GPT Image 2 prompts

Create a vertical 9:16 ultra-realistic Chinese guofeng bridal portrait of {argument name="character name" default="a young noblewoman"} looking back over her shoulder toward the viewer, with her body turned away and her face in a soft three-quarter profile. She has porcelain skin, delicate makeup, glossy dark eyes, soft red lips, and {argument name="hair color" default="black"} hair styled in a low traditional updo with loose wispy strands framing her face. She wears an extremely ornate golden phoenix crown: exactly one large sculpted phoenix with raised wings on the upper right side, one dense filigree crown base covered with pearls and red gemstones, three prominent long vertical tassel clusters hanging on the right, two shorter gold tassels near the temple, and one visible red-and-gold drop earring. Her robe is a luxurious embroidered Chinese wedding garment in {argument name="robe color" default="champagne gold with deep red and muted blue floral embroidery"}, featuring metallic gold thread, large peony blossoms, phoenix-like swirling embroidery on the back, red trim, and heavy brocade texture. Use warm candlelit palace interior lighting with soft amber bokeh in the background, shallow depth of field, cinematic realism, intricate jewelry detail, luminous silk sheen, elegant melancholic expression, high-end fashion editorial composition, close portrait crop from head to upper torso, no text, no watermark.

Create a polished anime-style single-panel illustration of two young women sitting together at an outdoor café terrace in warm late-afternoon sunlight. On the left is {argument name="left character hair color" default="short pale blonde bob hair"}, amber eyes, a cheerful open-mouth smile, leaning forward while holding one tan paper sheet with both hands; she wears an airy cream blouse with puffed sleeves, red ribbon straps/suspenders, a small red hair ribbon with dangling ornament near one side, and a delicate gold necklace. On the right is {argument name="right character hair color" default="long straight black hair"}, violet eyes, a soft reserved smile, looking toward the blonde girl; she wears a dark navy button-up blouse and a subtle pendant necklace, with her arms resting on the wooden table. Include exactly two visible people, exactly one paper sheet, exactly one white teacup on a saucer in front of the right girl, and exactly one small flower arrangement at the lower left edge with white daisies and red flowers. The setting is a cozy European-style terrace with wicker café chairs, a polished wooden tabletop, leafy greenery framing the sides, and a softly blurred townscape in the background with pale buildings and one church-like spire. Use cinematic golden-hour backlighting from the upper left, soft bokeh, gentle rim light on hair, detailed expressive faces, delicate linework, painterly anime rendering, warm inviting atmosphere, and a horizontal 3:2 composition. No text, no watermark, no extra characters, no modern signage.

Create a centered chibi fantasy character in crisp 16-bit pixel art on a plain white background. The subject is a cute small mage/priestess named {argument name="character name" default="Astra"}, shown full body, facing forward, with a neutral slightly serious expression, large dark red eyes, pale skin, and short blond hair with straight side locks. She wears an ornate golden headpiece resembling goggles or a circlet across the forehead, with a small red jewel centered above the brow, plus dark ear-covering side pieces. Her outfit consists of exactly 6 main visible clothing/accessory pieces: a dark blue scarf/capelet wrapping around the neck and flowing to the right, a white tunic dress, a gold waist belt with a small rectangular buckle, dark brown gloves or arm guards with gold cuffs, dark boots, and a deep blue cloak or backpack-like mantle behind her sides. In her left hand she holds one tall wooden staff positioned vertically along the left side of the image; the staff has a crooked dark-brown shaft, a round top frame holding a bright cyan crystal, and exactly one small red hanging charm dangling from a short cord below the crystal. Use chunky square pixels, limited color palette, visible black/dark-brown outlines, simple cel shading, no anti-aliasing, no gradients beyond pixel clusters, no text, no watermark, and keep the character occupying most of a square canvas. Customize the hair as {argument name="hair color" default="golden blond"}, the eye color as {argument name="eye color" default="dark red"}, the scarf color as {argument name="scarf color" default="deep navy blue"}, and the staff crystal color as {argument name="crystal color" default="bright cyan"}.

Create a photorealistic vertical beach portrait of an adult {argument name="subject" default="young East Asian woman"} standing waist-deep in the ocean at golden hour, smiling brightly at the camera with wet shoulder-length dark hair clinging naturally to her face and neck. She wears a simple {argument name="swimsuit color" default="black"} one-piece swimsuit and reaches one hand toward the lens while playfully throwing seawater, forming a large sparkling arc of water droplets around her head and across the foreground. Use a close, slightly low-angle perspective with the subject centered, ocean horizon in the background, warm sunset light from the left, soft backlit glow, shimmering bokeh droplets, shallow depth of field, realistic skin texture, natural joyful expression, cinematic summer atmosphere, high-speed photography freezing the splash, 35mm lifestyle photography look, no text, no watermark.

Goal: Create a 2x2 comparison collage showing four generated anime-style reference images for a short video concept, on a dark charcoal background with large white labels.

Canvas: Landscape 3:2 composition, approximately 1200x900 px. Use a matte black/dark gray background. Arrange exactly 4 rectangular image panels in a clean grid with generous margins and gutters. Each panel has a large bold white label above it: exactly 4 labels, “@image1” at top left, “@image2” at top right, “@image3” at bottom left, and “@image4” at bottom right.

Overall visual style: Soft hand-drawn anime illustration, warm muted colors, gentle line art, subtle watercolor-like shading, nostalgic Japanese school atmosphere, clean character design, no photorealism. The recurring subject is {argument name="character description" default="a cute middle-school Japanese girl with shoulder-length dark brown wavy hair, simple dot eyes, a small smile, and a sailor-style school uniform"}. Her outfit is consistent across panels: cream short-sleeve sailor blouse with navy trim, orange neckerchief, dark plaid pleated skirt with orange and teal lines, navy knee socks with orange stripes, and beige sneakers.

Panel @image1: A single illustration on a warm beige background. Show exactly 1 girl sitting at a classic school desk and chair in side three-quarter view, facing right. She is relaxed with both hands on the desktop as if writing or reading. Include exactly 1 desk and exactly 1 chair, with thin black metal legs and a wooden seat/backrest. Her legs extend forward slightly; sneakers are visible. Keep the background plain and minimal.

Panel @image2: A character turnaround sheet on a clean white background. Show exactly 3 full-body views of the same girl, evenly spaced: 1 front view on the left, 1 side profile view in the center facing left, and 1 back view on the right. Keep the proportions chibi-like but not super-deformed, with a large head, small body, and simple facial features. No extra props or text inside this panel.

Panel @image3: A bird’s-eye view illustration of {argument name="school setting" default="a small suburban Japanese school"}. Show exactly 1 main school building, rectangular and two stories tall, with a dark teal roof and long rows of windows. Include exactly 1 sandy schoolyard with faint white court markings, exactly 1 perimeter wall, and surrounding residential neighborhood houses, trees, narrow streets, utility poles, and warm afternoon lighting. The perspective should be high aerial/isometric, like a reference image for a 3D scene.

Panel @image4: View into a classroom through a large window frame, as if the viewer is outside looking in. In the foreground, show exactly 1 main girl seated at a desk near the window, facing slightly right, with an open book or notebook on her desk. Behind her, show exactly 6 background students seated at separate desks, softly blurred and simplified, facing forward or downward as if studying. Include warm sunlight, window reflections, classroom wall panels, and rows of desks. The window frame should visibly border the panel and create a cinematic shot.

Constraints: Keep all 4 panels in the same illustration style and color palette. Do not add extra panels, extra labels, watermarks, captions, or logos beyond the four @image labels. The collage should look like a social media post showing four prompt-generated reference images.

Create a warm, softly lit storybook watercolor illustration of a very fluffy golden Syrian hamster sitting centered on a pale wooden floor in a quiet artist studio. The hamster is round and oversized, with tiny rounded ears, closed sleepy eyes, a small pink nose, delicate whiskers, tiny front paws, and two little pink feet visible at the bottom. It holds one rectangular cream-colored placard hanging from two small metal rings, with hand-painted Japanese text reading {argument name="sign text" default="私はにじじゃーにーで\n既に200枚を\n使い切りました"}. Surround the hamster with exactly 10 blank picture frames or canvases: 6 on the left side consisting of a tan standing frame, a white standing frame, a tall gray leaning frame, a pale rectangular board behind them, a small square board in front, and one flat sheet on the floor; 4 on the right side consisting of a tan upright frame, a white leaning frame, a small tan rear frame, and one flat white board lying on the floor in the foreground. The background is a minimal pale plaster wall with subtle seams and texture, and a tall window at the upper right casts golden late-afternoon sunlight and soft rectangular shadows across the wall and floor. Use delicate ink outlines, soft watercolor washes, cream and honey tones, airy negative space, gentle melancholic cuteness, and a hand-drawn children’s book aesthetic. Keep the composition square, centered, uncluttered, no extra characters, no watermark, and no additional readable text.

Goal: Create a photorealistic portrait overlaid with a pose-estimation / 3D block-model visualization, as if analyzing a seated human body with cuboid volumes aligned to a floor grid.

Canvas: Vertical 4:5 image, soft natural daylight, realistic camera photo look. Indoor minimalist living room with pale wall, light wood floor, and a cream rug in the foreground. In the left background, include one wooden shelving unit with white books and woven baskets, plus one leafy green houseplant above it.

Main subject: A young East Asian woman, about early 20s, sitting on the floor facing the camera in a compact curled pose. She has {argument name="hair color" default="dark brown"} long straight hair with wispy bangs, natural makeup, warm eyes, and a gentle slight smile. She wears a loose {argument name="top color" default="cream white"} long-sleeve sweater, blue jeans, white socks, and no shoes. Her knees are pulled up close to her chest, arms wrapped around her shins, feet together near the bottom center, body leaning slightly to one side while maintaining eye contact with the camera.

Overlay: Add a semi-transparent technical 3D pose-estimation diagram over the photograph. Use thin brown-gray wireframe cuboids and translucent teal-blue rectangular prisms to approximate the body volumes. Count and show exactly 13 major cuboid body blocks: 1 head block, 1 neck block, 1 torso block, 1 pelvis/hip block, 2 upper-arm blocks, 2 forearm blocks, 2 thigh blocks, 2 lower-leg blocks, and 2 foot blocks. The blocks should be imperfectly aligned but plausibly matched to the seated pose, with visible perspective lines, overlapping transparent faces, and wireframe edges. Include a faint perspective floor grid in pale blue-purple lines, matching the room floor and receding toward the background.

Label: At the top left, place one rounded white translucent label bar with Japanese text exactly: {argument name="overlay label" default="直方体モデルの重ね合わせ｜グリッドと同じ1単位"}. The label should use a small clean sans-serif font, dark gray text, and sit slightly inset from the image edge.

Visual style: realistic high-resolution lifestyle photography blended with analytical AR overlay, soft shadows, shallow depth of field, calm domestic atmosphere, clean composition, no watermark, no extra labels or diagrams beyond the single top-left label and the cuboid/grid overlay.

Using REFERENCE_0 as the source scene, convert the game screenshot into a clean, explorable 3D environment render of the same old school gym battle arena, as if rebuilt in Blender/real-time 3D. Remove all game UI, dialogue, HUD elements, text overlays, minimap, health bars, and the player character. Keep only the gym setting and the central masked shadow spirit with its glowing purple sealing magic circle, but make the monster more like a solid 3D asset hovering above the court rather than a 2D effects-heavy apparition.

Environment changes: make the gymnasium architecturally realistic and detailed, with a polished wooden basketball court, accurate court markings, wall padding, wooden wall bars, doors, a stage with closed red curtains at the far end, side balconies/upper walkways with railings, large windows, visible steel roof trusses, and hanging industrial ceiling lamps. Include exactly 4 visible basketball hoops: two on the left wall, one at the far back, and one on the right wall. Use cool indoor evening lighting with subtle purple spill from the spirit and magic circle, realistic reflections on the lacquered floor, and a wide cinematic camera angle from an elevated spectator viewpoint.

Style: realistic 3D anime-game environment render, clean composition, high fidelity school gym details, no characters besides the summoned spirit, no interface, no captions, no watermark. The result should feel like a playable UE5/Blender level based on the reference image.

Using REFERENCE_0 as the character base, transform the anime character into a simple stylized 3D toy/avatar model while preserving the recognizable face cues, round glasses, short dark bob haircut, and gentle expression. Change the result from a 2D illustration lineup into a single full-body 3D render in a neutral standing pose, viewed slightly from above and slightly three-quarter front.

Style: soft, glossy plastic / clay-like 3D character with simplified anatomy, rounded forms, segmented doll-like limbs, and minimal facial detail. Make the hair into chunky sculpted pieces rather than painted strands.

New outfit and body design: replace the original exposed/censored body with a modest toy outfit made of exactly 5 visible components: 1 oversized white T-shirt, 1 pale blue letter “M” on the shirt front, 1 blue shorts/hip piece, 2 blue leg pieces, and 2 rounded white shoes. Use simple cylindrical arms with mitten-like hands and blocky shoulder pieces.

Scene: place the character alone on a pale blue-gray studio floor plane against a dark nearly black background, with soft overhead lighting, gentle shadows, and a clean 3D preview/render look.

Constraints: do not include the original multi-view lineup, censor mosaic, or reference sheet layout. Do not add text other than the single shirt letter {argument name="shirt letter" default="M"}. Keep the model cute, non-realistic, and clearly toy-like. Use {argument name="character style" default="soft glossy plastic 3D avatar"} and {argument name="background" default="dark studio backdrop with pale blue-gray floor"}.

Create a richly detailed vertical anime fantasy illustration of two young women relaxing at a small wooden café table on a high balcony built into an enormous forest city. In the foreground, show exactly 2 characters: a brown-haired girl in a green cloak on the left, leaning on one hand and smiling while holding a teacup, and a blonde girl in a blue-and-cream adventurer outfit on the right, seated with both hands around a cup, facing her friend. The table should include exactly 5 visible tabletop items: one dark green teapot, two teacups, one small plate with pastries, and one glowing lantern. Surround them with wooden railings, flower boxes, leafy plants, a canvas awning, and warm dappled sunlight. Beyond the balcony, reveal a vast vertical elven/treehouse metropolis built among gigantic ancient trees, with countless cozy houses, spires, market tents, hanging banners, glowing windows, and multiple elevated wooden bridges and rail lines layered into the distance. Include exactly 5 visible tram cars on the elevated tracks at different depths, with warm lit windows. Add a few small white birds flying in the sunbeams. Use a breathtaking high-angle composition, immense depth, intricate architecture, golden morning light filtering through dense green canopy, soft atmospheric haze, painterly anime style, cinematic fantasy worldbuilding, extremely detailed but clean linework, warm inviting mood, no text, no watermark. Customization slots: the city should feel like {argument name="fantasy city type" default="an elven forest tram city"}, the foreground characters should be {argument name="main characters" default="two young female adventurers having tea"}, the lighting should be {argument name="lighting mood" default="golden morning sunbeams through leaves"}, the setting details should emphasize {argument name="architectural focus" default="wooden bridges, treehouse towers, and elevated tram rails"}, and the art style should be {argument name="art style" default="highly detailed painterly anime fantasy illustration"}.

Create a high-quality vertical anime-style portrait of a cheerful Japanese high school girl in a sunlit school hallway. She is turned slightly away from the viewer but looking back over her shoulder with a gentle smile, raising one open hand in a friendly wave. She has {argument name="hair color" default="glossy black"} hair styled in two loose braided pigtails with soft wispy bangs, large warm brown eyes, delicate round wire-frame glasses, smooth fair skin, and a subtle natural blush. She wears a classic sailor-style school uniform: a white short-sleeve blouse, navy sailor collar with two white stripes, a red necktie, and a dark pleated skirt. The hallway background is softly blurred with windows on the left, cool blue-gray walls, and strong late-afternoon sunlight streaming in, creating bright rim light, dappled highlights on her hair and shirt, and cinematic depth of field. Use polished modern Japanese anime rendering with semi-realistic lighting, detailed hair strands, soft painterly skin, expressive eyes, clean linework, and a warm nostalgic school-life atmosphere. No text, no watermark, no extra characters.

Create a hyper-detailed premium collectible statue render of {argument name="character name" default="the Founder"}, a mythic ancient warrior-king posed on an ornate display base against a plain dark charcoal studio background. The figure is a full-body 3D figurine in a dramatic heroic stance: left arm extended outward with open hand, right fist clenched at his side, torso turned slightly left, one boot raised on jagged rubble. He is an elderly but extremely muscular man with tan skin, stern face, thick gray eyebrows, long flowing gray hair, and a full gray beard. Dress him in dark bronze-and-black fantasy armor: layered bracers, heavy boots, lion-head knee guards, engraved belt with a central lion face, black leather skirt panels with intricate gold filigree, fur-lined shoulder mantle, ornate round shoulder clasps, and a tattered deep red cape sweeping to the right. Surround him with exactly 4 large spiraling bands of glowing golden magical energy, made of many bright ember-like filaments and sparks, wrapping from the base around his legs, behind his torso, and over his head; include exactly 14 small floating dark rock fragments caught in the energy field. The base is a round black-and-bronze museum-quality statue plinth with jagged black rubble on top, exactly 3 broken classical stone columns, heavy chains, gold trim, and exactly 5 sculpted lion-head ornaments visible around the front rim. On the central front plaque, show the text {argument name="base plaque text" default="始祖"} in engraved gold characters. Lighting should be cinematic studio lighting with warm orange glow from the magic, crisp shadows, high contrast, ultra-sharp details, realistic resin/painted-metal materials, and a vertical product photography composition. Make it look like an exceptionally expensive limited-edition fantasy figure, not a flat illustration; no watermark, no extra text besides the base plaque.

Create a highly detailed vertical kawaii anime illustration in a soft pink bedroom filled with teddy bears and sparkling decorations. Center a cute anime girl named {argument name="character name" default="Astra"} with long fluffy twin-tail {argument name="hair color" default="bubblegum pink"} hair, glossy magenta-pink eyes, pale skin, a small pouty mouth, and a slightly bashful expression. She wears an elaborate pink idol-lolita dress with layered ruffles, lace trim, checkered pink fabric, bows, frilled wrist cuffs, a corset-style waist ribbon, thigh-high white-and-pink stockings, and multiple teddy-bear accessories. Her twin tails are tied with two oversized pink gingham lace bows, each decorated with a small bear face charm; add a curled ahoge strand above her head. She sits facing the viewer in a plush pastel room and holds a white rectangular sign in front of her chest with large handwritten Japanese text {argument name="sign text" default="あすとら"} in thick bright pink brush lettering, plus small doodles: a bow, crown, hearts, stars, wavy lines, and a simple bear face. Her right hand points toward the sign while her left hand grips it. Surround her with exactly 6 visible teddy bears: 1 large bear at lower left raising both arms, 1 medium bear at mid-left beside the sign, 1 bear peeking from the upper-left background, 1 bear at upper-right background, 1 cheerful bear at right middle raising one paw, and 1 large bear at lower-right raising both arms; all bears are beige with pink bow ties and joyful faces. Add white and pink decorative sparkle icons, heart doodles, and emphasis marks around the character, especially at the left and right edges. Background: dreamy pink bedroom with soft-focus curtains, plush bedding or cushions, a warm table lamp, pastel furniture, and more pink decorative details, blurred enough to keep focus on the character. Visual style: polished modern anime key visual, ultra-cute yume-kawaii aesthetic, pastel pink color palette, luminous highlights, soft bloom, glossy eyes, delicate linework, dense lace and fabric detail, high resolution, portrait 3:4 composition, no watermark, no extra readable text beyond the sign.

Create a cute, dreamy, ultra-realistic digital-art portrait of a young woman with {argument name="hair color" default="long wavy dark brown hair with subtle warm highlights"}, soft fair skin, large hazel-green eyes, natural brows, a small straight nose, and soft pink lips, gazing slightly upward and to the viewer’s right with a calm gentle expression. She wears a {argument name="headband style" default="red headband tied in a large bow with white polka dots"}, small gold heart-shaped earrings, a {argument name="shirt color" default="coral pink long-sleeve shirt"}, and blue denim overalls with visible seams, front bib pocket, straps, and brass hardware. Frame as a vertical waist-up portrait, centered, with her head and shoulders filling most of the image, slightly tilted pose, hair flowing over one shoulder in voluminous loose waves. Use a warm peach-to-orange dreamy background with soft glowing bokeh lights and exactly 12 floating decorative elements: 7 red hearts and 5 small golden stars scattered around her head. Make the style polished, cute, romantic, semi-photorealistic digital painting with smooth skin rendering, detailed hair strands, soft studio lighting, shallow depth of field, warm color grading, and no text or watermark.

Create a polished vertical portrait of a cute young woman with {argument name="hair color" default="long wavy dark brown hair"}, soft fair skin, large light hazel-green eyes, natural brows, subtle rosy makeup, and a gentle dreamy expression, looking slightly upward and to the side rather than directly at the camera. She wears a bright red headband tied in a large bow with white polka dots, small gold heart-shaped earrings, a {argument name="shirt color" default="coral pink"} long-sleeve shirt, and blue denim overalls with visible stitching, a front bib pocket, brass buttons, and a shoulder buckle. Frame her from mid-torso up in a centered three-quarter portrait, with her hair flowing over one shoulder and a soft studio beauty-lighting look. The background is a warm peach-orange gradient filled with creamy circular bokeh lights and exactly 14 floating decorative shapes: 8 red hearts of varying sizes and 6 small golden stars, softly blurred at different depths. Use a romantic kawaii-inspired semi-realistic digital painting style, high detail in the face and hair, smooth skin, warm color grading, shallow depth of field, no text, no watermark, no extra people, vertical 9:16 composition.

Goal: Create a warm vertical Xiaohongshu-style illustrated poster explaining that letting AI think longer can reduce the bill, using a cozy home DIY scene and clear handwritten Chinese typography.

Canvas: Vertical 3:4 social media poster, soft golden afternoon light, high-resolution anime/editorial illustration, inviting and optimistic.

Main headline: At the very top, place a large cream brush-stroke banner with bold hand-painted Chinese text: {argument name="headline text" default="让 AI 多想一会儿，账单竟然少了近一半"}. Emphasize the final phrase in orange-red while the rest is dark brown-black. Add small yellow-orange emphasis rays on both sides.

Subtitle: Directly below the headline, add a smaller rounded white label with Chinese text: {argument name="subtitle text" default="Astra 的能力曲线为什么开始拐弯"}.

Central scene: A cute young man with {argument name="hair color" default="messy dark brown hair"}, wearing a forest-green sweater and dark pants, sits cross-legged on a rug in a sunlit room. He looks upward thoughtfully with a small smile, holding a pencil near his chin and an open instruction booklet in his lap. The booklet shows a simple line drawing of a shelf on the left page and a checklist on the right page.

Counted text elements and labels: Include exactly 1 thought bubble above the character with Chinese text: {argument name="thought bubble text" default="先想清楚 再动手..."}. Include exactly 4 checklist rows in the booklet: 3 checked items labeled 「思考」, 「规划」, 「执行」, and 1 unchecked grey item labeled 「返工」. Include exactly 1 whiteboard chart in the background labeled 「效果 vs 成本」 with a vertical axis 「效果 (%)」 and horizontal axis 「成本 ($)」. On the chart, show exactly 2 curves: an orange solid curve with round markers bending upward then flattening, labeled 「Astra 开始拐弯」 with an orange arrow, and a grey dashed curve labeled 「不够思考 成本更高」.

Room and objects: The setting is a cozy living room or study with blurred plants, framed pictures, warm window light, and a wooden shelving unit being assembled. Show exactly 1 sleeping orange-and-white cat curled on top of the shelf. Show scattered DIY parts in the foreground: wooden boards, screws, and 1 orange-black screwdriver. Add exactly 1 white mug near the character with English text stacked as “Good Plan Lower Bill” and a small smiley face.

Sticky notes and cardboard signs: Include exactly 3 yellow note/sign elements: 1 sticky note on the upper right wall saying 「多一步思考 少很多返工 更聪明 也更省钱」 with a smiley face; 1 sticky note on the wooden shelf saying 「一次做好 省时省钱」 with a bold check mark and small yellow emphasis rays; 1 cardboard box sign in the lower right foreground saying 「更聪明的 AI 更轻松的生活」 with a simple house icon.

Visual style: Soft painterly anime illustration mixed with infographic design, rounded shapes, thick friendly hand-lettering, warm beige/orange/green palette, gentle depth of field, clean composition, lively but not cluttered.

Constraints: Preserve all Chinese text exactly as specified, keep the poster readable, use no logos or watermarks, and do not add extra charts, extra sticky notes, extra characters, or extra checklist items.

Create an ultra-detailed black-and-white pencil line-art portrait of {argument name="character description" default="a young woman with delicate symmetrical features"} on a clean white paper background. Show a front-facing bust portrait cropped from the shoulders upward, with the head slightly turned but eyes looking directly at the viewer. The expression is calm and gentle with a faint closed-mouth smile. Render large almond-shaped eyes with detailed irises and catchlights, softly arched dark eyebrows, a slim straight nose, full softly shaded lips, smooth oval face, and a long graceful neck. Style the hair as {argument name="hairstyle" default="dark medium-length hair parted in the center, loosely swept back into a soft messy updo with wispy strands framing both sides of the face"}. Use meticulous graphite pencil technique: fine layered linework, realistic cross-hatching, subtle tonal gradients, visible individual hair strokes, delicate skin shading, and crisp facial detail while keeping the shoulders and lower bust lightly sketched and fading into the white background. Maintain a realistic yet idealized fashion-illustration look, high contrast in the hair, soft shading on the face, no color, no background objects, no text, no watermark.

Create a highly detailed realistic graphite pencil sketch of a romantic South Asian couple standing close together in a vertical portrait composition. Show exactly 2 people: one man on the left and one woman on the right. The man is tall with wavy dark hair, a full trimmed beard, expressive eyebrows, and a gentle serious expression as he looks down toward the woman; he wears a light button-up shirt with the collar open, sleeves rolled to the forearms, dark trousers, and one hand tucked into his pocket. The woman stands close against him, looking up into his eyes with a soft smile; she has long dark hair parted near the center with loose face-framing strands, delicate features, earrings, bangles, and a ring. She wears an elegant traditional sari with an ornate embroidered border and flowing draped fabric. Her hand rests on the man’s chest, emphasizing intimacy and closeness. Use monochrome graphite shading on textured off-white paper, with meticulous crosshatching, soft smudged gradients, realistic skin tones in pencil, detailed hair strands, fabric folds, embroidery patterns, and subtle background shading. Keep the mood tender, cinematic, and timeless, with no color, no text, no watermark, and no extra people.

Create a highly detailed isometric 3D miniature diorama of a cozy American-style kitchen corner, like a handcrafted dollhouse scene rendered in Blender with soft global illumination. The room is an open cube set with two cream wallpapered walls meeting in a corner, a raised square tiled floor base, and warm medium-brown wood trim along the top and chair-rail height. Use a warm beige studio background and orthographic camera at a 3/4 overhead angle. The kitchen style is nostalgic, cute, and slightly toy-like with rounded edges, polished wood, realistic materials, and clean miniature proportions. Include exactly 12 main furniture and fixture elements: 1 cream retro refrigerator on the left with the word {argument name="refrigerator label" default="NORD"}, small colorful round magnets and brass handles; 1 mint-green gas stove with black burners and a lidded pot; 1 long wooden lower cabinet run on the right with drawers, paneled cupboard doors, brass knobs, and a sink; 1 double window above the sink with beige tied curtains on a silver rod; 2 wall-mounted wooden box shelves, one above the stove and one to the right of the window, containing books and white jars; 1 square dining table in the center covered with a white-and-green checkered tablecloth; 3 wooden chairs around the table; 1 small framed picture on the left wall; and 1 pair of brass wall lamps with round shades and pastel pink globe accents. Add exactly 10 visible tabletop or counter accessories: 1 tray with bread loaves, 1 wooden cutting board, 1 small green bottle, 1 utensil cup with wooden spoons, 1 soap pump bottle, 1 blue teapot or kettle on the dining table, 1 glass dessert cloche with red-topped sweets, 1 small cup and saucer, 1 tiny plate with food, and 1 small rectangular sponge near the sink. Materials should include glossy cream enamel, mint painted metal, varnished wood grain, semi-transparent glass, soft fabric curtains, ceramic tiles, and brushed metal. Lighting should be warm and soft, with gentle shadows and ambient occlusion, emphasizing the miniature scale and fine details. Color palette: {argument name="wood tone" default="warm medium brown"}, cream, mint green, beige, pale pink, muted green, brass, and soft gray tile. No people, no watermark, no modern appliances beyond the retro fridge and stove, no clutter outside the cube room.

Create a clean, high-detail full-body 3D character render of {argument name="character name" default="Solip"}, a friendly heroic humanoid robot standing in a confident front-facing pose against a pure black studio background. The robot has a bulky armored mech body made of angular mustard-yellow metal panels with black mechanical joints, subtle scratches, beveled edges, and realistic wear. Its head is a square yellow helmet-like monitor with rounded corners, side circular ear modules, a glossy black screen face, and a cute green LED pixel expression: exactly 2 upside-down U-shaped eyes and 1 smiling curved mouth. Add the teal marking {argument name="chest label" default="C2"} on the upper right chest plate. The robot wears exactly 1 dramatic black cape flowing behind both shoulders, with a teal inner lining and teal trim visible along the edges. Include detailed segmented arms, articulated black fingers, large shoulder rings, piston-like elbows, thick armored thighs, knee plates, heavy boot-like feet, and exposed dark understructure between plates. Use cinematic low-key lighting with warm golden rim light from the upper left, crisp reflections on metal, deep shadows, a subtle floor reflection, and an ultra-clean premium sci-fi toy/film render look. Center the character vertically in a portrait composition, slightly low camera angle, sharp focus, no background props, no extra characters, no text except the chest label.

Create an ultra-realistic vertical 4:5 fashion editorial studio photograph of {argument name="character name" default="a young woman"} standing centered and sharply in focus, facing the camera with a calm neutral expression. She has {argument name="hair color" default="dark brown"} hair styled in a loose low bun with soft face-framing strands, natural makeup, delicate features, and small earrings. Dress her in a relaxed {argument name="shirt color" default="warm chocolate-brown"} short-sleeve button-up camp-collar shirt with a chest pocket, tucked loosely at the front, paired with high-waisted wide-leg {argument name="pants color" default="cream linen"} trousers and off-white low-top sneakers; add a dark wristwatch on one wrist. Pose her with both hands in her trouser pockets, one leg crossed casually in front of the other, full body visible from head to shoes. Surround her with exactly four motion-blurred duplicate figures of the same woman: one blurred figure at far left walking sideways, one blurred figure just left of center behind her, one blurred figure just right of center behind her, and one blurred figure at far right walking sideways; all duplicates wear the same outfit and are heavily smeared with horizontal motion blur while the central subject remains crisp. Use a seamless warm tan studio backdrop and matching tan floor, soft diffused editorial lighting, shallow depth of field, muted earthy color palette, realistic fabric texture, subtle shadows under the shoes, high-end fashion campaign mood, no text, no logos, no watermark.

[Event Information]
- Event Name: {argument name="event name" default="Margins and Structures"}
- Date & Time: {argument name="date" default="October 12 – November 24, 2026"}
- Venue: {argument name="venue" default="National Museum of Modern Art"}

[Quality, Direction, and Composition Specifications]
- Style: A poster for a contemporary art exhibition or modern design event, clean and minimalist editorial layout.
- Visual Elements: A beautiful live-action composition conveying silence and intelligence, set against geometric abstract art objects or concrete and glass architectural spaces.
- Typography Placement (For GPT-image / Nano Banana Pro): In the empty margins of the screen, the event name '{argument name="event name" default="Margins and Structures"}', the date '{argument name="date" default="October 12 – November 24, 2026"}', and venue information '{argument name="venue" default="National Museum of Modern Art"}' are beautifully laid out in a sophisticated, modern sans-serif font. The typography harmonizes without detracting from the beauty of the overall image.
- Lighting & Color: A clean space based on white, cool natural light with soft gradients of light, neutral tones with accent colors (e.g., navy or dark gray).

[Strict Layout and Output Constraints (Required)]
- Output the completed design itself, filling the entire canvas. Scene descriptions inside the design (walls, spaces, shadows) may follow the text instructions.
- Prohibited items: Photographs of the finished poster inside a frame, stuck to a wall, mockup photos placed on tables or paper, perspective distortion of paper edges, or drop shadows.
- Output the finished flat 2D design itself, filling the entire canvas. Scene elements inside the design (walls, rooms, shadows) described above are allowed. Absolutely NO photo-of-a-poster mockups: no picture frames, no poster-on-wall or poster-on-desk shots, no perspective warp or drop shadow around the artwork's edges.

- Aspect Ratio: --ar 3:4

Extreme low-angle fisheye lens photograph of a {argument name="subject" default="young woman with long dark hair"} making rock sign hand gestures. She is wearing a {argument name="outfit style" default="Y2K street style outfit"}: a cropped denim vest over a white top, baggy olive-green cargo pants, a studded belt, chunky metallic silver sneakers, and silver chain jewelry. She stands in a {argument name="environment" default="futuristic white grid tunnel"} lined with bright vertical overhead lights, creating distorted, exaggerated perspective lines curving inward. Studio lighting, sharp focus, cool white tones, streetwear editorial aesthetic.

Create an image shows a {argument name="subject" default="young woman"} posing outdoors at night in front of a brick structure. She is wearing a stylish, {argument name="outfit" default="long white traditional outfit featuring layered sheer frills and vibrant blue accents"} along the hemline and cuffs. Her ensemble includes embroidered patterns near the neckline and is paired with matching white trousers. She has dark, shoulder-length hair and is smiling gently while resting one hand near her hair and touching a decorative door or gate with the other. The {argument name="background element" default="background consists of a exposed brick pillar illuminated by bright artificial lighting"}. Adjacent to her is an intricate golden-brown decorative gate or wooden screen. To her right, a paved sidewalk extends down a city street under dim nighttime lighting. In the distant background, streetlights and faint figures of pedestrians can be seen along the pathway. The overall atmosphere is warm and brightly lit around the subject, contrasting with the darker ambient urban street scene.