subtle green glow, sparkles, and a positive atmosphere. In the background, show two business colleagues standing and discussing, a bright office window, plants, and presentation materials. Deliberately obscure or softly blur all human faces for privacy-like anonymization.

Left text: At the top, place a green rounded title label reading 「AIを活用している人」. Under it, add the headline 「活躍して成果を出している！」. Include exactly 2 white thought/speech bubbles: one large bubble saying 「AIがサポートしてくれるから効率的に進められる！アイデアも広がる！」 and one smaller bubble saying 「さすが！仕事が早くて助かるよ！」. Include exactly 3 floating AI support cards around the worker: 「情報収集・要約」 with a document and magnifying glass icon, 「アイデア出し」 with a lightbulb icon, and 「資料作成サポート」 plus 「データ分析」 with chart icons. On the desk, include a gold trophy labeled 「成果・信頼 評価UP!」. At the bottom left, add a white checklist card with exactly 4 green check items: 「作業時間を大幅削減！」, 「質の高い成果を創出！」, 「評価・信頼UP！」, 「新しいことに挑戦できる！」.

Right panel: Show a stressed office worker who is not using AI. The main subject is a young Japanese businessperson in a white shirt and blue tie slumped at a desk, holding their head with one hand while looking overwhelmed at a laptop. Surround the desk with large stacks of papers, binders, and documents. The office should look dim, cold, cluttered, and late-at-night, with a wall clock, scribble stress marks, a downward-trending chart, and an exhausted mood. Deliberately obscure or softly blur the human face as on the left side.

Right text: At the top, place a dark rounded title label reading 「AIを使えていない人」. Under it, add the headline 「苦労して成果が出せず、遅れてしまう…」. Include exactly 1 large white thought bubble above the worker saying 「調べるのに時間がかかる…資料作るのも大変…終わらない…」. Include exactly 3 beige sticky notes on the wall or around the worker: 「時間がない！」, 「資料が多すぎる…」, and 「何から手をつければ…」. Add a small label near the downward chart reading 「進捗の遅れ…」. At the bottom right, add a white checklist card with exactly 4 black X items: 「作業に時間がかかり、残業続き…」, 「成果が出ず、評価が上がらない…」, 「新しいことに手が回らない…」, 「周りに差をつけられて焦る…」.

Visual style: High-quality Japanese business illustration, semi-realistic anime, clean infographic composition, crisp readable typography, soft shading, detailed office props, strong emotional contrast between success and struggle. Keep all Japanese text legible and exactly as written. No watermark, no extra logos, no additional checklist items.

Create a square, cinematic portrait photo of a person centered in frame inside a dark, warm old library, standing in front of tall wooden bookshelves filled with books and a softly glowing table lamp on the right. The subject is {argument name="character description" default="a young adult man with short light brown hair"}, wearing {argument name="coat" default="a beige trench coat with wide collar and shoulder epaulettes"}, holding a white round plate at chest height with {argument name="dessert" default="one dark chocolate cake"} on it. The cake should be a single round cake with glossy chocolate frosting, visible slice divisions on top, and a decorative border of chocolate pieces or frosting around the rim. The subject faces the camera directly, but the entire face is obscured by a smooth vertical rectangular skin-colored block with no facial features, covering from forehead to chin while leaving the hair, ears, neck, and clothing visible. Use shallow depth of field, warm amber library lighting, dark vignette around the edges, realistic photography, centered composition, slightly surreal censored-face effect, no text, no watermark.