GPT Image 2 prompts

Goal: Create a vertical travel-aesthetic diptych about {argument name="destination" default="Lake Como, Italy"}, combining a vivid scenic photograph on top with a soft gouache sketchbook collage on the bottom.

Canvas: Portrait 3:4 composition, split horizontally into two equal panels. No border between panels. The upper half is realistic photography; the lower half is an off-white paper background with airy watercolor/gouache studies.

Top panel: A bright Mediterranean lakeside villa scene in crisp summer daylight. Show turquoise lake water filling the left foreground, a small wooden floating dock near the lower right waterline, ornate stone terrace stairs and carved balustrade on the right, a twisted carved stone column near the right edge, and lush pink oleander blossoms overhanging from the upper right. Across the water, show elegant yellow and cream villas with terracotta roofs, tall dark cypress trees, manicured gardens, and hazy blue mountains under a deep blue sky with a few white clouds. Use saturated but healing colors, cinematic travel photography, sharp foreground details, sunlit stone texture, tranquil atmosphere.

Bottom panel: A minimalist gouache-and-pencil sketchbook layout on warm cream paper, with loose brush texture, soft edges, muted pastel palette, and lots of negative space. Include exactly 8 separate collage elements: 1) a small lakeside villa vignette at upper left with a yellow building, cypress trees, shrubs, a stone wall, and a pale blue water patch; 2) a handwritten quote near the upper center reading {argument name="upper quote" default="The lake keeps things we forget to say."}; 3) a beige spiral stone column sketch at upper right; 4) a small pink flower sprig beside the column; 5) a large pink oleander branch with green leaves at lower left; 6) a pale blue lake-water brush puddle in the center with a tiny brown wooden dock; 7) a pale blue simplified mountain silhouette near the lower center; 8) a small villa-and-cypress vignette at lower right with a yellow villa, red roof, green ground, and two tall dark cypress trees.

Additional handwritten text: Place a second small pencil-written quote near the lower middle-right reading {argument name="lower quote" default="Light, stone, and the sound of somewhere staying still."} with a faint pink underline. Keep the handwriting casual, delicate, and slightly uneven.

Visual style: GPT-image-2 aesthetic, split-media travel poster, top half photorealistic and richly colored, bottom half light gouache illustration, Japanese design-zine sensibility, soothing palette of turquoise blue, cypress green, sunlit yellow, stone beige, and soft pink. The overall mood should feel light, slightly clumsy, handmade, poetic, and calming.

Constraints: Keep the exact two-panel vertical composition and the exact count of 8 illustrated collage elements in the lower half. Avoid people, cars, logos, watermarks, heavy outlines, or extra text beyond the two quotes.

Create a 3:4 vertical ultra-realistic street-fashion advertising photo where a real person appears to pull a music-player phone interface out into the real world. The subject is {argument name="character description" default="a young East Asian woman with fair skin, soft natural makeup, dark brown hair in a loose messy bun with wispy bangs"}, standing centered in front of a muted gray-blue vintage double door on a city street in daytime natural light. Use a high-angle wide selfie-like perspective from slightly above and in front of her, with mild wide-angle distortion. She looks directly at the camera with a gentle smile and reaches one hand toward the lens, palm open and very close to the viewer, creating strong first-person interaction and shallow depth of field. She wears {argument name="outfit" default="a fitted light gray cropped T-shirt, high-waisted light blue denim shorts, white socks, chunky white sneakers, and a slim brown shoulder bag"}. Background should be softly blurred but recognizable: paneled blue-gray door, stone wall edges, sidewalk pavement, bright sun and soft shadows.

Surround her with exactly 5 floating translucent glass music-player UI cards, as if smartphone app panels have detached from the screen and are hovering in physical space. All cards are semi-transparent dark frosted glass with rounded corners, thin pale outlines, glossy reflections, subtle refraction, realistic perspective, and cast faint shadows/occlusion against the scene. Each card contains album art, track title, artist name, progress bar, time stamps, cast icon, and playback controls with white minimalist icons. Count and place the 5 cards as follows: 1 large card in the lower left foreground, closest to camera, tilted in perspective, showing sunset ocean album art and the text {argument name="main song title" default="Echoes in Waves"} with artist "Haycoon" and duration around 4:18; 1 medium card in the upper left showing black-and-white portrait-with-flowers album art and the text "Midnight Drive" by "Velora"; 1 medium card in the upper right showing pink cloud album art and the text "Cloud Eight" by "Lume"; 1 medium vertical card on the right side showing black-and-white windy portrait album art and the text "Fading Signals" by "Noir"; 1 small card in the lower right showing blue abstract album art and the text "Lumen" by "Astra". Keep the floating panels integrated into the lighting and perspective so they feel physically present around the woman rather than flat overlays.

Visual style: hyperrealistic live-action photography, creative commercial ad aesthetic, crisp skin and fabric detail, natural daylight, gentle lens flare, soft bokeh, realistic shadows, high dynamic range, no cartoon styling. Composition should emphasize depth: the reaching hand is large and slightly blurred in the foreground, the subject's face is sharp, and the UI cards float at different distances around her. Avoid extra people, extra UI cards, watermarks, captions outside the cards, distorted anatomy, unreadable gibberish text, or a purely graphic mockup look.

Create a photorealistic cinematic street scene in modern Tokyo on a clear sunny day: a massive humanoid police patrol robot, about three stories tall, walks down a narrow residential road between apartment buildings. The robot is bulky and highly detailed, built from white armor plates over black mechanical joints, pistons, cables, bolts, vents, and exposed hydraulics, with a rectangular sensor head packed with multiple camera lenses. It has Japanese police markings on its chest and shoulders reading 「警視庁」 and “MPD,” and smaller “MPD” markings on its legs. The robot is friendly rather than threatening, standing in the left-center foreground with one huge articulated hand raised in a wave toward residents. On the right, a beige multi-story apartment building with metal balcony railings fills the frame; exactly four visible people wave back from balconies: one boy on an upper balcony, and three children on a lower balcony. Include laundry poles, balcony details, potted greenery, roadside shrubs, utility poles, overhead wires, a small urban street receding into the background, parked bicycles, lane markings, and hard midday shadows. Use a low-angle wide lens perspective from street level, realistic scale, sharp focus, natural Japanese residential textures, blue sky, high dynamic range, documentary realism, no anime styling, no extra text beyond the robot markings. Customize the robot unit as {argument name="robot unit label" default="警視庁 MPD"}, the city setting as {argument name="city setting" default="Tokyo residential street"}, the waving residents as {argument name="waving residents" default="four children on apartment balconies"}, the time of day as {argument name="time of day" default="clear sunny midday"}, and the mood as {argument name="mood" default="friendly neighborhood patrol"}.

Create a dark monochrome science-fantasy landscape titled by mood: {argument name="theme" default="vibration"}. Show a vast alien wasteland under an enormous storm-like sky made of concentric warped shockwave rings, as if the atmosphere itself is vibrating. The ground is black cracked stone and metallic ash, with jagged obsidian spires and ruined gothic-industrial towers rising from the foreground and midground. In the far distance, place a dominant central mountain-fortress with needlelike peaks, surrounded by smaller serrated mountains and citadel silhouettes. Add exactly 12 small dark spacecraft hovering in the sky, arranged as 6 on the left side, 1 near the center-left, and 5 on the right side, all seen in silhouette with faint highlights. Use a square vertical composition with a low horizon, deep perspective, cinematic scale, and a desolate apocalyptic atmosphere. Palette: nearly black, charcoal gray, gunmetal, and cold silver-white highlights. Lighting should be dim and dramatic, with pale light breaking through the swirling atmospheric bands and reflecting on wet cracked terrain. Style: ultra-detailed dark fantasy concept art, biomechanical sci-fi architecture, epic matte painting, high contrast, realistic texture, no people, no readable text, no logo, no watermark.

Create a photorealistic cinematic night portrait of a young adult woman relaxing on a worn dark-brown velvet sofa in a cozy high-rise apartment lounge. She has long wavy {argument name="hair color" default="blonde"} hair with soft bangs, fair skin, natural makeup, and a calm slightly wistful expression, leaning diagonally with her head resting on one hand and looking toward the camera. She wears a fitted white ribbed camisole tank top and loose gray drawstring lounge shorts with frayed hems. Behind her is a large window showing a blurred nighttime city skyline with colorful bokeh lights and red aircraft warning lights. On the right side, hanging clothes are visible above the sofa: exactly 4 garments, a black coat, a black jacket, a blue denim jacket, and a black-and-white striped shirt. Add warm ambient lamp light from the right, contrasting with cool blue city light from the window. In the foreground on a low table, include exactly 3 drinking items out of focus: one green glass bottle near the bottom center-left and two large beer mugs with golden beer and white foam on the right. Use shallow depth of field, realistic skin texture, soft shadows, intimate moody atmosphere, 35mm lifestyle photography, horizontal composition, no text, no watermark.

Create a cinematic anime-style portrait of an elegant young woman lounging sideways on a dark patterned sofa in a dim luxury lounge at night. She has {argument name="hair color" default="short chestnut-brown hair"} in a tousled bob with soft bangs, warm brown eyes, delicate facial features, glossy lips, and a calm intimate half-smile while looking directly at the viewer. She rests her head on one bent arm along the sofa back, with her other arm relaxed in front; show a close three-quarter upper-body composition from a slightly high angle. She wears {argument name="dress color" default="deep navy satin slip dress"} with thin straps and a low neckline, plus exactly 2 visible jewelry pieces: one fine silver drop necklace with a small pendant and one dangling cross earring on the visible ear. Use warm amber practical lighting, soft rim highlights on hair and shoulders, realistic skin shading, painterly anime rendering, subtle fabric sheen, and a shallow depth of field with large blurred bokeh lights in the dark background. The mood should be intimate, elegant, quiet, and cinematic, with rich shadows, no text, no watermark, and no extra characters.

Create a highly detailed cinematic anime illustration of a young woman reading a handwritten letter by oil lamp in a dark attic room at night. The scene is vertical portrait format, close side profile composition from the waist up, with the woman seated at a wooden writing desk on the right side of the frame. She has {argument name="hair color" default="soft chestnut brown"} hair with straight bangs and a long loose braid down her back, delicate pale skin, subtle blush, blue-gray eyes, and thin round wire-rim glasses. Her expression is quiet, pensive, and melancholy as she looks down at the letter held in both hands. She wears a vintage cream-white nightgown with lace trim around the neckline and cuffs, gathered sleeves, soft fabric folds, and a modest old-fashioned silhouette. The desk contains exactly 4 visible objects besides the letter: one glowing glass oil lamp with brass base, two stacked old books, and one framed picture leaning in shadow. The handwritten letter should show faint cursive lines but no readable modern text. The background is a dim wooden attic with slanted roof beams, dark planks, and a small window at left showing deep blue night sky and distant house lights. Lighting should be dramatic and warm from the oil lamp, casting golden highlights on her face, glasses, hands, letter, and desk, with cool blue moonlit shadows in the room. Use refined Japanese anime realism, painterly texture, delicate linework, realistic anatomy, soft skin shading, intricate hair strands, moody chiaroscuro, shallow depth of field, nostalgic 19th-century atmosphere, no watermark, no captions, no extra characters.

Create a glamorous high-fashion studio portrait of a young adult woman with {argument name="hair color" default="voluminous dark chestnut brown"} tousled wavy shoulder-length hair, pale luminous skin, striking hazel-gray eyes, softly arched brows, subtle warm eye makeup, and glossy deep {argument name="lipstick color" default="crimson red"} lipstick. She wears a thick ribbed {argument name="sweater color" default="red"} turtleneck sweater pulled high around the neck, with the knit texture clearly visible. Pose her in a three-quarter bust portrait, shoulders angled left, chin slightly lifted, lips gently parted, gazing directly at the camera with a confident sultry expression. Use a seamless {argument name="background color" default="dark rich red"} studio backdrop matching the glamorous red theme. Lighting should be soft but dramatic, with smooth beauty-dish illumination on the face, gentle shadows under the jaw, subtle catchlights in the eyes, and realistic skin texture. Composition is vertical 3:4, tight crop from upper torso to above the hair, centered slightly to the right, editorial fashion photography style, ultra-realistic, shallow depth of field, no jewelry, no text, no watermark.

Create a dark, cinematic anime illustration of {argument name="character name" default="an exhausted young office worker"} lying unconscious or asleep on her back in a flooded office at night. Use a vertical 2:3 canvas viewed from a high overhead angle, with the body placed diagonally from lower center toward the middle right. She has {argument name="hair color" default="long messy black hair"} floating in shallow black water, pale skin, closed eyes, a loosened white button-up work shirt with rolled sleeves, dark high-waisted slacks, black loafers partly slipped off, and a blue lanyard with a glowing blank ID card on her chest. Her arms are relaxed outward, one hand loosely holding crumpled paperwork, conveying burnout, depersonalization, and quiet collapse rather than violence. Surround her with a cluttered Japanese-style office: exactly 6 large desks or cabinet surfaces visible around the edges, exactly 3 office chairs partially visible, exactly 2 large copy/printer machines in the background/right side, 1 dark computer monitor on the left desk, 1 black calculator near the lower left, 1 glowing smartphone on the right with unreadable chat bubbles, 1 fallen disposable coffee cup near the phone, 1 small black lens-like object, and numerous scattered documents, forms, sticky notes, paper clips, red and black stamp pads, binders, and small office supplies floating in the water. The floor is covered by ankle-deep glossy black floodwater with strong reflections, ripples around the body and papers, and a bright vertical reflection from a distant doorway or fluorescent light in the upper background. Lighting should be moody blue-green, low key, with sharp white highlights on wet surfaces and the ID badge and phone as small light sources. Style: detailed modern Japanese anime, realistic proportions, fine linework, painterly shading, high-detail office debris, melancholic psychological atmosphere, no gore, no explicit text, no watermark. Optional mood keywords: {argument name="mood" default="overwork, alienation, burnout, drowning in paperwork"}.

Create a square close-up Y2K kawaii studio portrait of a young woman with {argument name="hair color" default="dark black-brown"} slightly messy shoulder-length hair and wispy bangs, looking upward to the side with glossy eyes and a playful duck-face pout. She is centered against a smooth pastel lavender background with soft even lighting and a dreamy beauty-editorial finish. Style her with a pale powder-blue knitted beanie that has two rounded bear-ear bumps, a light blue ribbed camisole with white trim and a tiny bow at the neckline, a silver chain necklace with a small heart charm, and long fuzzy fingerless arm warmers with horizontal pastel rainbow stripes in pink, blue, purple, yellow, and peach. Pose both hands raised symmetrically, index fingers pressing gently into her cheeks. Add small pastel star stickers on both cheeks, about 16 total, scattered in pink, blue, yellow, and lavender. Makeup should be soft and glossy: pink blush, subtle shimmer eyeshadow, defined lashes, natural dewy skin, and shiny pink lips. Use a shallow depth of field, crisp facial detail, soft film-like color grading, high-resolution fashion photography, nostalgic early-2000s Japanese idol portrait mood, cute and polished, no text or watermark.

Create a vertical anime-style portrait of a young Japanese bookstore clerk in a warmly lit bookstore aisle. She is centered in a close-up bust composition, facing the viewer with a gentle small smile and soft, expressive brown eyes. She has {argument name="hair color" default="warm dark brown"} short bob hair with airy loose waves, wispy bangs covering the forehead, fine flyaway strands, and warm rim light outlining the top of her hair. She wears a slightly wrinkled cream button-up shirt under a navy bookstore apron with shoulder straps, metal strap buckles, a small white “BOOKS” logo on the chest, and a clipped rectangular staff name badge with Japanese text including 「店員」 and the name 「貝渕」. Add small stud earrings and natural rosy cheeks. She holds one visible book at the lower left edge of the frame, a teal-green hardcover with vertical Japanese title text. The background is a softly blurred bookstore interior with shelves on both sides, warm ceiling lights creating round bokeh, and a large out-of-focus Japanese sign on the left reading 「文庫・新書」 and 「話題の本」. Use cinematic golden-hour indoor lighting, slightly dark cozy exposure, shallow depth of field, detailed painterly anime rendering, delicate skin shading, realistic fabric folds, soft amber highlights, and a calm intimate atmosphere. Canvas ratio 2:3, portrait orientation. Avoid extra characters, avoid modern UI elements, avoid watermarks, and keep all background text blurred except the badge and apron logo.

Create a vertical cinematic fantasy anime illustration of {argument name="character name" default="a noble heroine"} standing at the top landing of a grand temple staircase, framed by a monumental white stone gateway. Use a strong leading-line composition: a wide staircase rises from the bottom foreground directly toward the character, with symmetrical railings, pillars, and ornate gold architectural details guiding the viewer’s eye upward. The heroine is centered slightly above the midpoint, looking back over her shoulder like the protagonist of an epic story. She has {argument name="hair color" default="long flowing dark brown hair"}, a delicate jeweled tiara or hair ornament, and a serene but dramatic expression. She wears {argument name="dress style" default="an elegant white and pale blue goddess-like gown"} with translucent layered fabric, gold trim, ribbons, and long fluttering veils trailing in the wind. The architecture should feel like a celestial palace or sacred temple: tall white columns, carved gold filigree, decorative lantern-like posts, and a large ornate lintel overhead. Behind her is a bright open sky with soft clouds, distant pale mountains, and warm backlighting from the sun, creating a halo glow around her silhouette and illuminating the fabric edges. Color palette: pearly white, pale blue, champagne gold, soft gray stone, and warm sunlight. Mood: majestic, romantic, ethereal, dramatic, storybook heroine. Render in highly detailed polished anime fantasy art, delicate linework, luminous atmosphere, realistic depth, soft volumetric light, flowing motion in hair and fabric, no text, no watermark, no extra characters.

Create a vast cinematic science-fiction cityscape titled by concept as {argument name="concept" default="artificial sun and city"}: a colossal domed megacity seen from a high balcony, with an enormous blazing artificial sun embedded in the ceiling at the top center. The sun is a white-gold fusion-like orb surrounded by concentric mechanical rings, radial cables, transparent dome panels, and delicate golden circuitry, casting warm shafts of light downward through haze. Below it stretches a utopian futuristic metropolis built around turquoise lakes, terraced greenery, bridges, and distant snow-capped mountains or cloudlike rocky ridges enclosed inside the dome. The foreground includes two small human silhouettes standing on a curved observation balcony at the lower left, emphasizing immense scale. On the right and left edges, towering cylindrical glass-and-metal skyscrapers with rounded balconies and glowing interior floors frame the view; in the lower half, include layered elevated transit rails, sleek transparent tube trains, spires, circular platforms, and dense metallic infrastructure. Use {argument name="color palette" default="warm gold sunlight, cool cyan water, silver metal, soft mist"}, ultra-detailed concept art, painterly realism, intricate architecture, luminous atmosphere, volumetric light, reflective glass, shimmering highlights, epic vertical composition, high depth, awe and wonder, no text, no logo, no watermark.

Create a dark, cinematic fine-art portrait in vertical 9:16 format: a young woman with {argument name="hair color" default="dark curly hair"} and olive skin is encased from the shoulders up inside a perfectly clear glass cube filled with transparent amber liquid or resin. Her face is centered slightly right, calm and melancholic, eyes half open and looking forward, lips relaxed, with realistic skin texture and wet highlights. The glass cube has sharp visible edges, thick refractive corners, glossy reflections, tiny bubbles, ripples, and distorted light caustics across the surface. Inside and around the cube are delicate tangled green stems and botanical filaments, plus exactly 8 visible dark red cherries suspended at different depths: 3 on the left side, 1 near the lower center front, and 4 on the right side. The lower part of the image shows a second rounded glass vessel or pedestal beneath the cube, also filled with dark amber reflections and dripping liquid. Use an almost black background with warm golden bokeh, low-key chiaroscuro lighting, high contrast, rich brown and bronze tones, shallow depth of field, hyperrealistic photographic detail, dramatic editorial fashion mood, no text, no watermark, no extra faces.

Create a vertical realistic social media ad photo about AI image realism testing. Show a young adult white man with short blond hair, blue eyes, light stubble, and a slight confident smile, wearing a plain black T-shirt in a modern neutral-toned apartment or studio kitchen. He is seated behind an open laptop on a table and holds a small black handheld microphone with a gray furry windscreen near his chest, as if presenting a test result. The laptop screen is clearly visible and displays a side-by-side comparison with exactly 2 portrait panels of the same man holding a white cylindrical product: the left panel looks slightly soft, waxy, and blurry and is labeled “4K” in bold white text at the bottom; the right panel looks sharper and more natural and is labeled “2K + HIGH” in bold white text at the bottom. Add a large bold all-caps white headline at the top reading {argument name="headline text" default="REALISM TEST"}. Use natural window light, shallow depth of field, realistic skin texture, muted beige-gray walls, shelves with minimal decor and a small plant in the background, clean creator-testimonial composition, vertical 9:16 framing, high-end UGC ad aesthetic. Keep all text legible, use only the headline and the two laptop labels, no logos, no watermark, no extra UI elements.

Goal: Create a desktop screenshot-like collage showing 10 AI-generated recruitment poster variations for a Chinese tech company, all with nearly identical purple-and-white branding and a cute rabbit mascot, arranged above a prompt input bar.

Canvas: Wide 16:9 white interface screenshot, about 1064×922 px. Leave generous white margins. The image area occupies the upper 80%, and a rounded prompt composer bar sits centered along the bottom.

Main layout: Arrange exactly 10 square poster thumbnails in a loose grid with slight spacing, as if displayed in an image-generation results gallery. Count and placement of thumbnails: 3 posters across the top row; 4 posters across the middle row; 3 posters across the bottom row. Each poster is a clean Chinese recruitment flyer with the same core visual identity but small layout variations.

Poster design shared by all 10 thumbnails: Use a light lavender-to-white background, deep purple and bright blue typography, rounded cards, small icons, thin dividers, soft shadows, and a polished SaaS/AI startup aesthetic. Every poster should feature the logo text {argument name="company name" default="兔子 AI"} near the top, a large bold Chinese headline {argument name="headline text" default="兔子 AI 继续招聘 全栈开发实习生"}, and multiple information blocks resembling a job description. Use readable-looking Chinese microtext but it may be partially too small to read at thumbnail size. Include iconography such as gift boxes, graduation caps, location pins, calendars, code brackets, laptop icons, check marks, and circular badges.

Mascot subject: Include a cute white 3D rabbit mascot in most posters, with pink inner ears, glossy black eyes, a friendly smile, and a purple hoodie or shirt branded with the company name. Vary the mascot pose across the 10 posters: sitting with a laptop, waving, giving a thumbs-up, peeking from the bottom edge, wearing round glasses, and standing beside cards. The rabbit should feel like a friendly AI assistant mascot.

Poster content blocks: Each thumbnail should show several compact recruitment sections, including exactly these recurring block types across the designs: recruitment target, requirements, job location, internship participation/work content, work arrangement, and benefits. Some posters may have a purple CTA strip or footer, small QR-code-like square, or decorative code panel, but keep all poster variants visually consistent.

Bottom prompt composer UI: At the bottom center, draw a large rounded white input box with soft shadow, resembling an AI image generation chat bar. Inside it show the gray placeholder text {argument name="input placeholder" default="描述你想要创建的图片"}. Along the lower edge of the bar include small UI icons and controls: image icon, grid icon, book icon, @ symbol, a dropdown labeled image, a model label {argument name="model label" default="gpt2"} with tiny green signal bars, a dropdown reading auto / 1K / auto, a count selector showing {argument name="generation count" default="10个"}, and a paper-plane send button on the far right. Add a three-dot menu at the top-right of the composer.

Visual style: Clean modern Chinese AI-product interface screenshot, soft pastel lavender, white, cobalt blue, and purple. The 10 posters should look like outputs from the same prompt: highly consistent layout, typography, colors, and mascot styling, with only minor differences in composition. Use crisp vector-like UI, subtle gradients, rounded rectangles, and high-resolution details.

Constraints: The collage must contain exactly 10 poster thumbnails and one bottom prompt composer bar. Do not add people, photos, watermarks, browser chrome, or extra panels. Keep the overall impression that the AI generated many nearly identical recruitment poster options.

Goal: Create a 6-panel editorial fashion photography comparison collage with neon cyberpunk lighting, showing the same model and styling in each panel.

Canvas: Landscape collage, approximately 5:4 aspect ratio, arranged as a 2-column by 3-row grid with thin black dividers between panels. Each panel is a high-angle or fisheye fashion photo inside a small metallic industrial room.

Layout: Use exactly 6 panels. Add a small rounded white label with dark text at the top-left of each panel. The 6 visible labels are: 1) MIDJOURNEY V8.2, 2) GROK IMAGINE 2.0, 3) SEEDREAM 5 PRO, 4) REVE 2.0, 5) NANO BANANA PRO, 6) GPT 2. Keep labels compact and unobtrusive.

Subject details: The same young fashion model appears in all 6 panels: pale skin, slim build, intense editorial expression, heavy tattoos on both arms and chest, orange-red lipstick, and a blunt neon yellow bob haircut with straight bangs and a black circular dyed spot at the crown. She wears an oversized off-shoulder neon camouflage dress in hot pink, lime green, yellow, and black. Pose her crouching, kneeling, or seated on the concrete floor in each panel, often looking up directly into the camera. Use {argument name="hair color" default="neon yellow bob with black crown spot"}, {argument name="outfit" default="oversized hot pink and lime neon camouflage off-shoulder dress"}, and {argument name="model expression" default="intense confrontational editorial gaze"}.

Environment: A cramped industrial metal room or container with ribbed steel walls, worn concrete floor, dark stains, and vertical blue fluorescent tube lights mounted on the walls. The lighting is dominated by saturated electric blue and violet neon, with the outfit glowing strongly against the cool background. Use {argument name="location" default="small ribbed metal industrial room with blue fluorescent tube lights"}.

Camera and style: Editorial fashion photography, wide-angle lens, overhead and high-oblique viewpoints, dramatic perspective distortion, glossy high-contrast color grading, vivid neon saturation, sharp details, realistic skin texture and tattoos, cinematic blue shadows, modern fashion magazine energy. Each panel should have slightly different pose, framing, and angle, but preserve the same model, outfit, hair, tattoos, and location. Use {argument name="collage labels" default="MIDJOURNEY V8.2, GROK IMAGINE 2.0, SEEDREAM 5 PRO, REVE 2.0, NANO BANANA PRO, GPT 2"}.

Constraints: Exactly 6 panels, exactly 6 labels, no extra panels, no extra text, no watermark, no logos, no borders beyond the collage dividers. Keep the image photorealistic rather than illustrated.

Create a cinematic cyberpunk character portrait of {argument name="character name" default="8ug8ear"}, a skilled female netrunner in a cramped rain-soaked hideout in Night City. She sits sideways on a worn narrow cot, leaning forward with elbows near her knees, looking down and to the right with a tired, guarded expression. She has {argument name="hair color" default="platinum blonde"} hair styled as a tall swept-back mohawk with shaved sides and long hair flowing behind, pale skin, dark smoky eye makeup, subtle facial cyberware seams and small black interface marks around the temple and cheek. Her body shows delicate glowing gold circuit tattoos on both arms. Dress her in a glossy metallic {argument name="bodysuit color" default="deep red"} cybernetic armored bodysuit with high collar, segmented chest plates, mechanical thigh and knee joints, red chrome prosthetic-looking legs, and sharp high-heeled cyber boots. The room is cluttered and industrial: visible cables and server panels on the left wall, small blue monitor screens behind her, dirty tile floor, battered metal storage crates, a disposable noodle cup with steam on a crate to the right, a coiled black cable beside it, and exactly two pistols lying on the cot near her left hip. Behind her is a grimy metal door with a rain-streaked window showing blurred neon city signs outside, including teal and orange East Asian characters. Use moody cinematic lighting with teal-blue shadows, warm orange neon reflections, wet glass, subtle smoke or steam, realistic skin and metal textures, shallow depth of field, ultra-detailed photorealistic concept art, vertical 3:4 composition, no watermark, no extra people, no readable English text.

Goal: Create a 2-column by 3-row editorial comparison grid of six AI image model outputs, each showing the same close-up jewelry photography subject: a cropped side portrait of a punk/goth person’s ear wearing a black plug-style earring with a dangling silver cross charm.

Canvas: Landscape collage, approximately 1200×1000 px, no outer border, six equal rectangular panels touching edge-to-edge in a 2×3 grid.

Layout: Use exactly 6 panels with small rounded white label pills near the top-left of each panel. Panel labels, in reading order, must be: 1) MIDJOURNEY V8.2, 2) GROK IMAGINE 2.0, 3) SEEDREAM 5 PRO, 4) REVE 2.0, 5) NANO BANANA PRO, 6) GPT 2. Keep the labels compact, uppercase, black condensed sans-serif text on off-white rounded rectangles.

Subject details: Every panel is an extreme close-up editorial portrait crop focused on {argument name="jewelry subject" default="a black circular plug earring with a dangling silver cross charm"}. Show only part of the face and ear: cheek texture, ear cartilage, stray dark hair strands, and sometimes a partial eye, nose ring, lips, neck, or jawline at the edge of the crop. The person has {argument name="skin texture" default="realistic pale skin with visible pores, redness, shine, blemishes, and uneven texture"} and dark messy hair. The cross charm should be metallic, reflective, and slightly different in shape and scale across panels, as if generated by different models.

Panel variations: Top-left panel is the widest facial crop, showing the left side of the face with a partial eye, nose ring, lips, cheek, ear, and small silver cross; top-right is a tight ear crop with strong pink-red flash lighting and a bright cross; middle-left is similar to top-right but closer, with the cross blown out by flash; middle-right is a darker purple-toned side-of-head crop with the ear and smaller cross against a near-black background; bottom-left is a gritty flash photo with pronounced facial stubble/pores, black plug, and bright silver cross against a dark red-black background; bottom-right is an extreme macro of the earlobe with a black oval plug and large glowing silver cross, warm skin tones and magenta shadows.

Visual style: {argument name="photo style" default="raw editorial macro jewelry photography, harsh on-camera flash, high contrast, glossy skin highlights, shallow depth of field, gritty realism"}. Use a dark club-like background with black, burgundy, and purple tones. Make the collage feel like a side-by-side model comparison posted on social media, with each panel having subtly different realism, anatomy, lighting, and jewelry rendering.

Constraints: Do not add any title outside the six panels. Use exactly the six label pills listed above and no extra captions. Keep the jewelry as the visual focus in every panel. Avoid clean studio beauty retouching; preserve pores, redness, flash glare, and imperfect skin detail.

Goal: Create a vertical educational knowledge-card poster explaining {argument name="headline text" default="分散构图"} with a dark, modern graphic-design style, about scattered composition in visual layout.

Canvas: Portrait 3:4 poster, black background with subtle paper grain, high contrast, generous empty space, clean Swiss/modern editorial layout.

Main title area: Place a very large two-line Chinese headline in the upper left. The first line is off-white, the second line is lavender-purple. Under it, add the English subtitle “SCATTERED COMPOSITION” in uppercase lavender. Below the subtitle, add a short lavender horizontal rule and a left-aligned Chinese explanatory paragraph: “将视觉元素有意分散在画面各处，形成多个视觉焦点，营造开放、轻盈与多向的视觉体验。”

Visual structure: Scatter geometric elements across the poster, using asymmetrical spacing and multiple focal points. Include exactly 15 main graphic elements: 1 large yellow circle near the upper right, 1 medium purple circle at the center-right, 1 small orange circle near the middle, 1 teal square in the lower-left quadrant, 1 small pink square at the right-center, 1 small purple circle near the lower center-left, 1 large off-white hollow ring in the lower-right quadrant, 5 white plus signs distributed around the page, 1 yellow plus sign near the lower center, 1 purple 3-by-3 dot grid near the upper right, and 1 off-white 3-by-3 dot grid near the lower center-left.

Callouts: Add exactly 3 dotted leader-line annotations with small endpoint dots. Callout 01 points to the large yellow circle and uses yellow label text: “视觉焦点 01”, followed by white body text: “大面积色块吸引视线，建立主要焦点。” Callout 02 points to the medium purple circle and uses purple label text: “视觉焦点 02”, followed by white body text: “中等元素与留白结合，引导视线自然停留。” Callout 03 points to the small orange circle and uses orange label text: “视觉焦点 03”, followed by white body text: “小面积高对比元素，成为次级视觉锚点。”

Tip section: In the lower left, add a small purple lightbulb icon, the label “技巧提示” in purple, and the body text “通过大小、色彩、形状、方向的变化，在分散中建立联系，在留白中制造节奏。” Add a thin off-white underline below this block.

Legend: In the lower right, beside the large hollow ring, create a compact legend with exactly 4 rows. Row 1 has a yellow 3-by-3 dot icon, Chinese label “变化”, and English label “VARIATION”. Row 2 has a purple wavy-line icon, Chinese label “节奏”, and English label “RHYTHM”. Row 3 has a teal plus icon, Chinese label “呼吸”, and English label “BREATH”. Row 4 has a pink outlined square icon, Chinese label “开放”, and English label “OPENNESS”.

Visual style: Minimalist Chinese design infographic, bold typography, flat vector shapes, matte texture, sharp edges, dotted connector lines, color palette of black, off-white, lavender purple, yellow, orange-red, teal, and pink. Use strong negative space and no borders.

Constraints: Keep the poster text legible, maintain the exact counts of graphic elements, avoid extra illustrations, avoid photorealism, avoid watermark or logo.

Create a premium vintage travel-journal editorial page, vertical 4:5, featuring a warm photorealistic documentary photograph of a quiet {argument name="location" default="Bangkok neighborhood street"} with a {argument name="monument" default="monumental golden Buddha statue"} rising behind modest buildings, tangled overhead electrical wires, concrete utility poles, lush tropical greenery, weathered walls, narrow alleyways, and a {argument name="vehicle" default="small orange-red scooter"} parked in the foreground, captured in soft late-afternoon sunlight with nostalgic analog film grain and slightly faded warm tones; beside it, create a minimalist hand-drawn screen-print illustration of the exact same scene using rough ink outlines, muted olive green, ochre gold, terracotta, charcoal and cream colors, distressed imperfect ink and visible warm ivory paper texture, surrounded by generous negative space, with small elegant monospaced typewriter-style archival text reading “Bangkok, Thailand / No. 035 / temple · alley · everyday / 2026”; sophisticated Japanese travel-zine and vintage scrapbook aesthetic, refined editorial composition, tactile aged paper, subtle printing imperfections, authentic analog character, cohesive photo-to-illustration transformation, understated typography, cinematic yet natural, high detail, premium magazine design, no watermark, no logos, no unnecessary elements.

Turn the reference photo into a travel souvenir enamel pin badge. Compose it as a SCENE, not a single isolated object.

Subject hierarchy: the defining landscape, terrain or landmark of the photo forms the main body of the badge and occupies most of its area. If a person appears prominently in the photo, keep them in the badge as a small, simplified figure at true relative scale within that landscape — the person is an accent, the landscape is the subject.Preserve the original spatial relationship and scale between the figure and the surroundings.

How to render the person: flat enamel color blocks matching their real clothing and hair color from the photo. The face is a smooth plain area of light skin-tone enamel with no drawn facial features — do NOT render the person as a dark or black silhouette, and do NOT black out the face or head. Skin reads as a warm light enamel color, clearly lighter than the clothing.Styling: thin polished gold outline around the silhouette and along every internal divider, glossy enamel color fill, gentle even lighting with only a soft sheen on the gold lines, very subtle drop shadow. Outer contour follows the scene's own shape, not a plain rectangle.

Background: flat {argument name="background texture" default="dark navy coarse linen"} texture. Badge centered, filling about 60% of the frame.Avoid: black silhouette figure, blacked-out face, dark featureless head, portrait close-up, detailed facial features, person dominating the badge, cropping out the landscape, three-quarter angle, macro product photography, heavy specular glare, cartoon, realistic scene, text, watermark.

Create a {argument name="subject" default="charming minimalist 3D miniature coffee shop scene"} inspired by a {argument name="style" default="cozy handmade paper-and-clay aesthetic"}. Place a tiny, beautifully designed coffee store in the lower-center of a large textured off-white paper background, leaving plenty of clean empty space around it.

The coffee shop should look like a handcrafted miniature café: a small cream-colored storefront with a warm wooden counter, tiny espresso machine, coffee cups, pastries, coffee beans, little menu board, hanging sign, potted plants, stools, and subtle café decorations. Add a few tiny customers enjoying coffee and a barista behind the counter, keeping everything cute, delicate, and uncluttered.

Use {argument name="color palette" default="soft ivory, beige, warm brown, muted sage green, and subtle terracotta accents"}, with realistic soft shadows and gentle natural lighting. Add tiny hand-drawn black doodles around the café—small hearts, steam lines, stars, coffee beans, arrows, and simple decorative marks—to create a playful contemporary scrapbook feeling.

The overall composition should feel premium, cozy, whimsical, handcrafted, and Instagram/Pinterest aesthetic, with a tactile textured-paper background, miniature diorama appearance, soft 3D details, lots of negative space, and a peaceful cozy coffee-shop mood. Vertical 4:5 composition, highly detailed, clean, elegant, photorealistic miniature craft style.

Transform the people in the reference photo into a {argument name="illustration style" default="stylish hand-drawn fashion illustration"} while keeping their facial features, poses, expressions, hairstyles, clothing, body proportions, and overall composition recognizable. Use a {argument name="aesthetic" default="mixed-media aesthetic combining a realistic photographic background with detailed pencil-and-colored-pencil sketching on the people"}. Add visible hand-drawn cross-hatching, rough pencil strokes, subtle ink outlines, textured shading, and slightly imperfect sketch details. Keep the clothing highly detailed with realistic fabric folds and denim texture.

Surround each illustrated person with a thick irregular white sticker/paper-cutout border, as if they were individually cut out by hand. Add small pieces of semi-transparent white masking tape around the edges of some figures, creating a scrapbook/editorial collage effect. The background should remain realistic, softly lit, natural, and slightly blurred, creating a strong contrast between the photographic environment and illustrated subjects.

Aesthetic: Korean/Japanese fashion editorial, contemporary street-style illustration, scrapbook collage, fashion sketchbook, photorealistic background + hand-drawn characters, clean but imperfect pencil artwork, cozy muted tones, subtle film grain, soft natural lighting, premium editorial photography.

High detail, realistic faces, natural anatomy, expressive eyes, detailed hair strands, realistic clothing textures, clean composition, full-body framing, professional fashion editorial quality. Avoid overly cartoonish proportions, CGI appearance, excessive saturation, distorted hands, extra fingers, warped faces, or overly smooth digital painting.

For the exact {argument name="scene" default="“3 friends walking”"} look

Add this at the end:

Three stylish young adults walking together casually, interacting naturally and looking at each other, full-body shot, candid friendship moment, urban university/campus setting, relaxed oversized streetwear, wide-leg jeans and trousers, sneakers, tote bags and backpacks, photographed at eye level.