GPT Image 2 prompts

Create an ultra-photorealistic cinematic fashion editorial portrait of {argument name="subject" default="a young woman with shoulder-length black hair, wispy bangs, and round eyeglasses"} sitting curled up inside a large dark cylindrical industrial tunnel or pipe. The camera looks straight into the circular pipe from the open end, creating a strong centered composition with the subject seated low in the middle, knees drawn up tightly, feet together, and arms folded casually across the tops of her knees. She wears {argument name="outfit" default="a fitted black short-sleeve T-shirt, loose black pants, and black canvas sneakers with white laces and white soles"}. Her expression is calm and slightly confident, with direct eye contact and a subtle closed-mouth smile. The tunnel interior is black, glossy, rough-textured metal with visible scuffs, scratches, and wet-looking highlights. Surround the subject with dramatic circular motion-blur light trails following the pipe’s circumference: warm amber, orange, and occasional white streaks, especially near the outer rim, while the center remains sharp. Use moody low-key lighting with a warm rim light catching the hair and arms, soft frontal fill on the face, deep shadows around the pipe edges, and a high-contrast editorial look. Compose as a vertical 4:5 image, wide-angle lens perspective, symmetrical circular framing, subject centered, crisp realistic skin texture, natural proportions, detailed fabric, no text, no logos, no watermark. Make it feel like a high-end urban fashion photograph shot inside a dark industrial pipe with long-exposure light painting.

Create a photorealistic vertical winter portrait of {argument name="subject" default="a young Japanese woman"} outdoors in a city park, framed from chest up and looking directly into the camera with a gentle, quiet smile. She has {argument name="hair color" default="dark brown"} medium-length slightly messy hair with wispy bangs and loose flyaway strands glowing in backlight, warm brown eyes, natural makeup, soft skin texture, and subtle freckles across her cheeks and nose. She is wearing an oversized thick ribbed fuzzy knit sweater in {argument name="sweater color" default="warm gray taupe"}, with very long sleeves pulled over both hands as she cups her cheeks. Use a shallow depth of field with blurred green hedge leaves in the foreground at the bottom and a softly defocused urban background with tall buildings and round bokeh lights. Lighting should feel like {argument name="time of day" default="late winter afternoon golden hour"}: strong sun behind her head creating a bright rim light around her hair, warm highlights, soft shadows on the face, and a calm intimate mood. Shoot in a realistic 85mm portrait lens style, f/1.4, natural color grading, high detail on eyes, hair, and knit texture, vertical 2:3 composition, no text, no watermark, no extra people.

Create a gritty first-person survival-horror video game screenshot in a ruined industrial courtyard, as if captured from a cinematic FPS. The viewer holds a black semi-automatic pistol in the lower right foreground, aimed at one grotesque humanoid enemy standing extremely close in the center. The creature is hunched, wet, and decayed, with a lumpy parasite-like head covered in slick brown-black organic matter, dangling tendrils, exposed sinewy chest tissue, and a dark torn coat. The environment is a grimy abandoned brick-and-concrete factory alley with wet cobblestone paving, puddles, rust stains, blood smears, scattered debris, and heavy rain or water streaking across the image. Include exactly 1 large rusted cylindrical metal tank or silo elevated on thin legs in the upper right, exactly 1 large arched industrial window on the left brick wall, exactly 1 dark car partly visible in the background alley, and exactly 3 prominent vertical metal posts around the tank area. Use a wide 16:9 frame, low camera height, aggressive wide-angle lens distortion, high contrast, motion blur, dirty glass artifacts, heavy diffusion, chromatic smearing, and overprocessed photorealistic game-render texture. Add a minimal translucent HUD: in the bottom left show the label “HEALTH” above the number “32”; in the bottom right show a small ammo indicator with “AMMO” and the numbers “18” and “123”. Overall mood: oppressive, damp, rusted, diseased, chaotic, like {argument name="game style" default="a modern first-person survival horror shooter"}; make the scene feel like an intense close-quarters encounter with {argument name="enemy type" default="a grotesque parasite zombie"} in {argument name="location" default="an abandoned industrial courtyard"}. Use {argument name="lighting" default="cold dim overcast light with harsh wet reflections"} and {argument name="image treatment" default="extreme diffusion, grime, rain streaks, and GPT-image-like artifacting"}.

Create a photorealistic street-fashion portrait of a young East Asian woman in an all-black outfit sitting on a weathered wooden bench outside an old stone building. She is absorbed in reading a small paperback book, looking downward with a calm, introspective expression. She wears oversized black over-ear headphones, a loose black hooded sweatshirt layered under a black oversized utility jacket, faded charcoal wide-leg jeans, and chunky black lace-up combat boots with thick platform soles. Her {argument name="hair color" default="black"} hair is loosely tied in a messy bun with wispy bangs framing her face. One knee is raised on the bench while the other leg stretches forward, creating a relaxed urban pose. Place one compact patterned black-and-gray crossbody bag beside her on the bench. The setting is a muted city exterior with aged cream stone walls, a dark distressed wooden window frame with glass panes behind her, worn bench slats, and gray pavement. Use a subdued monochrome black-and-charcoal wardrobe palette, natural overcast daylight, soft shadows, realistic fabric texture, scuffed wood, slightly desaturated tones, shallow depth of field, and editorial fashion photography composition in a vertical 3:4 frame. No visible logos, no readable text on the book, no extra people, no watermark.

Goal: Create an elegant Chinese literary presentation cover slide about {argument name="topic" default="李清照对当代女性的启示"}, blending Song dynasty poetic atmosphere with modern editorial design.

Canvas: 16:9 horizontal slide, clean off-white background with a pale sage-green vertical panel occupying the right third. Use lots of negative space, refined margins, soft paper texture, faint ink-wash stains, and subtle gray botanical shadows across the middle.

Layout: Left two-thirds is the text area; right third is a still-life photograph area. Place the large headline in the upper-left, arranged as two lines of dark forest-green Chinese serif type: line 1 “李清照对当代”, line 2 “女性的启示”. Under the headline add a thin muted red horizontal accent line. Below it place the subtitle in smaller black Chinese serif text: {argument name="subtitle text" default="从文学人生，看见女性如何表达自我、选择人生、抵抗困境。"}

Middle-left feature row: include exactly 3 small icon cards in a horizontal row, separated by two thin vertical divider lines. Card 1 has a muted rose circular icon with a white leaf symbol and the label “以文学\n确立自我”. Card 2 has a warm beige circular icon with a white balance-scale symbol and the label “在时代与命运之间\n保持判断”. Card 3 has a desaturated teal circular icon with a white user silhouette and the label “不被单一\n身份定义”.

Bottom-left keyword row: include exactly 3 keywords separated by vertical bars, with a small dark green leading mark: “表达自我 | 保持独立 | 承受变化”.

Right still-life details: show an open antique Chinese letter or manuscript paper lying diagonally on a desk, with visible vertical handwritten Chinese calligraphy in gray ink. A black-and-brown calligraphy brush rests diagonally over the paper, pointing toward the lower-right. Add exactly 2 blooming plum blossom branches: one branch crosses the upper-right corner with several pale white-pink blossoms and buds, and one smaller branch extends from the center-left toward the right, casting soft shadows. The right panel background should be pale sage green; the paper is warm ivory with slightly curled edges and soft folds.

Visual style: tasteful, literary, museum-catalog minimalism; calm Song dynasty aesthetics; natural daylight from upper left; soft shadows; muted palette of ivory, forest green, sage, rose, beige, and ink gray; high-resolution editorial composition, realistic still-life photo blended with clean graphic typography.

Constraints: Keep all visible text in Chinese exactly as specified, with no extra captions or watermark. Maintain the 3 icon cards and 3 bottom keywords exactly. Avoid clutter, bright colors, cartoon styling, or modern tech UI effects.

Goal: Create a clean screenshot-like composition showing an AI image editing variation of a simple bear character, with the smaller original/reference result above and a larger edited result below.

Canvas: Wide horizontal canvas, approximately 1200×960 px, very light gray-white background with lots of empty space. Minimal interface feel, like a chat/image generation workspace.

Layout: Place exactly 2 bear illustration cards on the canvas. Card 1 is small and positioned in the upper-right quadrant, with a rounded white image area. Card 2 is much larger, positioned lower-left/center, also inside a rounded white image area. Between them, slightly below the small top bear, place exactly 1 pale blue rounded chat bubble containing Japanese instruction text. On the large bottom image card, include exactly 2 small translucent gray UI controls: one rounded pill button at the bottom-left labeled 「編集」 and one circular icon button at the bottom-right with a simple upload/share arrow icon.

Text content: The single chat bubble must read exactly: {argument name="edit instruction text" default="頬の横から首にかけてのあたりを、もっと細くしてください。"}

Subject details: The subject is exactly 2 versions of the same cute, hand-drawn, upright bear-like character. The character has off-white fur, thick black sketchy outlines, rounded ears with small inner-ear marks, wide circular eyes with black pupils, a large black oval nose, a tiny straight horizontal mouth, pink circular blush marks on both cheeks, short arms hanging down, stubby legs, and small toe lines. The top bear is smaller and slightly slimmer with a more vertical body. The bottom bear is larger and centered in its card, with a rounded head and body, narrowed neck/cheek area, simple symmetrical pose, and a slightly uncertain blank expression.

Visual style: Minimal doodle mascot illustration, rough black ink outline, subtle paper or canvas texture, soft off-white fill, pale pink cheek circles, no shadows except very faint card/UI softness. The overall image should look like a casual GPT image editing interface screenshot, not a polished poster.

Constraints: Use exactly 2 bear illustrations, exactly 1 Japanese chat bubble, and exactly 2 UI overlay controls. Keep the background mostly empty, preserve the asymmetrical placement, avoid adding extra characters, extra text, watermarks, or decorative elements.

Create a wide cropped comparison graphic showing two side-by-side image-generation quality results on a plain white background. The canvas is an ultra-wide horizontal strip, about 5:1 aspect ratio, cropped tightly so only the top portion of each result is visible. At the top left above the first crop place the bold black uppercase label “MEDIUM”; near the upper center above the second crop place the bold black uppercase label “HIGH”. Each of the 2 comparison panels shows the same fitness-class style tiled layout: a photographic band at the top with gym equipment and dark exercise machines, underneath a deep teal rectangular title bar with large bold white Japanese text {argument name="main tile text" default="有酸素"}. Use thick white borders and sharp diagonal white dividers between tiles, giving the layout a dynamic slanted collage look. Count exactly 2 main visible teal title tiles with the full text “有酸素”, one in each panel, plus exactly 2 partially visible neighboring teal tiles at the right edge showing only the first character or fragment {argument name="partial tile text" default="ス"}. A thin lower white divider and the top edge of another teal row are barely visible along the bottom, cropped off. Emphasize the artifact being compared: around the white Japanese letters on the solid teal backgrounds, include subtle uneven brightness and saturation patches, faint haloing, and mottled texture, with the “HIGH” panel slightly cleaner but still showing visible nonuniformity. Keep the composition as a technical screenshot/comparison crop, not a polished poster. Use crisp sans-serif typography, high contrast, no extra captions, no watermark.

Create a photorealistic waist-up outdoor portrait of a young East Asian woman, {argument name="character age" default="early 20s"}, with a natural gentle expression, looking directly into the camera. She has {argument name="hair color and style" default="medium chestnut-brown shoulder-length hair with soft layers and wispy straight bangs"}, warm brown eyes, smooth natural makeup, and slightly parted lips. She is wearing {argument name="outfit" default="a clean white lightweight hooded sweatshirt with drawstrings"}; show the hoodie fabric realistically with subtle folds, seams, sleeves, and soft shadows. Pose her standing at a slight angle with relaxed shoulders, hands lightly gathered near the lower right edge of the frame, upper torso visible. Use bright natural daylight with soft backlighting and rim light through her hair, creating a fresh candid city-street feeling. The background should be heavily blurred with shallow depth of field: dark vertical architectural columns or railings, circular white bokeh highlights, and a few small warm yellow/orange blurred lights. Use realistic skin texture, natural proportions, corrected hands and fingers, high-resolution DSLR portrait quality, 85mm lens look, f/1.8 bokeh, soft contrast, clean color grading, no text, no watermark, no extra people, no exaggerated glamour styling.

Create a vertical storybook paper-cut diorama illustration in warm autumn light: a tiny golden-brown hamster stands at the threshold of an arched doorway made from exactly 3 oversized maple leaves, counted as 1 muted green left leaf, 1 tall ochre center leaf forming the peak, and 1 golden-orange right leaf. The hamster, {argument name="character name" default="a small fluffy hamster"}, is seen from behind in three-quarter view, with round ears, black bead eye, tiny paws lifted, soft fur, and a small white tail, gazing into a glowing miniature autumn forest. Inside the leaf arch, show exactly 1 winding leaf-covered path, 2 dark tree trunks framing the sides, layered orange hills in the distance, and several falling maple leaves silhouetted against a bright sunset sky. Outside the doorway, use a matte sage-green paper-textured background and floor, with botanical cut-paper decorations around the frame: exactly 2 tall leafy sprigs on the left side and exactly 2 tall leafy sprigs on the right side, plus scattered flat autumn leaves on the ground. The whole scene should feel handmade from textured paper, with visible leaf veins, embossed fibers, soft shadows, warm golden light streaming out of the doorway, and a long cast shadow from the hamster across the foreground. Use a cozy seasonal palette of {argument name="autumn palette" default="sage green, ochre, amber, burnt orange, and soft gold"}. No text, no watermark, no photorealistic plastic look; keep it whimsical, tactile, softly cinematic, and centered.

Create a wide 16:9 anime-style classroom illustration with warm afternoon sunlight streaming through tall windows on the left, wooden desks, school bags, a green chalkboard with faint math equations, wall posters, a teacher's podium, and a door on the right. Show exactly 5 main characters in the classroom: 1) a strict young female teacher with long dark brown hair in a navy school-uniform-like jacket standing behind the podium, angrily pointing and throwing a piece of chalk; 2) a cheerful short blonde girl at the left desk wearing a black military-style beret and orange-black jacket, laughing with eyes closed; 3) a tiny purple-haired chibi girl in a lavender beret and outfit standing on a small stool beside a desk, gently poking or trying to wake someone; 4) a blonde schoolgirl asleep face-down at the front-right desk, messy hair, hair clips, navy blazer, plaid skirt, black boots, looking exhausted; 5) a dark-haired ponytail schoolgirl at the right desk in a navy uniform, startled with a sweat drop while watching the sleeping girl. Add a large comic thought bubble above the sleeping blonde girl showing exactly 7 miniature characters on a stage scene: the same blonde girl standing proudly in the center under warm spotlight, one smiling adult male teacher or host beside her, one elderly bald man clapping, and four smaller students around them applauding or watching. Use expressive manga faces, clean line art, soft cel shading, detailed classroom props, dynamic motion lines around the flying chalk, and a humorous school-comedy mood. Character customization: the sleeping girl is {argument name="sleeping character" default="a blonde schoolgirl with hair clips"}, the teacher is {argument name="teacher character" default="a strict long-haired brunette teacher"}, the small helper is {argument name="small helper character" default="a tiny purple-haired chibi girl in lavender"}, the left student is {argument name="left student character" default="a cheerful blonde girl in a black beret and orange jacket"}, and the setting is {argument name="classroom setting" default="a Japanese-style classroom at sunset"}. Avoid photorealism, avoid extra characters outside the listed 12 visible figures, and do not add readable text beyond faint chalkboard equations.

Create a clean anime-style half-body portrait of a young woman centered on a plain white background. She has {argument name="hair color" default="medium chestnut brown"} shoulder-length hair with soft layered ends, side-swept bangs, loose flyaway strands on both sides, and glossy highlight strokes. Her face is gentle and youthful with large warm brown eyes, bright white eye highlights, thin lashes, soft eyebrows, a tiny nose, a small closed smile, and faint pink blush lines on both cheeks. She is looking directly at the viewer with a slight head tilt and relaxed posture. Dress her in a simple cream long-sleeve blouse with a modest split neckline and soft fabric folds, tucked into a high-waisted dark navy skirt or waistband visible at the bottom of the frame. Use polished Japanese anime illustration style: clean dark line art, smooth cel shading, warm skin tones, subtle shadows under the chin and in the clothing folds, crisp details in the hair and eyes, no text, no props, no scenery, no watermark. Portrait composition, cropped from head to upper waist, with the character occupying most of the canvas.

Create a simple full-body cartoon illustration of a cute standing bear character on a plain off-white background. The bear is centered and facing forward, with a tall rounded body, white or very pale cream fur, thick uneven black hand-drawn outlines, and a deliberately naive children’s doodle style. Give it two round ears with pink inner circles, a slightly bumpy head outline, large wide-open circular eyes with tiny black pupils looking blankly ahead, and a large vertical pear-shaped orange snout outlined in black with a black oval nose and a short drip-like line beneath it. The body should have two long hanging arms along the sides, small three-bump paws, short legs, and simple toe marks. Add exactly 11 faint beige short dash marks scattered on the belly as subtle fur texture. Keep the composition minimal, flat, playful, slightly awkward, and imperfect, with no shadows, no text, no props, and no background details.

Using REFERENCE_0 as the character base, convert the subject into a clean 3D-model preview suitable for head-and-body joining tests. Repose the character to a mostly front-facing upper-body bust, simplify the silhouette, and make the head/neck connection clearly visible while preserving the unsettling doll-like face, horn-like side spikes, wrapped textile outfit, dangling cords, and worn fabric textures from the reference. Place exactly 2 identical copies of the resulting character render side by side, one on the left and one on the right, with matching scale and pose for comparison. Use a plain {argument name="background color" default="dark charcoal gray"} background, soft studio lighting, and a slightly rendered/photogrammetry look rather than a polished illustration. Crop to a wide landscape frame showing the head, shoulders, and upper torso only. Avoid adding text, logos, props, or extra characters.

Create a highly detailed anime-style semi-realistic illustration set in an old European medieval village courtyard beside a stone water well. The main subject is one young woman, {argument name="character name" default="a gentle village girl"}, shown from the waist up in the foreground, turned slightly sideways but looking directly at the viewer with a soft smile. She has {argument name="hair color" default="warm chestnut brown"} hair in a long loose braid over one shoulder, wispy bangs, fair skin with a subtle blush, bright gray-blue eyes, and delicate round wire-frame glasses. Dress her in a traditional peasant outfit: cream puff-sleeve blouse, dark forest-green fitted bodice with front lacing, green gathered skirt, and simple waist sash. Behind her, show exactly four background villagers near the well: 1) a young woman in a brown corset dress standing at left, 2) a small child partly hidden near the bucket chain, 3) a boy standing behind the well, and 4) two young women on the right drawing water together counted as one paired group interaction but visibly two figures, softly blurred by depth of field. Include a circular stone well in the left foreground with a wooden roof beam, hanging iron chain, and metal bucket; rustic cream plaster houses with dark roofs in the background; and a distant church tower with a pointed steeple rising into a bright hazy sky. Use {argument name="time period" default="medieval countryside"} atmosphere with no modern objects except the character's subtle fantasy-style glasses. Lighting should be warm late-afternoon sunlight from behind and above, creating rim light on her hair, soft bloom, gentle shadows, cinematic depth of field, painterly realism, intricate clothing folds, natural skin texture, and a peaceful nostalgic mood. Vertical portrait composition, 3:4 aspect ratio, no text, no watermark.

Create a highly detailed fantasy architectural product shot of an entire miniature city carved inside one continuous curved ribbon of {argument name="stone material" default="translucent white alabaster marble"}, shaped like a large open shell or looping stone band standing upright on a dark teal studio surface. The city should look like a luxurious Baroque Mediterranean micro-kingdom grown from the same stone: smooth white terraces, arched arcades, tiny stairways, bridges, colonnades, balconies, glowing warm windows, and delicate gold-vein inlays running through the stone like kintsugi. Include exactly 5 main landmark elements: 1 large circular domed observatory palace on the upper left with a brass armillary ring on its roof, 1 tall lighthouse-like tower on the upper right, 1 smaller round tower with a brass astrolabe on the center-right terrace, 1 small domed pavilion near the lower center, and 1 long arched aqueduct/gallery along the lower left. Add turquoise water features integrated through the city: 3 visible pools and 3 cascading waterfalls flowing between terraces. Add miniature cypress trees, tiny gardens, flowering shrubs, moss, and planters throughout the terraces, but keep the architecture dominant. Use {argument name="metal accent" default="thin polished brass"} for the astronomical instruments, fine seams, and delicate decorative lines. Lighting should be cinematic and museum-like, with warm golden light glowing from the windows and cool teal ambient light behind the sculpture; the background is a smooth dark {argument name="background color" default="deep teal"} gradient with soft haze. Render as an ultra-detailed macro photograph of a collectible architectural sculpture, three-quarter view from slightly above, crisp ornate details, translucent stone subsurface glow, polished wet reflections on the pools, shallow depth of field, no people, no text, no watermark.

Goal: Create a photorealistic fashion character design sheet for {argument name="character name" default="a stylish Black gangster-inspired antihero"} on a clean white studio background, showing the same character and outfit consistently across multiple views.

Canvas: Wide horizontal character sheet, approximately 16:9 aspect ratio, bright high-key studio lighting, pure white background, no shadows except soft contact shadows under the shoes.

Layout: Use exactly 3 visible character views arranged left to right: 1) full-body front view on the left, head cropped out at the top so the outfit is emphasized; 2) full-body side/profile view in the center, also with the head mostly cropped by tall hair and coat collar; 3) larger upper-body three-quarter portrait on the right showing the face, sunglasses, cigar, hair, jewelry, and coat details. Keep generous white negative space between the views.

Subject details: The character is a tall slim Black man with dark skin, angular face, confident intimidating expression, exaggerated upright spiked dreadlocks, black oversized sunglasses, and a cigar held in his mouth with a small glowing ember. He wears {argument name="statement coat" default="a long tan faux-fur coat with large irregular black leopard spots"}, with an oversized shaggy blond fur collar and plush sleeves. Under the coat is {argument name="shirt color" default="a vivid red satin open-collar shirt"}, partly unbuttoned at the chest. Add layered gold chains and pendants around the neck, a black leather designer belt with a gold double-ring buckle, high-waisted loose black trousers, glossy black pointed dress shoes, and red shirt cuffs visible at the wrists.

Props and enumerated visible items: Include exactly 2 firearms: one black handgun held low in the left/front view, and one compact black assault-style rifle held vertically downward in the center side view. Include exactly 3 character renderings/views: front full-body, side full-body, and close-up three-quarter portrait. Include multiple layered gold necklaces, black sunglasses, one cigar, one belt, and one long spotted fur coat repeated consistently across all views.

Visual style: Ultra-realistic editorial fashion photography mixed with character concept art, crisp fabric texture, detailed fur fibers, realistic skin, polished leather reflections, sharp focus, high-resolution product-design presentation, dramatic luxury streetwear mood.

Constraints: No text labels, no logos except a subtle designer-style belt buckle, no extra characters, no additional weapons beyond the 2 specified, no background environment, no cartoon rendering, maintain consistent outfit colors and proportions across all 3 views.

Create an ultra-photorealistic cinematic fashion editorial photograph of {argument name="subject" default="a young woman with long dark hair and round glasses"} sitting curled up inside a large dark cylindrical industrial tunnel or pipe. Use a vertical 4:5 composition shot from directly in front of the pipe, centered on the subject, with the circular tunnel filling the entire frame like a vortex. The subject sits low in the center with knees drawn up, arms folded and resting across the knees, feet close together, looking calmly into the camera with a subtle confident smile. She wears {argument name="outfit" default="a fitted black T-shirt, loose black pants, and black canvas sneakers with white laces and soles"}. The tunnel interior is black, glossy, worn, textured metal or concrete, with circular scuffs and gritty industrial surface detail. Add dramatic concentric light trails around the inside rim of the tunnel, mixing warm orange highlights and thin white streaks, as if created by long-exposure reflections following the pipe’s curvature. Lighting should be moody and high contrast: soft frontal light on the face and arms, warm rim highlights in the hair, deep shadows around the outer edges, and a strong circular frame around the subject. Use a wide-angle editorial lens feel with slight fisheye distortion, sharp focus on the subject, detailed skin and fabric texture, realistic glasses reflections, natural proportions, and no text, logos, watermark, or extra people.

Goal: Create a hyper-realistic, high-fashion editorial character bible sheet for {argument name="character name" default="DONATO"}, a Neapolitan pizzaiolo, presented like a premium fashion campaign and film character reference.

Canvas: Wide horizontal 16:9 white studio layout, clean magazine look, crisp cutout photography, soft shadows, high-resolution editorial lighting.

Layout: On the left, place massive bold black condensed sans-serif typography reading "{argument name="main title" default="DONATO"}" at the top. Directly below it, add the subtitle "{argument name="subtitle" default="THE PIZZAIOLO / NAPLES"}" in smaller bold black uppercase. Beneath the title area, show a large action portrait of the chef tossing stretched pizza dough, lit with a warm terracotta glow and flour dust in the air. In the center, display a full-body turnaround lineup with exactly 3 standing views of the same man: front view, side profile view, and back view. Along the right edge, stack exactly 4 rectangular close-up detail panels vertically: 1 close-up of intense brown eyes and flour-dusted face, 1 close-up of navy pinstripe apron tie and brass ring detail, 1 close-up of floury hand pressing dough on marble, and 1 close-up of worn black leather chef shoes.

Character details: Handsome Mediterranean man in his late 30s to early 40s, olive skin, wavy dark brown hair swept back, light stubble, strong nose, athletic average build, serious focused expression. He wears a white button-up shirt with sleeves rolled to the forearms, a dark navy charcoal pinstripe apron tied at the waist, black tailored trousers, and worn dark leather shoes. Keep the same facial features and body structure across all views.

Color system: Include exactly 4 circular color swatches near the lower-left/center area, each with small black labels and hex codes: Terracotta Ember #C85A32, Flour Dust White #F7F4EE, Fresh Basil #2E5A36, Hearth Charcoal #1F1E20.

Text content: Add the bottom-center tagline in bold uppercase black: "{argument name="tagline" default="90 SECONDS AT 900 DEGREES."}". Keep all typography sharp, editorial, and aligned with generous white space.

Visual style: Hyper-realistic studio photography mixed with luxury fashion reference sheet design, clean white background, premium culinary branding, dramatic but controlled lighting, subtle grain, no illustration style, no cartoon effects.

Constraints: Use exactly 1 large action portrait, exactly 3 full-body turnaround figures, exactly 4 right-side close-up panels, and exactly 4 color swatches. Do not add extra characters, props, logos, watermarks, or additional text.

Create a high-quality vertical outdoor portrait photograph of a young South Asian man with {argument name="hair style" default="short black hair parted to the side"}, medium warm-brown skin, thick eyebrows, dark eyes, and a neatly trimmed short beard and mustache. He is seated casually on an ornate black wrought-iron garden bench, facing the camera with a calm, neutral expression. He wears a {argument name="outfit color" default="dark chocolate-brown"} traditional shalwar kameez with a collared button-up tunic and matching loose trousers. Include exactly 3 visible accessories: a gold wristwatch on his right wrist, a silver ring on his left hand, and a thin black bracelet on his left wrist. Pose him with one arm resting along the bench back, the other hand relaxed near his knee, one leg bent and the other extended slightly, wearing brown leather sandals. Set the scene in a lush garden during golden hour, with warm sunlight filtering through trees and a canopy of bougainvillea flowers hanging overhead. The flowers should include exactly 3 prominent color groups: bright pink, pale pink, and creamy white blossoms, with green leaves surrounding them. Use shallow depth of field, creamy bokeh, soft backlighting, natural skin texture, realistic proportions, and a premium DSLR portrait look. Composition should be tall 9:16, subject centered in the lower half, floral canopy filling the upper third, no text, no watermark, no exaggerated retouching.

Using the provided reference image as a layout and style guide, create a clean before/after comparison showing a real coastal photo transformed into soft healing-color pixel art. Change the subject to {argument name="scene subject" default="a sunny seaside road with orange roadside convex traffic mirrors, blue ocean, and snowy mountains in the distance"}. Layout: use exactly 2 vertical panels side by side — the left panel is the realistic photo source, and the right panel is the pixel-art reconstruction. Keep the split at the center with no border.

Left panel: make it a bright, saturated real-photo coastal landscape with blue sky, large white clouds, turquoise sea, distant snow-covered mountains, a low concrete seawall, and orange roadside mirror poles. Include 2 visible convex mirrors: 1 full round mirror near the left-center edge and 1 partial cropped round mirror at the far left edge.

Right panel: reinterpret the left panel as low-resolution pixel art with large square blocks, pastel blue, cream, peach, lavender, and mint tones, airy negative space, and a calm therapeutic palette. Include exactly 2 full circular convex mirrors on one orange pole near the lower center-left, with the ocean, mountains, clouds, seawall, and small water highlights simplified into pixel blocks.

Add decorative pixel details only on the right panel: dotted halftone squares, tiny pastel square accents, a small sparkle/star icon, and exactly 3 small heart icons stacked vertically near the upper-right area. Add small pixel text at the lower-left of the right panel reading {argument name="caption text" default="WIND FROM\nTHE SEA\nCARRIES LIGHT."}. Use a wide horizontal canvas, crisp pixel edges on the right, bright daylight, no people, no watermark.

Goal: Create a detailed vintage illustrated visual reference sheet for {argument name="food subject" default="Croissant"} in a warm hand-drawn {argument name="art style" default="Studio Ghibli style"}, like a pastry-making guide from an old cookbook.

Canvas: Wide horizontal 16:9 composition on warm cream parchment paper, with thin brown rounded panel borders, muted sepia ink outlines, soft watercolor shading, and cozy bakery lighting. Use an off-white background with subtle paper texture.

Header: Large bold hand-lettered title at the top left reading “{argument name="headline text" default="CROISSANT"}”. Beneath it, smaller uppercase subtitle: “VISUAL REFERENCE SHEET – STUDIO GHIBLI STYLE”, flanked by small decorative leaf sprigs.

Layout: Divide the sheet into 5 main areas: 1 large ingredients panel on the upper left, 1 tools panel on the lower left, 1 color palette strip along the bottom left, 1 large finished croissant showcase panel on the upper right, and 1 making process panel with 5 numbered steps on the lower right.

Ingredients panel: Label the panel “INGREDIENTS”. Show exactly 6 ingredient illustrations arranged left to right, each with a bold uppercase label and a short note: 1) raw dough ball, smooth and pale, dusted with flour; 2) flat beaten butter, pale yellow and cold; 3) rolled out dough, thin and even rectangular sheet; 4) dough triangle, before rolling; 5) raw crescent, unbaked and pale soft; 6) baked croissant, golden and flaky with caramelized surface.

Tools panel: Label the panel “TOOLS”. Show exactly 5 tools arranged left to right: 1) wooden rolling pin, captioned for rolling dough evenly; 2) pastry knife with wooden handle, captioned sharp blade for clean cuts; 3) metal baking tray lined with parchment paper; 4) pastry brush with wooden handle, captioned for egg wash application; 5) brick oven with glowing fire, captioned high heat for baking.

Finished croissant panel: Label it “FINISHED CROISSANT”. Show one large finished croissant on a white oval plate, angled slightly from lower left to upper right. The croissant is oversized, glossy, golden brown, crescent-shaped, with many visible laminated layers, darker caramelized ridges, flaky cracks, toasted spots, and a soft shadow on the plate.

Making process panel: Label it “MAKING PROCESS”. Include exactly 5 vertical numbered cards from left to right, each with a dark circular number badge and a small illustration above text: 1) “BEAT BUTTER FLAT” showing a square block of butter on parchment, note that butter is beaten between sheets until flat and even in a square; 2) “WRAP AND SEAL” showing dough folded around butter, note to place butter in the center of rolled dough and seal edges tightly; 3) “FOLD AND ROLL” showing a folded laminated dough stack, note to fold dough and roll out and repeat several times to build layers; 4) “CUT AND SHAPE” showing long dough triangles and a raw crescent, note to cut into triangles and roll up from base to tip; 5) “EGG WASH AND BAKE” showing several croissants on a baking tray, note to brush with egg wash and bake until golden and flaky.

Color palette strip: Label it “COLOR PALETTE”. Show exactly 7 circular color swatches with names and hex codes: 1) Dough Cream #F5ECD7, 2) Butter Yellow #F5C518, 3) Baked Gold #D4A55A, 4) Caramel Crust #8B5E3C, 5) Flaky Interior #FAF3E0, 6) Parchment White #F9F6F0, 7) Char Brown #3D1F0A.

Typography and style: Use bold condensed hand-drawn uppercase lettering for labels, smaller neat handwritten captions, dark chocolate-brown ink, rounded cream label tabs, and consistent old-fashioned bakery reference-sheet design. Keep all illustrations charming, clean, and readable, with soft painterly shadows and warm amber highlights.

Constraints: Include no people, no photorealism, no modern UI elements, no watermark, and no extra sections beyond the described 5 main areas. Keep all visible English text legible and spelled correctly.

Cinematic, ultra-realistic portrait of a {argument name="subject" default="young man"} use image for face standing in a vast field of {argument name="flower type" default="vibrant red poppies"} at {argument name="time of day" default="sunset"}, shown in left-facing side profile. He has dark hair, subtle stubble, and a calm, serious expression. He wears a white nike tshirt with denim jeans. Thick atmospheric smoke and mist drift around the field and partially obscure the lower body. Dramatic storm clouds fill the sky, with an intense fiery red-orange sunset glowing along the horizon, contrasted by cool cyan-blue light and haze on the right side. Moody, melancholic, dramatic atmosphere, strong cinematic lighting, deep shadows, volumetric fog, shallow depth of field, foreground poppies softly blurred, highly detailed face and fabric texture, realistic skin, natural proportions, editorial fashion photography, dark teal and burnt-orange color grading, anamorphic cinematic aesthetic, 85mm lens, f/1.8, HDR, photorealistic, vertical composition, 4:5 aspect ratio.

A stunning, high-detail portrait of an elegant {argument name="subject" default="young East Asian woman"} with a {argument name="hairstyle" default="delicate updo hair hairstyle"} adorned with glowing {argument name="accessory" default="red butterfly"} accessories. She is wearing an intricate, sleeveless crimson red gown featuring a sheer back crafted from lace and glitter with a prominent red butterfly design centered on her back. Dark, ethereal background filled with soft bokeh lighting and floating glowing red butterflies, cinematic lighting, 8k resolution, photorealistic, ultra-detailed.

Ultra-realistic cinematic editorial portrait of a strikingly handsome young man in his early 20s, completely original character, posed at an {argument name="setting" default="elegant vintage billiards hall"}. He has thick, slightly tousled {argument name="hair color" default="jet-black"} hair, strong well-defined eyebrows, deep expressive dark-brown eyes, a straight sculpted nose, prominent cheekbones, a defined masculine jawline, and subtle natural stubble. He wears a {argument name="clothing" default="crisp off-white button-up shirt with black suspenders"}, and tailored black trousers.
He is seated beside a classic green-felt billiards table, holding a wooden pool cue naturally with both hands, looking slightly to the side with a calm, serious, thoughtful expression. Several colorful billiard balls are visible in the foreground with beautiful shallow depth of field.
The setting is a luxurious old-world billiard room, dark polished wood, vintage wall decorations, warm table lamps, rich brown tones, subtle burgundy curtains, elegant atmospheric details. Warm cinematic tungsten lighting falls naturally across his face, creating soft highlights and deep shadows. Photorealistic skin texture, realistic fabric details, natural hands and anatomy, sophisticated masculine styling, cinematic color grading, 85mm portrait lens, f/1.8, shallow depth of field, soft background bokeh, dramatic but elegant composition, high-end editorial photography, ultra-detailed, 8K realism, vertical 2:3 composition.