GPT Image 2 prompts

Browse GPT Image 2 prompts for fashion portraits and graphic compositions. Compare how each prompt describes its subject and the way the image is arranged.

探索提示词

9,926 条提示词

Social Media Post - Candid Nighttime Balcony Smartphone Photo — output

Social Media Post - Candid Nighttime Balcony Smartphone Photo

𝗦𝗮𝗻𝗶𝗮GPT Image 2
A genuine-looking nighttime phone photo of a {argument name="subject" default="young East Asian woman"} standing casually on a {argument name="location" default="small apartment balcony or terrace"}, captured spontaneously by a friend on a modern smartphone. She has {argument name="hair style" default="medium-length dark brown hair tied loosely into a relaxed half-up style"}, with wispy strands falling around her cheeks and forehead. She wears a simple fitted white short-sleeve high-neck top and dark casual bottoms, with a black shoulder bag strap visible over one shoulder. She faces the camera naturally with a soft confident smile and a slightly tilted head, looking directly into the lens. Warm light from a nearby wall lamp falls across one side of her face and hair, creating a cozy golden glow, while the rest of the scene fades naturally into deep nighttime shadows. A few green plants sit beside the wall, and a dark window or balcony opening behind her reveals blurry city lights in the distance. Make the photograph feel completely unplanned and personal: handheld smartphone framing, slightly uneven exposure, mild low-light grain, subtle autofocus softness, realistic shadows, natural skin texture, tiny hair flyaways, ordinary background imperfections, gentle warm color cast, no professional lighting, no studio setup, no cinematic grading, no beauty filter, no excessive retouching. Authentic everyday mobile-camera quality, intimate nighttime atmosphere, realistic proportions, vertical portrait photo, highly believable as an actual phone snapshot.
使用此提示词 ↗
Comic / Storyboard - Futuristic Sci-Fi Gravity Reversal Keyframe — output

Comic / Storyboard - Futuristic Sci-Fi Gravity Reversal Keyframe

Sheikh Sharik 2.0GPT Image 2
Create a single cinematic keyframe from an original futuristic sci-fi action film. A young Korean woman in her mid-20s rides a sleek matte-black futuristic electric motorcycle through a massive futuristic city at night. She wears a fitted black tactical riding suit, short black hair, and a dark transparent visor. The motorcycle has a distinctive narrow silhouette, thin cyan glowing wheel rims and one small red rear light. The impossible event has just begun: gravity has reversed across the entire city. Dozens of futuristic cars, buses and motorcycles are falling upward from the streets toward the sky, while rain droplets also travel upward. Some vehicles are already attached to the sides of enormous glass skyscrapers, creating the illusion that the entire city has become vertical. The rider is still moving normally across the wet road, looking upward at the chaos while one futuristic sports car passes dangerously close above her. Camera: extremely low cinematic angle positioned behind and slightly to the side of the motorcycle, 24mm wide lens, strong foreground perspective, rider and motorcycle sharply visible while the city towers dramatically into the background. Lighting: deep midnight atmosphere, cyan and violet neon reflections on wet asphalt, warm headlights from floating vehicles, subtle red emergency lights, volumetric mist and rain illuminated by the city. Composition: rider in the lower-left foreground, enormous vertical city dominating the frame, floating vehicles creating a spiral toward the sky, clear visual hierarchy, no text. Style: photorealistic cinematic sci-fi, original anime-inspired character design, realistic metal, glass and rain, physically detailed vehicles, dramatic scale, blockbuster cinematography, sharp details, natural motion blur. No existing characters, anime references, logos, brands, recognizable copyrighted vehicles, text or watermark. Create a single cinematic keyframe from an original futuristic sci-fi chase film. The same young Korean female rider and the exact same matte-black futuristic motorcycle race through a rain-covered futuristic boulevard at night. Suddenly, the city's entire gravity field rotates sideways. Cars are no longer falling upward—they are sliding horizontally across the sides of skyscrapers as if the buildings have become roads. A huge futuristic traffic stream is moving across a glass tower directly beside the heroine, while streetlights, rain and loose debris are being pulled sideways. The heroine leans aggressively into the turn as her motorcycle begins climbing onto the vertical wall of a skyscraper, its cyan wheel rims glowing against the wet glass. Far below, the original streets appear almost vertical, creating a dizzying sense of scale. Camera: dynamic 28mm lens, low side angle following the motorcycle, camera tilted approximately 45 degrees to make the viewer question which direction is actually down; strong foreground-to-background perspective. Lighting: cold cyan building lights, violet neon signs, warm headlights sweeping across the scene, wet glass reflections, atmospheric blue haze and subtle red energy from the motorcycle's rear light. Composition: heroine and motorcycle dominate the foreground, sideways traffic creates a powerful diagonal line through the frame, skyscrapers disappearing into mist behind her. Style: high-budget cinematic sci-fi, photorealistic environment, original anime-inspired heroine, realistic rain and reflections, detailed futuristic vehicles, dramatic perspective, intense depth of field, subtle film grain, dynamic action photography. No existing characters, anime franchises, logos, brands, recognizable copyrighted vehicles, text or watermark.
使用此提示词 ↗
Social Media Post - Dunhuang Style Classical Beauty Makeup — output

Social Media Post - Dunhuang Style Classical Beauty Makeup

李岳GPT Image 2
9:16 vertical orientation, bright beauty portrait of an ancient-style noble lady, half-body close-up of an oriental classical woman, morning light courtyard corridor scene, the person is standing by a wooden corridor, body slightly turned naturally, head tilted gently towards the camera, eyes looking at the camera gently and brightly, a slight smile on the lips, overall temperament is warm, bright, soft, and approachable, with a clear and noble aura of a well-bred lady.

The subject is a young oriental woman with a visual age of approximately 20–26 years old, clearly an adult, with a gentle and noble face, a soft oval face shape, a naturally full forehead, a plump and soft mid-face, a delicate and smooth jawline, elegant brows and eyes, clear and spirited eyes with a naturally slender shape, a smooth and elegant nose, naturally plump lips, harmonious and pleasing features, and an overall gentle, bright, and affluent appearance.

The makeup is 'Golden Marigold Morning Dew Warm Light Makeup'. The base makeup is clear and delicate, the skin tone is clean and transparent, retaining a natural soft skin texture. The eye makeup uses warm golden apricot, light peach apricot, and a small amount of soft brown gradient blending, with fine warm golden pearls in the center of the eyes and naturally elongated eye corners. The blush uses a soft apricot-orange color, lightly spread over the center of the face and apple muscles for a fresh look. The bridge and tip of the nose have a delicate and bright morning dew luster, with restrained and non-greasy highlights. The lip makeup is a milk tea apricot-pink moist lip, with naturally clear lip beads, overall presenting a warm, bright, and moist post-makeup temperament.

The hairstyle is long black hair loosely tied, naturally voluminous on top, with a soft and full bun at the back and smooth hair falling behind. Wears a marigold hairpin, a small white jade hairpin, and a small amount of pearl bead tassels in the hair, with long pearl earrings; the overall hair accessories are exquisite, elegant, and not overly exaggerated.

The clothing is a pine-flower yellow waist-high Ruqun, paired with a bean-green embroidered upper garment and an ivory white shawl. The upper garment has small light-colored floral embroidery and fine gold thread patterns, the shawl is thin, soft, and drapes naturally, and the skirt color is bright and fresh. The clothing colors are mainly bean green, pine-flower yellow, and ivory white, bright and warm, but without making the subject's skin tone look yellow; the subject's facial skin tone remains clean and natural.

The pose is a half-body close-up, the person is standing by the corridor, one hand naturally raised near the collarbone and lapel, the other hand naturally hanging in front of the waist/abdomen, the posture is relaxed and stretched, with a dignified and beautiful demeanor.

The scene is a morning light courtyard, wooden corridor, marigold bonsai, and warm white sunlight. A cluster of marigolds is visible in the foreground and side, while the background consists of wooden pillars, the corridor, warm white lanterns, and a blurred courtyard view. Warm white morning sunlight shines in from the side and back, forming soft rim lighting and natural facial fill lighting; the overall scene is bright and transparent with soft flower shadows and a shallow depth of field in the background to avoid distraction.

85mm portrait lens, realistic photographic texture, high-end ancient-style noble lady portrait, clear details of the subject's eyes, eyelashes, lip makeup, embroidery, and hair accessories, the image is warm and clear, with a morning atmosphere and a sense of life.
使用此提示词 ↗
Social Media Post - Japanese Cafe Memory Journal Page — output

Social Media Post - Japanese Cafe Memory Journal Page

TaarukGPT Image 2
Create a premium editorial “memory journal” page combining a real lifestyle photograph with a hand-drawn illustrated interpretation of the same moment. Use a vertical 4:5 composition divided diagonally/vertically into two complementary sections: the left side is a warm, natural, slightly film-grainy photograph of a {argument name="scene" default="Japanese café scene"}, showing beautifully plated food or dessert and coffee on a wooden table, with realistic ambient café details, soft window light, shallow depth of field, and subtle nostalgic tones; the right side is a minimalist {argument name="art style" default="hand-painted watercolor/colored-pencil illustration"} recreating the same food and drink with delicate imperfect ink outlines, muted earthy colors, visible paper texture, and an artistic handmade feel. Keep the right side mostly warm ivory textured paper with generous negative space. Beneath the illustration, add small typewriter-style archival text containing the {argument name="location and date" default="Tokyo, Japan / No. 0018 / coffee / toast / quiet time / 2026"}. The design should feel like a curated Japanese travel diary, café memory archive, contemporary scrapbook, and vintage lifestyle magazine, with sophisticated editorial composition, warm cream paper, muted teal, brown, beige and dusty colors, subtle grain, imperfect printing, understated typography, authentic tactile paper texture, elegant minimalism, photorealistic photography seamlessly paired with handmade illustration, high detail, cohesive visual storytelling, no logos, no watermark.
使用此提示词 ↗
Social Media Post - Oriental Zen Minimalist Poster — output
Profile / Avatar - Cozy Dinner with Rabbit Plush — output

Profile / Avatar - Cozy Dinner with Rabbit Plush

Prompt アトリエ|AI画像プロンプトGPT Image 2
Subject:
{argument name="main theme" default="Supper with a rabbit and lights"}

Main Subject:
In the center of the screen, at a night restaurant table, a woman in a white dress holds a round white rabbit plushie next to her face. Dishes on a white plate in the foreground, a wine glass, and a candle create a dinner atmosphere.

Person/Expression:
The woman tilts her face slightly to the right of the screen and looks straight at the camera with a calm, expressionless look. A rounded oval face with a small chin, large horizontally long eyes, thin loose eyebrows, a small rounded nose tip, thin upper lip and thick reddish lower lip. Bright skin with light pink around the eyes and cheeks. A bright {argument name="hair color" default="chestnut"} shoulder-length bob is parted near the center, with thin bangs and hair ends moving inward and outward.

Clothing/Pose:
An ivory thin-strap dress with fine gathers at the low neckline and soft transitions and ruffles below the waist. Both elbows are placed on the table, supporting a round rabbit plushie on the left side of the face with both hands. Wearing a thin necklace and bracelet.

Background/Light:
A white plate and silver cutlery in the foreground, a wine glass and small flowers on the left, and a mirrored shop interior, bottles, and hanging lights in the background. The candle on the left and a {argument name="light color" default="warm light source"} above softly illuminate the face and white cloth.

Composition/Camera:
3:4 vertical orientation, capturing the seated person from the waist up at a horizontal camera angle. The rabbit is to the left of the face, the food plate is in the lower left foreground, focusing on the person and plushie while making the background lighting a bokeh effect.

Texture/Style:
A warm amber-toned live-action photo. Finely depicts the soft plushie, satin-like clothes, and the luster of glass and food.

Negative:
Do not change the white rabbit plushie to another animal
使用此提示词 ↗
Profile / Avatar - Out of Focus Balcony Portrait — output
Profile / Avatar - Black and White Studio Portrait with Pet — output

Profile / Avatar - Black and White Studio Portrait with Pet

HarborisGPT Image 2
Create an ultra-realistic black-and-white 9:16 studio portrait using the person from the attached reference image. Preserve their exact facial identity, facial features, beard, mustache, proportions, expression, and natural skin texture. The person is sitting on a minimalist studio floor, holding a {argument name="pet" default="large domestic cat"}. One leg is bent toward the body and the other extends diagonally along the floor. One arm supports the cat while the other rests on the raised knee, with the head slightly tilted toward the arm. The person and cat both look directly into the camera. Keep the pose natural, relaxed, intimate, and slightly editorial. Use a {argument name="top clothing" default="light, loose cotton T-shirt"} and {argument name="bottom clothing" default="dark textured denim jeans"}. Preserve visible tattoos, realistic fabric folds, seams, and natural wrinkles. Use soft frontal-side studio lighting with smooth shadows and natural highlights. Keep the background clean, light, plain, and cyclorama-like. Ultra realistic RAW photography, sharp focus, realistic skin microtexture, detailed fur, natural anatomy, realistic fabric texture, rich grayscale tones, natural shadows, documentary-style fashion editorial, 8K detail. No CGI, plastic skin, skin smoothing, beauty filters, excessive retouching, distorted anatomy, extra fingers or limbs, added furniture, accessories, or background objects.
使用此提示词 ↗
Product Marketing - Premium Pizza Advertising Poster — output

Product Marketing - Premium Pizza Advertising Poster

ᴍᴜʀᴘʜʏGPT Image 2
CREATIVE DIRECTION
Create a premium, agency-level {argument name="brand" default="DOMINO'S"} advertising poster inspired by the visual language of bold QSR / FMCG social campaigns: strong graphic composition, one instantly readable visual metaphor, controlled product photography, saturated brand colour as the entire world, clean negative space, tactile food realism, short stacked typography and carousel-system consistency.
Do not copy any specific reference composition.
Extract the common principles and build an original execution.
The poster must feel like a real global pizza campaign art-directed for Instagram, photographed by a commercial food photographer, not a generic AI food poster.

The visual must communicate the idea before the viewer reads the copy.

CAMPAIGN DNA
Brand: {argument name="brand" default="DOMINO'S"}
Hero product: {argument name="product" default="signature pepperoni / cheese pizza"} in authentic Domino's packaging language
Campaign territory: craving + delivery win
Concept: THE BOX IS THE WIN
Personality: hungry, playful, confident, fast, slightly cheeky
Colour system
- Dominant {argument name="color" default="red (#E31837)"}
- Domino's blue (#006491) used only as logo, box accent, small graphic punctuation
- White
- Soft cream / mozzarella highlight
- Restrained dark red shadow
The red must own the frame immediately. It should not look like generic ketchup advertising.

CREATIVE EXECUTION
Graphic visual metaphor + premium pizza hero + QSR social poster
Use:
- oversized short typography
- product scale
- repetition of brand red
- negative space
- one gag / one object relationship
- controlled steam and cheese gloss
- strong alignment
Avoid environmental documentary. This is not a street-lifestyle film still unless the specific frame requires hands/tray.

BACKGROUND
A completely controlled advertising field.
Rich saturated Domino's red with subtle tonal depth.
Allowed:
- extremely subtle blob / pepperoni-dot pattern at very low contrast
- restrained radial falloff
- soft dimensional shadowing
Forbidden:
- random restaurant interior as default
- dirty kitchen
- city street
- collage clutter
- extra brands

HERO PRODUCT
Photoreal Domino's pizza as the most important physical object.
Preserve recognizable Domino's box / logo geometry. Do not invent a new logo. Do not redesign the wordmark.
Show:
- molten mozzarella
- pepperoni oil
- realistic crust blistering
- visible steam, restrained
- authentic corrugated pizza box when the box is in frame
- believable grease sheen, not plastic CGI
Product occupies roughly 50–65% of the frame width unless the idea needs scale contrast.

TYPOGRAPHIC SYSTEM
Headline: short, 3–6 words, bold contemporary grotesk / heavy sans.
Primary line in white.
One hook word may be cream-yellow.
Secondary line smaller, quieter.
Optional bottom lockup: ORDER NOW as a small yellow pill.
Optional footer: Hot. Fast. Yours.
Typography is hierarchy, not decoration.
Do not flood the frame with copy.
使用此提示词 ↗
Profile / Avatar - Urban Alleyway Golden Hour Portrait — output
Profile / Avatar - East Asian Beauty Editorial Portrait — output
Comic / Storyboard - Japanese Sketchbook Lifestyle Illustration — output

Comic / Storyboard - Japanese Sketchbook Lifestyle Illustration

SnowGPT Image 2
Create a fresh, heartwarming hand-drawn colored-pencil illustration of a {argument name="subject" default="stylish young couple"} enjoying a quiet walk on a peaceful day, inspired by contemporary {argument name="style" default="Japanese and Korean sketchbook lifestyle art"}. The couple is shown full-body in a natural candid moment: the boy gently holds the girl’s hand while she looks up at him with a soft, happy expression, their steps slightly out of sync as if captured mid-walk.

The girl wears a cozy oversized cream cardigan over a simple white top, wide-leg muted olive trousers, and classic canvas shoes. Her long, softly curled dark hair flows naturally in the breeze, with a small shoulder bag adding a casual touch. The boy wears a loose charcoal bomber jacket over a plain beige T-shirt, relaxed-fit blue jeans, and simple sneakers, with slightly tousled hair and an effortlessly stylish appearance.

Use expressive graphite and colored-pencil linework, visible sketch strokes, delicate cross-hatching, and layered hand-colored textures. Add soft watercolor washes, gentle cheek blush, subtle shadows, minimal yet emotionally expressive facial features, and natural fabric folds. Keep the proportions slightly cute and stylized while maintaining believable anatomy and relaxed body language.

Place the couple against a spacious {argument name="background" default="warm ivory sketchbook-paper background"} with faint paper grain, tiny pencil imperfections, and subtle unfinished marks around the edges, creating the feeling of an authentic artist’s lifestyle journal. Use a harmonious palette of warm beige, dusty green, faded blue, soft brown, and muted charcoal. Romantic, cozy, elegant, intimate, editorial-quality hand-drawn illustration, beautifully detailed, soft artistic texture, vertical portrait composition, 4:5 aspect ratio.
使用此提示词 ↗
Social Media Post - Morning Light Shadow Portrait — output

Social Media Post - Morning Light Shadow Portrait

Prompt アトリエ|AI画像プロンプトGPT Image 2
Subject: {argument name="subject" default="Sunlight shadows and white camisole"}

Subject: A close-up portrait in the center of the screen, against a gray wall, where a woman in a {argument name="outfit" default="white camisole"} rests her right hand on her cheek. Diagonal sunlight illuminates the face and chest, creating bands of light and dark on the wall.

Person/Expression: The woman tilts her face slightly to the left of the screen, looking quietly at the camera and parting her lips slightly. Round oval cheeks and a small chin, elongated bright eyes, thin loose eyebrows, a thin bridge and small tip of the nose, and thick coral lips with round contours. Black-brown chin-length bob is parted near the center, with thin bundled bangs and ends that flip outwards. Thin brown lines around the eyes, pale pink on the cheeks, natural glossy skin.

Clothing/Pose: A {argument name="top" default="white thin-strap ribbed camisole top"} with thin lace edging at the chest and a ribbon tie in the center. The subject's right elbow is pushed to the left of the screen, and the fingers of the right hand are lightly placed on the chin and cheek. The left shoulder is naturally lowered, leaning the upper body against the wall.

Background/Light: The background is a rough gray wall, with a bright vertical light from the left to the center of the screen and a soft shadow on the right. Hard direct sunlight from the upper left of the screen illuminates the cheeks, nose, and collarbones.

Composition/Camera: 2:3 vertical orientation, chest-up close-up from a horizontal camera view. The face is in the center of the upper half, the right arm is cropped at the left edge of the screen, focusing on the eyes and lips of the face and slightly blurring the wall.

Texture/Style: A realistic photo capturing the texture of the skin, thin ribs, lace, and wall roughness in high definition. Contrast between warm skin tones and neutral gray.

Negative: Significant change in facial features; do not omit the right hand placed on the cheek
使用此提示词 ↗
Social Media Post - Dark Surrealist Flooded Opera House — output

Social Media Post - Dark Surrealist Flooded Opera House

PSSGPT Image 2
Use case: stylized-concept
Asset type: vertical social-media artwork for the “Your Dark Side” theme

Create a haunting original scene in a {argument name="location" default="gigantic abandoned opera house"} flooded with shallow black water. On the empty stage stands a {argument name="subject" default="lone person dressed in bone white"}, facing the audience. The seats are vacant, but hundreds of tall shadow versions of that same person rise silently from the water between the rows. Every shadow has its hands covering its own mouth except one enormous silhouette in the royal box, whose mouth is a perfectly black doorway opening into a deeper impossible space. The real person has no visible facial detail and remains composed.

Vertical 9:16 composition viewed from the rear of the auditorium, stage centered far away, layered depth through flooded seating, towering royal box near the upper third. Cold silver spotlight on the small white performer, almost total darkness elsewhere, very restrained wine-red reflections beneath the silent shadow audience. Decayed velvet, wet gilded surfaces reduced to black, mist, fine dust in the light beam, premium cinematic dark surrealism, photorealistic textures, elegant and psychologically unsettling.

Color palette: {argument name="colors" default="obsidian, charcoal, tarnished silver, bone white, minimal wine red"}.

Constraints: entirely original; one real human figure only, with shadow forms functioning as metaphor; no text, logos, signatures, borders, or watermark.

Avoid: facial mutilation, black material covering skin, glowing eyes, gore, screaming monsters, theatrical comedy/tragedy masks, busy colorful décor, imitation of any named artist.
使用此提示词 ↗
Profile / Avatar - Premium Yoruba Agbada Studio Portrait — output

Profile / Avatar - Premium Yoruba Agbada Studio Portrait

Abkr SadiqGPT Image 2
Create an ultra-realistic premium studio portrait of {argument name="subject" default="a young adult Yoruba man"} wearing an elegant deep emerald green traditional Yoruba Agbada ensemble. He is centered, facing forward with a calm serious expression, photographed from mid-thigh upward. The outfit includes exactly 6 prominent visible elements: a structured emerald green Yoruba fila cap with subtle diagonal fabric texture, oversized flowing velvet Agbada outer robe with broad sleeves and glossy highlights, matching inner tunic with intricate gold geometric embroidery down the chest, two layered long black beaded necklaces, a black beaded bracelet on one wrist, and a gold wristwatch on the other wrist. His hands are clasped neatly in front of him, resting on the gold handle of a black walking cane. He wears thin gold-rimmed eyeglasses and has a clean, polished appearance. Use a warm mottled golden-brown studio backdrop with painterly texture, soft vignette, and professional portrait lighting: large soft key light from the front, gentle shadows, crisp facial detail, rich velvet texture, realistic skin tones, shallow depth of field, high-end editorial fashion photography, vertical 2:3 composition, no text, no watermark. If a reference photo is provided, preserve the exact facial identity from the reference while applying this outfit, pose, and studio setting.
使用此提示词 ↗
Social Media Post - Man Summoning Fiery Phoenix — output
Profile / Avatar - Cinematic Black Leather Executive Portrait — output

Profile / Avatar - Cinematic Black Leather Executive Portrait

Abkr SadiqGPT Image 2
Create an ultra-realistic cinematic studio portrait of {argument name="subject" default="an adult Black man in his late 20s"} seated confidently in a premium black leather armchair against a deep matte-black studio background. The subject faces the camera directly with a calm, composed, professional expression, short neatly trimmed black hair, clean-shaven face, and natural skin texture. Dress him in a crisp white long-sleeve dress shirt, fitted black waistcoat, slim black necktie, black dress trousers, and a silver metal wristwatch with a black round dial on his right wrist. Pose: relaxed but authoritative, torso angled slightly toward camera, right forearm resting on the chair arm with the hand near his lap, left arm relaxed with the hand resting on the seat edge, legs casually apart. Use a medium three-quarter seated crop from upper thighs to head, centered composition, portrait orientation. Lighting should be high-end studio photography: soft key light from front-left, gentle fill on the face, subtle rim separation, controlled highlights on the leather chair, and smooth falloff into the black background. Make the image look like a premium executive portrait shot with a professional full-frame camera, sharp facial detail, realistic fabric folds, glossy leather texture, shallow depth of field, natural color grading, no visible logos, no text, no watermark.
使用此提示词 ↗
YouTube Thumbnail - Realistic Creator Interview Photo — output
Comic / Storyboard - Vintage Karate Kid Movie Poster — output

Comic / Storyboard - Vintage Karate Kid Movie Poster

LANDCÄSTER.EXEGPT Image 2
Goal: Create a vintage 1980s martial arts movie poster remake for {argument name="movie title" default="THE KARATE KID"}, dramatic and nostalgic, like a folded theatrical one-sheet.

Canvas: Vertical poster, 2:3 aspect ratio, aged cream paper border, worn corners, visible fold lines crossing horizontally and vertically, subtle stains, grain, scratches, and faded print texture.

Visual style: Painted 1980s Hollywood movie-poster realism with warm orange-red sunset lighting, deep blacks, high contrast, airbrushed faces, cinematic composition, slightly imperfect vintage typography and distressed ink.

Top composition: A fiery sunset over the ocean fills the upper half. Two large heroic portrait heads dominate the sky: in front is a serious teenage martial arts student with dark tousled hair, tan skin, intense eyes, wearing a white gi and a white rising-sun headband; behind him to the upper right is an older Japanese mentor with a mustache and short gray beard, solemn expression, wearing a matching white rising-sun headband and white robe with a dotted scarf detail. Add the tagline in small white serif capitals at upper left: {argument name="tagline" default="A WARRIOR FIGHTS FOR VICTORY. A STUDENT FIGHTS FOR HONOR."}

Silhouette action vignettes: Include exactly 3 dark martial-arts silhouettes on the left side against the sunset: 1) a flying kick silhouette near the upper left sky, 2) two fighters sparring at sunset near the middle left horizon, 3) a kneeling student practicing a strike against a wooden training dummy near the lower left.

Title area: Place the huge centered title {argument name="movie title" default="THE KARATE KID"} across the middle-lower poster in large cream-colored vintage serif capitals, with “THE” above “KARATE KID,” slightly distressed and shadowed.

Bottom tournament scene: Show an indoor karate tournament arena below the title. Exactly 2 teenage fighters face each other on a red-and-white mat: 1) left fighter in a white gi with black belt and circular chest patch, standing in a guarded stance, 2) right fighter in a black gi with black belt and circular patch, standing in an aggressive fighting stance. Exactly 1 referee stands centered between and behind them, wearing a red shirt and dark pants. Behind them is a crowd in dark bleachers and a tournament bracket board labeled {argument name="tournament board text" default="ALL VALLEY KARATE CHAMPIONSHIP"} with small illegible bracket names and a clear “FINALS” section.

Credits and logos: Add a dense block of tiny white movie credits at the very bottom with names, a small studio logo at bottom left, and a small PG-style rating box at bottom right. Use {argument name="studio credit" default="NEW WORLD PICTURES Presents"} in the credit line.

Constraints: Keep the poster text readable where specified, preserve the 1980s theatrical poster mood, use no modern elements, no photorealistic contemporary camera look, no extra characters beyond the counted figures and silhouettes, and make the final image look like an authentic aged printed movie poster.
使用此提示词 ↗
Social Media Post - Candid Night Horseback Campfire Photo — output

Social Media Post - Candid Night Horseback Campfire Photo

Artificial StudioGPT Image 2
Create a raw candid vertical iPhone night photograph of {argument name="subject" default="a 35-year-old European man with a sun-kissed glow"} sitting on a {argument name="horse color" default="white-gray horse"} beside a small campfire gathering in a dark forest. The man is centered slightly right, photographed from close range at a low-to-mid angle, riding bareback or in a dark saddle, holding black reins with both hands. He is caught mid-laugh with teeth visible, looking off-camera to the left toward friends, relaxed and charismatic. He has tousled brown hair, light stubble, tanned skin, and wears an open off-white linen button-up shirt over a cream knit T-shirt, blue jeans, and a dark wristwatch. The horse’s head fills the right foreground, cropped at the muzzle and neck, with visible ears, mane, bridle, reins, and soft gray speckling on its coat. In the left background, show exactly three friends seated low around a campfire: one person in a pale shirt at far left smiling, one dark-haired person behind center holding a drink, and one blond man in a dark shirt laughing near the fire. Include a small grill over glowing coals with flames, smoke drifting upward, plates or camp food nearby, and one warm lantern glowing at the bottom left foreground. Use {argument name="lighting" default="warm firelight and lantern light against deep black forest shadows"}, subtle motion blur, high ISO grain, imperfect phone flash/low-light exposure, realistic skin texture, candid composition, shallow depth of field, and no posed studio look. Aspect ratio vertical 2:3, hyper-realistic, natural colors, no text, no watermark.
使用此提示词 ↗
Infographic / Edu Visual - Split Fantasy Portrait Comparison — output

Infographic / Edu Visual - Split Fantasy Portrait Comparison

John QiaoGPT Image 2
Create a side-by-side comparison image showing two versions of the same dreamy fantasy portrait. Canvas is a horizontal 16:9 split-screen composition with a perfectly vertical divide down the center, no gap, left panel and right panel each occupying exactly half the image. In both panels, depict the same ethereal young woman in a luminous fairytale garden, shown as a close-up bust portrait with pale porcelain skin, soft gray-blue eyes, delicate lips, and loosely pinned wavy brown hair. She wears an ornate pastel floral crown with pink roses, tiny crystal flowers, pearls, translucent butterfly ornaments, and soft feathers, plus dangling crystal earrings and a sheer embroidered gown with iridescent floral appliqué. Her hand is raised gently near her chin, giving a calm, romantic, slightly wistful expression while looking toward the viewer. The scene is filled with pastel blossoms, sparkling bokeh, floating dust motes, translucent butterflies, crystal petals, and soft backlit haze. Use an ultra-detailed high-fashion fantasy photography style, shallow depth of field, pearly highlights, glittering refractions, delicate skin texture, and pastel lavender, blush pink, silver, and pale blue tones. Make the left panel slightly more textured, crisp, and detailed in skin and fabric microtexture; make the right panel slightly smoother and more airbrushed, with softer pastel lighting and gentler facial texture. Add exactly 2 label boxes: one white rounded rectangle at the top left of the left panel reading {argument name="left label" default="OpenAI 官方"}, and one white rounded rectangle at the top left of the right panel reading {argument name="right label" default="Azure West US 3"}. Use clean black sans-serif text inside the labels. Keep both portraits similar enough to clearly compare rendering differences, but not identical; avoid watermarks, logos, extra captions, borders, or additional text.
使用此提示词 ↗
Comic / Storyboard - Xiaohongshu Comic Post Screenshot — output

Comic / Storyboard - Xiaohongshu Comic Post Screenshot

壹新GPT Image 2
Goal: Create a realistic smartphone screenshot of a Xiaohongshu-style post featuring a simple two-panel hand-drawn comic about a tired young man trying outdoor activities, with engagement metrics circled in red.

Canvas: Vertical mobile screenshot, 9:16 aspect ratio, white app interface, iPhone-like status bar at the top showing 08:34, signal bars, “4G”, and a battery icon.

Top app header: Show a back arrow on the left, a small circular avatar, the username {argument name="account name" default="水枪装尿呲谁谁叫"}, a rounded pink-outline follow button labeled “关注”, and a share arrow icon on the right.

Main post image: A large white comic card with a thick black rectangular border, divided into exactly 2 stacked panels by one horizontal black divider. Add a small gray rounded page indicator in the top-right corner of the comic card reading “2/11”. Use loose black ink line art with muted watercolor fills, casual sketch style, lots of white space.

Comic panel 1: At the top left, handwritten red-and-black Chinese text reads {argument name="first panel text" default="逛洗浴、露营,"}. In the center, draw a slim tired young man with short messy black hair, pale face, droopy eyes, dark green jacket, gray shirt, and dark pants, hands in pockets. Around him place exactly 3 simple activity icons: a steaming bath tub on the left, a hanging towel at lower left, and a camping tent on the right.

Comic panel 2: At the top left, handwritten red-and-black Chinese text reads {argument name="second panel text" default="钓鱼、爬山……"}. Draw the same tired young man centered slightly right, holding a fishing rod in one hand with the line and hook hanging down, the other hand in his pocket. Around him place exactly 3 simple outdoor icons: mountains with a tiny cloud at upper left, the fishing rod and hook extending from his hand toward the left, and a backpack on the right.

Below the comic: Add a carousel dot indicator with exactly 4 dots, the second dot red and the other 3 gray. Then show the bold caption {argument name="caption text" default="这日子真是越过越有盼头"}. Below it, show exactly 5 hashtag phrases in blue-gray Chinese: “#漫画”, “#当漫画照进生活”, “#原创漫画”, “#突然的绷不住”, “#每天一个治愈小漫画”. Add a rounded search suggestion bar with a magnifying glass icon and Chinese text beginning with “猜你想搜|日子过得越来越有盼头了”.

Bottom interaction area: Add a pale comment input pill on the left with a pencil icon and placeholder “说点什么...”. On the right, show exactly 3 interaction icons with counts: a heart icon with {argument name="like count" default="1703"}, a star icon with “408”, and a comment bubble icon with “1003”. Draw a thick freehand red circle around these three engagement metrics, as if marked with a digital pen.

Visual style and constraints: Keep the screenshot clean and realistic, with crisp UI elements and a slightly imperfect hand-drawn comic. Use black, white, muted green, gray, pale pink, and red accents. Preserve all visible Chinese UI text exactly where specified. Do not add extra panels, extra icons, watermarks, or unrelated decorations.
使用此提示词 ↗
Profile / Avatar - Cute Tabby Cat LINE Sticker — output
Profile / Avatar - Transparent AI VTuber Mascot — output
按模型、风格或主题浏览

寻找下一个方向

ASTORIE CANVAS

让灵感,继续生长。

在同一个创作空间,连接提示词、参考素材和生成结果。

打开创作画布 ↗