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.

Explore prompts

10,036 prompts

Game Asset - Cat Ear Girl Digital Illustration — output

Game Asset - Cat Ear Girl Digital Illustration

Kitten KikiGPT Image 2
I want to see {argument name="subject" default="beautiful cat ears"} bursting toward summer. Can you generate a {argument name="style" default="crisp digital illustration similar to Niji-journey"}?
Product Marketing - Custom Character-Wrapped Streetcar Illustration — output

Product Marketing - Custom Character-Wrapped Streetcar Illustration

アシタ🩵GPT Image 2
Make an illustration.
Create an original Japanese {argument name="character type" default="character"}-wrapped {argument name="vehicle type" default="streetcar"} based entirely on the uploaded illustration. Design a fully fictional tram system and railway company naturally born from the artwork’s universe, never resembling any real railway operator or existing vehicle. The design must adapt to the illustration itself: cute rounded styling for soft fantasy or shrine themes, elegant luxury styling for regal worlds, futuristic styling for cyberpunk settings, mystical styling for magical worlds, retro-modern styling for nostalgic atmospheres, or heroic styling for adventure-themed characters.

The tram body shape, front face, windows, headlights, roof equipment, pantograph, interior seating, floor patterns, destination displays, lighting, materials, and overall silhouette must visually reflect the uploaded illustration’s colors, motifs, fashion, architecture, symbols, magic, technology, and emotional tone. All wrapping artwork, logos, route emblems, railway insignia, typography, station signage, and decorative graphics must be fully original fictional designs inspired only by the uploaded illustration.

The tram should travel through a {argument name="environment" default="realistic city, historic district, seaside boulevard, futuristic downtown, shrine town, or fantasy capital"} naturally derived from the artwork’s world. If a character exists in the illustration, place them naturally beside the tram, boarding it, waving from a platform, or riding inside while preserving their identity.

Cinematic transportation photography, dramatic low-angle composition, ultra detailed, anime-inspired masterpiece, premium railway advertisement quality, no watermark.
Product Marketing - Intricate Kirie Paper-Cut Outfit — output

Product Marketing - Intricate Kirie Paper-Cut Outfit

えりしえら・さくら|YozakuraGPT Image 2
The outfit is rendered as intricate kirie paper-cut art, with delicate layered washi paper relief, visible paper thickness, carved paper edges, lace-like cutout patterns, stacked silhouettes, handmade paper craft texture, subtle fiber details, soft matte paper surface, elegant shadow gaps between each paper layer, dimensional paper folds, refined {argument name="flavor" default="strawberry choco-mint"} washi paper costume design.
Comic / Storyboard - Desert Night Airplane Cafe Story — output

Comic / Storyboard - Desert Night Airplane Cafe Story

もしもし@AiartGPT Image 2
The Airplane Cafe visited by a traveling boy.

At the counter in the desert night, {argument name="traveler" default="a traveling boy wearing a cloak"} sat down tonight.

He ordered a warm coffee, and beside him as he held his blue cup, the {argument name="cat" default="Cat Manager"} was already working hard to get his attention.

Holding out a light like the first star of the evening, and stretching as if to say "look over here," it seemed the boy's traveler's expression softened just a little.

Perhaps it's a place that best suits those who have come from afar—starting with a single cup and a deep breath.
Profile / Avatar - Soft Cat Ears Anime Art — output

Profile / Avatar - Soft Cat Ears Anime Art

Kitten KikiGPT Image 2
I want to see beautiful {argument name="subject" default="cat ears"} bursting toward summer. Can you generate a fluffy digital illustration in the style of {argument name="style" default="NijiJourney"}?
Comic / Storyboard - Multi-Era Cinematic FPV Storyboard — output

Comic / Storyboard - Multi-Era Cinematic FPV Storyboard

akiraGPT Image 2
Please create a storyboard for 8 shots. Include the image storyboard so the flow of each scene from start to end is clear. The scene prompts are as follows:

S1 {argument name="scene 1 theme" default="Dinosaurs and Great Canyon"} High-speed FPV drone shot. Bursting through the golden mist of an ancient dawn, a first-person perspective flight camera flies low over a vast Jurassic canyon. It brushes past a herd of giant long-necked sauropods grazing, passes over a river where dinosaurs are drinking, and plunges straight into a dense wall of green ferns and jungle. Photorealistic, ultra-realistic, cinematic, dynamic morning light, strong motion blur, high definition, one-cut, no cuts, no drones or aircraft visible.

S2 Dinosaurs, Jungle to Volcano High-speed FPV drone shot. A first-person flight camera dives through dense green ferns into a primitive jungle, passing at high speed beside a roaring T-Rex. Raptors scatter, and pterosaurs dive across the screen. The camera hurtles toward a massive erupting volcano glowing red with lava, then plunges into the thick volcanic smoke where embers dance. Photorealistic, ultra-realistic, cinematic, strong motion blur, high definition, one-cut, no cuts, no drones or aircraft visible.

S3 {argument name="scene 3 theme" default="Edo Town (Aerial)"} High-speed FPV drone shot. A first-person flight camera emerges from morning mist over an Edo-period Japanese castle town. It flies low over wooden buildings with tiled roofs toward a tall white castle tower. On the streets below, people in kimonos and processions of horses are visible before diving down toward a bustling market street. Photorealistic, ultra-realistic, cinematic, golden morning light, strong motion blur, high definition, one-cut, no cuts, no drones or aircraft visible.

S4 Edo, Market Street to Under Bridge High-speed FPV drone shot. A first-person flight camera hurtles low through a crowded Edo-period market street lined with wooden stalls, banners, and lanterns. It passes samurai, merchants, and horses at high speed, heads toward a wooden arch bridge over a river, and plunges into the dark shadows under the bridge. Photorealistic, ultra-realistic, cinematic, strong motion blur, high definition, one-cut, no cuts, no drones or aircraft visible.

S5 {argument name="scene 5 theme" default="Showa Shopping Street"} High-speed FPV drone shot. A first-person flight camera bursts from a dark passage into a bustling 1960s Showa-era Japanese shopping street. It races low past glowing retro neon signs, clattering old streetcars, shopkeepers, and playing children. Laundry hangs overhead before plunging into the thick white smoke of a steam locomotive stopped at a station. Photorealistic, ultra-realistic, cinematic, nostalgic warm light, strong motion blur, high definition, one-cut, no cuts, no drones or aircraft visible.

S6 Showa, Station to Tunnel High-speed FPV drone shot. A first-person flight camera hurtles along a crowded Showa-era station platform, passing through rising white steam. It races past passengers in old-fashioned clothing and flies alongside an accelerating steam locomotive before plunging into a dark tunnel ahead. Photorealistic, ultra-realistic, cinematic, strong motion blur, high definition, one-cut, no cuts, no drones or aircraft visible.

S7 Reiwa, Crowded Train to Platform High-speed FPV drone shot. A first-person flight camera bursts from a dark subway tunnel into the interior of a modern Tokyo train crowded with rush-hour commuters. It hurtles through the crowded aisle past passengers looking at smartphones, exits through open doors onto a bustling platform, and then races up an escalator toward bright daylight. Photorealistic, ultra-realistic, cinematic, strong motion blur, high definition, one-cut, no cuts, no drones or aircraft visible.

S8 Reiwa, Shibuya to Sky (Closing) High-speed FPV drone shot. A first-person flight camera bursts from a station exit into today's Shibuya Crossing in Tokyo. It races low over massive crowds, neon screens, and traffic before rising straight up between towering glass skyscrapers at close range. As glass walls fill the screen, it finally bursts out into the bright, open sky. Photorealistic, ultra-realistic, cinematic, vibrant neon, strong motion blur, high definition, one-cut, no cuts, no drones or aircraft visible.
Game Asset - Tiny Boy Character Sheet — output

Game Asset - Tiny Boy Character Sheet

なおGPT Image 2
Please create a simple character sheet for a boy about the same size as a mug. Include a three-view drawing, a close-up of the face, and an image of a skateboard. Do not write text in detail. Do not include any real corporate logos or text. Do not include corporate logos or text on the clothes either.
Profile / Avatar - Cinematic Lakeside Portrait — output

Profile / Avatar - Cinematic Lakeside Portrait

SGPT Image 2
An ultra-realistic cinematic portrait of a {argument name="subject" default="beautiful young woman"} sitting peacefully {argument name="setting" default="beside a calm lake"} during {argument name="lighting" default="golden hour sunset"}, captured in a soft side-profile pose. She has elegant delicate facial features, glowing fair skin, soft natural makeup, glossy lips, and deep expressive eyes looking thoughtfully into the distance. Her dark hair is styled in a loose low bun with soft face-framing strands gently falling around her cheeks, moving slightly in the evening breeze. She wears an oversized cozy beige knitted sweater with soft fabric texture, creating a warm autumn aesthetic. Golden sunlight gently illuminates one side of her face, casting soft shadows and warm highlights on her skin and sweater. The background features blurred trees, warm sunset reflections on the water, dreamy bokeh effect, peaceful lakeside atmosphere, soft warm orange and brown tones, calm emotional mood, cinematic storytelling, photorealistic details, shallow depth of field, natural outdoor lighting, cozy autumn feeling, elegant composition, editorial portrait photography, moody yet peaceful vibe, ultra detailed, 8k quality, realistic skin texture, warm golden color grading, soft focus, serene atmosphere.
Product Marketing - Urban Portal Fashion Photography — output

Product Marketing - Urban Portal Fashion Photography

Hania AiGPT Image 2
A stylish young woman sitting casually on a white ledge, framed within a {argument name="window style" default="large circular portal window"} with a soft silver rim, {argument name="background" default="city skyline"} visible in the background under a clear teal-blue sky. She has a warm olive complexion, soft glowing skin, dark hair tucked under a beige baseball cap, subtle makeup with glossy lips. Wearing a {argument name="outfit" default="navy blue satin bomber jacket"} over a light grey striped crop top, rust-brown tailored wide-leg trousers with subtle cuffed hem, and clean white leather sneakers. She sits with legs gracefully crossed at the ankle, hands resting softly on her lap, slight smile, gazing off to the side. Wrist watch, minimalist gold earrings. Studio-clean white background below the circle. Editorial fashion photography, soft natural light, sharp detail, 8K.
Social Media Post - GPT Image 2 Street Photography — output

Social Media Post - GPT Image 2 Street Photography

PromptLabGPT Image 2
prompt:

{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "photoreal_artistic_street_photography", "version": "v1.0_STREET_ART_REALISM_SER_EN", "priority": "highest" }, "output_settings": { "aspect_ratio": "4:5", "orientation": "portrait", "resolution_target": "ultra_high_res", "render_style": "ultra_photoreal_candid_film_still", "sharpness": "crisp_but_natural", "film_grain": "subtle_35mm", "color_grade": "restrained_cinematic_realism", "dynamic_range": "natural_not_hdr", "skin_rendering": "real_texture_no_retouch" }, "creative_prompt": { "scene_summary": "Documentary-style candid street photograph shot on location in [CITY/NEIGHBORHOOD]. An unscripted, unposed moment that feels emotionally honest and visually true.", "subject": "A [AGE] [GENDER] dressed in [CLOTHING], captured mid-movement: [MICRO-ACTION]. Completely natural facial expression with slight asymmetry kept intact.", "camera": "35mm lens equivalent, eye-level perspective, close yet respectful distance, intentionally imperfect framing like a real street photographer, sharp focus on the eyes, shallow-to-medium depth of field.", "lighting": "Organically motivated natural light sourced from [SOURCE: shop window / street lamp / sunset / neon signs], deep shadows that still hold detail, zero studio lighting.", "environment_details": "Authentic urban textures: peeling posters, scratched and dented metal, rain-dotted pavement, subtle glass reflections, genuine city clutter with no cleaned-up background.", "authenticity_markers": "Slight motion blur on background elements only, soft halation on bright highlights, minor film gate weave, realistic grain throughout, no beauty retouching at all.", "mood": "[MOOD: melancholic / hopeful / tense / quiet joy], cinematic in feeling but entirely believable." }, "negative_prompt": [ "studio lighting", "beauty retouch", "plastic skin", "over-sharpened", "HDR", "AI glow", "perfect symmetry", "overly clean background", "fake bokeh shapes", "text", "logo", "watermark", "painterly", "cartoon" ] } }
Comic / Storyboard - Motocross Legend Storyboard — output

Comic / Storyboard - Motocross Legend Storyboard

𝗦𝗮𝗻𝗶𝗮GPT Image 2
Storyboard sequence, 10 cinematic frames: A {argument name="subject" default="stylish young woman"} relaxes in a {argument name="setting" default="modern desert-view room"} while drinking from a glass bottle, then stands and gazes out the window with determination before casually tossing the bottle aside. She exits the building and walks toward her FMX motocross bike, gears up, and puts on her helmet. The action escalates as she {argument name="action" default="races down a giant mega ramp"}, launches into the open sky, performs a breathtaking backflip high above the desert landscape, and lands in a dramatic cloud of dust. In the final frame, she removes her helmet, her hair falling free as smiling friends run toward her cheering, all captured in ultra-realistic cinematic storytelling, golden-hour lighting, dynamic camera angles, emotional sports-drama atmosphere, and high-end action photography.
Social Media Post - Cyber-Fashion Street Portrait — output

Social Media Post - Cyber-Fashion Street Portrait

PhotoGPTGPT Image 2
Ultra realistic cyber-fashion street portrait of {argument name="reference person" default="[REFERENCE PERSON]"}, preserve the exact facial identity, facial structure, eye shape, lips, skin texture, hairstyle, makeup style, and overall likeness from the reference image with extremely high identity fidelity and photorealistic detail. Scene composition must remain nearly identical to the original image: subject standing inside a {argument name="location" default="retro Japanese public phone booth"} at night in a neon-lit city street environment, cinematic urban Tokyo aesthetic, colorful blurred neon signs visible outside the booth windows, authentic nighttime atmosphere with realistic reflections and ambient glow. Camera framing and perspective: dramatic close-up vertical portrait shot using a slightly wide-angle/fisheye lens look, centered composition, direct eye contact with camera, fashion editorial styling. Pose and interaction: subject holding a {argument name="phone color" default="bright mint-green"} retro telephone receiver to the ear with one hand while the other hand adjusts narrow red tinted sunglasses near the face. Expression confident, stylish, bold, glamorous. Character styling details MUST stay highly consistent with the original image: Leopard print newsboy/fashion cap with identical texture and pattern Narrow red translucent sunglasses with glossy finish Oversized dark rust-brown faux fur coat with heavy fluffy texture Long styled auburn/red hair flowing naturally beneath the cap Glamorous makeup with sharp eyeliner, long lashes, glossy lips Multiple silver rings, bracelets, and luxury jewelry details Long decorated manicure/nail art with rhinestone accents Leopard print lower outfit details partially visible Environment details: Authentic Japanese payphone booth interior Mint-green retro public telephone Japanese signage and stickers on booth walls Neon city lights outside the glass Nighttime cinematic urban mood Reflections on glass and metallic surfaces Realistic booth lighting from overhead panel light Lighting style: cinematic neon lighting mixed with indoor fluorescent booth light, realistic skin highlights, glossy reflections, dramatic fashion editorial contrast, high-detail textures on fur, accessories, and face. Photography style: ultra photorealistic DSLR fashion portrait, editorial magazine quality, 24mm wide-angle lens, shallow depth of field, HDR detail, cinematic color grading, hyper detailed textures, realistic anatomy, luxury cyber-fashion aesthetic. Important: replace ONLY the woman’s identity with the exact reference person while preserving ALL styling elements, accessories, clothing, props, pose, booth environment, phone color, glasses style, cap pattern, fur coat texture, lighting mood, and overall composition exactly like the original image. Negative prompt: distorted face, inaccurate identity, asymmetrical eyes, extra fingers, bad hands, blurry details, AI artifacts, plastic skin, cartoon style, CGI appearance, low quality, duplicate accessories, wrong phone color, missing j
Product Marketing - 3D Luxury Birthday Poster — output

Product Marketing - 3D Luxury Birthday Poster

TaarukGPT Image 2
Professional luxury birthday poster, 3:4 ratio. Entire frame filled with a {argument name="wall texture" default="premium off white luxury paper textured wall"}. Large number “{argument name="age" default="2"}” precisely carved in the wall with visible depth and realistic inner shadows. Inside the number: soft pink and pink balloons, subtle white flowers, elegant bouquet arrangement, premium celebration styling. A happy {argument name="child description" default="2 year old child"} with preserved reference facial features, wearing a milky white T shirt and pink denim overalls, laughing naturally. Face, shoulder, one hand and one foot extend outside the number creating a realistic 3D effect. Warm cinematic sunlight from one side, soft rim light, photorealistic skin, premium studio photography, ultra realistic, sharp focus. Typography on wall: {argument name="headline" default="MUNONYE, CHAPTER 2, 365 MORE DAYS OF WONDER"}. Clean minimalist layout, luxury magazine cover aesthetic, high end art direction, realistic shadows, natural colors, no tree shadows, no fake lighting, no AI artifacts.
Comic / Storyboard - Cinematic Karate Pizza Chef Storyboard — output

Comic / Storyboard - Cinematic Karate Pizza Chef Storyboard

Shara | AI Video CreatorGPT Image 2
Create 8 separate ultra-cinematic 3D animated cartoon storyboard frames of an {argument name="subject" default="energetic chef"} making {argument name="food item" default="pizza"} at impossible speed in {argument name="martial arts style" default="karate warrior"} style. Style: vibrant colorful 3D animated cartoon, NOT Pixar NOT Disney, original animation style, bright warm colors
Profile / Avatar - Ultra-Realistic Cyber-Fashion Portrait — output

Profile / Avatar - Ultra-Realistic Cyber-Fashion Portrait

PhotoGPTGPT Image 2
Ultra realistic cyber-fashion street portrait of {argument name="subject" default="REFERENCE PERSON"}, preserve the exact facial identity, facial structure, eye shape, lips, skin texture, hairstyle, makeup style, and overall likeness from the reference image with extremely high identity fidelity and photorealistic detail. Scene composition must remain nearly identical to the original image: subject standing inside a {argument name="location" default="retro Japanese public phone booth"} at night in a neon-lit city street environment, cinematic urban Tokyo aesthetic, colorful blurred neon signs visible outside the booth windows, authentic nighttime atmosphere with realistic reflections and ambient glow.
Product Marketing - Retro-Modern Beverage Campaign Concepts — output

Product Marketing - Retro-Modern Beverage Campaign Concepts

PanGPT Image 2
Soft Drinks & Beverages ({argument name="brands" default="Pepsi, Coca-Cola, Sprite, Red Bull"}). retro-modern glow, dynamic stadium vibes, lime street style, and high-performance racing graphics. {argument name="campaign" default="Pepsi × Sydney Sweeney — 'THE BLUE HOUR'"}
Comic / Storyboard - 第3张分镜图提示词: — output

Comic / Storyboard - 第3张分镜图提示词:

松果先森GPT Image 2
请创作一张高完成度、高清晰度的「汉唐宫廷舞 / 霓裳羽衣舞 · 16宫格分镜图」。

【整体定位】
这不是普通古风写真,也不是单纯舞蹈教学图,而是一张融合「汉唐宫廷舞」「霓裳羽衣舞」「真实宫苑空间」「电影分镜感」「16步动作编排」的高完成度分镜海报。
Social Media Post - Yellow Chick Mascot on Japanese Train — output

Social Media Post - Yellow Chick Mascot on Japanese Train

MarioTanGPT Image 2
Create a photorealistic, slightly whimsical scene inside a crowded Japanese commuter train in {argument name="city" default="Nagoya"}. In the exact center aisle stands a large life-size mascot character: a round fluffy {argument name="animal" default="yellow chick"} with soft shaggy fur, black glossy eyes, a small orange beak, orange webbed feet, tiny wings, and a small pink flower hair clip near the top of its head. Dress the mascot in a chunky knitted {argument name="clothing item" default="mustard-yellow cable-knit cardigan"} with visible braided patterns and fringe at the hem, matching the body color. Surround it with standing adult commuters in winter business attire and coats, lined along both sides of the aisle; their faces should appear intentionally blurred or anonymized. The train interior should be realistic and dense: silver handrails, hanging strap handles, fluorescent ceiling lights, purple seats at the sides, worn dark floor, windows and sliding doors, and Japanese advertisement posters throughout. Include overhead digital route signs, one prominently showing {argument name="destination text" default="名古屋"} in green Japanese text. Use a wide-angle eye-level composition, symmetrical perspective down the train car, warm indoor lighting, high detail, documentary street-photography realism mixed with surreal mascot humor. No extra characters in the aisle, no watermark, no captions, no cartoon rendering.
Product Marketing - Futuristic BentoCard Floppy Ad — output

Product Marketing - Futuristic BentoCard Floppy Ad

MarioTanGPT Image 2
Goal: Create a dark, premium Apple-style product advertising poster for a fictional tech product named {argument name="product name" default="BentoCard"}, presented as a next-generation 3.5-inch floppy disk with futuristic storage performance.

Canvas: Square 1:1 composition, 768×768 or similar, matte charcoal-black background with subtle vignette, soft gradients, faint texture, and glowing UI-card outlines. Overall mood is minimalist, high-end, futuristic, and product-launch oriented.

Header: Centered at the top, show a silver Apple logo icon, then the small product name “BentoCard”, then a large Chinese headline: “新一代 3.5 寸软盘”. Under it, add the smaller Chinese subtitle: “传统尺寸,颠覆性能”. Use clean sans-serif typography, white and light gray text, with strong letter spacing and Apple-like restraint.

Main layout: Use a two-column hero layout. On the left, place a large realistic 3D render of exactly 2 overlapping 3.5-inch floppy disks: one front disk in bright brushed silver with rounded corners, black shutter area, small Apple logo centered near the top, circular metallic hub in the middle, small black screw holes and slots; one darker rear disk offset behind it to the left, partially visible, with black/graphite finish and a circular hub. Add soft shadows and subtle reflections, as if photographed in a studio.

Right feature column: Create exactly 3 stacked rounded-rectangle feature cards with thin translucent borders and soft blue glow icons on the left. Card 1 icon: rounded square storage chip outline; text “32 TB 容量” and smaller line “比传统软盘提升 22857143 倍”. Card 2 icon: lightning bolt; text “USB 4 传输速度” and smaller line “最高 40Gb/s”. Card 3 icon: battery outline; text “超低功耗设计” and smaller line “续航提升 50%”.

Lower feature row: Under the hero area, create exactly 3 equal rounded feature cards. Card 1 has a shield icon and text “军工级防护” with smaller line “抗摔 · 防水 · 防尘”. Card 2 has a cloud icon and text “跨平台兼容” with smaller line “Mac, PC, Linux 全支持”. Card 3 has a sprout/leaf icon and text “环保材质” with smaller line “100% 可回收铝金属”.

Footer bar: At the bottom, add exactly 1 long rounded translucent bar. On the left of the bar place a small glowing rounded-square icon, then bold Chinese slogan text “传统设计,未来性能”, and on the right smaller text “3.5 寸软盘 2024”.

Visual style: Dark glassmorphism UI, subtle bevels, frosted translucent cards, cool blue icon highlights, silver metallic product material, realistic lighting, precise spacing, balanced grid, no clutter. Keep all text crisp and legible, preserve the Chinese wording exactly, and avoid extra logos, watermarks, or additional feature cards.
Profile / Avatar - Neon Censored Portrait Avatar — output

Profile / Avatar - Neon Censored Portrait Avatar

AZIZ | AI 🇸🇦GPT Image 2
Create a square-crop profile-picture style cinematic portrait of a bald adult man viewed from the front, tightly framed from the top of the head to the upper chest. The subject has visible ears on both sides, a strong neck, and wears a black leather jacket with a short stand collar and a small front zipper. Cover the entire face with exactly 1 large centered opaque square censor block, aligned vertically and horizontally over the head, extending from just below the top of the skull down past the mouth/chin area; the block should be a muted dark plum-to-purple gradient with no text or symbols. Use dramatic neon studio lighting: warm amber/orange rim light on the left side of the head and neck, bright magenta/pink rim light on the right side, with a dark indigo-purple background and soft depth-of-field blur. The visible skin should have realistic texture and high-detail pores, while the overall look is photorealistic, moody, futuristic, and suitable as a mysterious social media avatar. Use {argument name="censor block color" default="muted dark plum purple gradient"}, {argument name="jacket color" default="black leather"}, {argument name="left rim light color" default="warm amber orange"}, {argument name="right rim light color" default="magenta pink"}, and {argument name="background color" default="dark indigo purple"}.
Product Marketing - Glossy Pink Betta Fish Transformation — output

Product Marketing - Glossy Pink Betta Fish Transformation

ibexdreamGPT Image 2
Using REFERENCE_0 as the visual style reference only, transform the surreal glossy macro studio aesthetic into a single {argument name="subject" default="pink betta fish"}. Remove the mouths, teeth, tennis ball, jewelry, and mirror reflection entirely. Keep the high-contrast black background, dramatic wet-looking highlights, close-up product-photography lighting, and hyper-detailed texture. Create the fish in side profile facing right, with a rounded spotted head, large glossy black eye, pouty lips, and translucent flowing fins. Use a saturated {argument name="main color" default="deep magenta pink"} palette with darker black speckles across the head and upper body. Show exactly 6 prominent fin elements: 1 large rippling tail fin trailing left, 1 top dorsal fin, 1 long lower flowing fin, 1 rounded gill-side fin near the head, and 2 thin dangling ventral fins. Add a centered opaque rectangular censor block over the middle of the fish body, colored {argument name="censor block color" default="dark burgundy"}, with sharp edges and no text. Composition should be wide horizontal, minimal, isolated on {argument name="background color" default="pure black"}, with no extra objects, no reflection, and no typography.
Profile / Avatar - Ukiyo-e Portrait Transformation — output

Profile / Avatar - Ukiyo-e Portrait Transformation

コンドウハルキ|HarukazeGPT Image 2
Using the provided reference image, transform the person into an Edo-period ukiyo-e / nishiki-e / kabuki actor portrait style while preserving the original pose, black bucket hat, hand-near-mouth gesture, and anonymous blurred face area. Replace the modern shirt with traditional layered kimono robes: a dark navy outer robe with two circular floral crests, a tan checked inner robe, and subtle reddish trim. Change the composition to a vertical close-up woodblock print on aged beige washi paper with visible grain, ink texture, worn edges, and muted traditional pigments. Add exactly 4 new decorative/background elements: 1 vertical title cartouche on the upper left with Japanese calligraphy reading {argument name="vertical title text" default="東都新賢似顔繪"}, 1 red artist seal beneath it reading {argument name="seal text" default="豊國画"}, and 2 stylized blue-gray Edo cloud motifs, one near the upper right and one along the left middle. Keep the face intentionally obscured with a soft rectangular blur matching the reference privacy treatment. Avoid photorealism, modern lighting, and extra text.
Product Marketing - Newton Coffee Opening Poster — output

Product Marketing - Newton Coffee Opening Poster

牛顿AI中转站GPT Image 2
Goal: Create a vertical premium coffee shop grand-opening promotional poster for {argument name="brand name" default="牛顿咖啡"}, with a warm beige marble-paper background, brown typography, taped paper collage elements, and a realistic mall storefront mockup in the center.

Canvas: Portrait poster, 2:3 ratio, high resolution. Use an elegant cream, caramel, coffee-brown, and warm gold palette. The overall mood is modern Chinese commercial advertising, cozy, polished, and upscale.

Top section: Center a simple coffee-cup logo with steam above the brand name {argument name="brand name" default="牛顿咖啡"} and small English text “NEWTON COFFEE”. Below it place spaced uppercase text “NEW STORE OPENS”. The main oversized headline should read {argument name="headline text" default="拍围挡 · 喝咖啡"} in bold dark-brown Chinese serif display type.

Coupon banner: Under the headline, add a torn white paper strip taped at the upper-right corner with beige masking tape. On the left of the strip draw a small line-art steaming cup and handwritten “Enjoy!”. In the center place a huge “1000”. On the right place Chinese and English offer text: “杯免费送”, “FREE COFFEE”, “FREE COFFEE”.

Central storefront scene: Create a realistic curved mall construction hoarding / storefront wall with glossy floor reflections and glass mall architecture behind it. The hoarding is wrapped in coffee-themed graphics with swirling latte foam and marble textures. It contains exactly 5 visible collage areas: 1) left vertical torn-edge coffee photo showing latte art in a cup, 2) small taped left notice reading “新店开业 / 1000杯 / 免费送 / FREE COFFEE”, 3) large central cream panel with the logo, brand name, and handwritten slogan {argument name="slogan" default="好咖啡,这里喝得到!"}, 4) right taped notice reading “NEW STORE OPENS / 2026 / 6/9 / 我们在这里等你”, 5) lower-right torn photo of a warm coffee shop interior with a small cup illustration beside it.

Central feature icons: Along the bottom of the large central panel, show exactly 3 minimal brown line icons with labels: 1) coffee bean icon labeled “现磨咖啡 / FRESHLY GROUND”, 2) milk carton icon labeled “鲜奶拿铁 / FRESH MILK LATTE”, 3) dessert cloche icon labeled “手作甜点 / HANDMADE DESSERT”.

Instruction section below storefront: On a clean cream background, create exactly 3 horizontal participation steps separated by arrows: 1) camera icon with “拍围挡打卡”, 2) cup icon with “领免费咖啡”, 3) smiley icon with “进店体验”. Beneath the steps, add two centered lines of smaller Chinese instruction text: “拍下围挡任意角度照片,发布至社交平台并带话题 #牛顿咖啡新店开业#” and “即可到店领取免费咖啡一杯!每日限量,先到先得!”

Bottom information row: Create exactly 3 information blocks with thin vertical dividers: 1) location pin icon, “牛顿商场名”, “NEWTON MALL”; 2) stacked-floor icon, “L1层”, “LEVEL L1”; 3) calendar icon, {argument name="opening date" default="2026 - 6 - 9"}, “盛大开业”. At the very bottom add handwritten Chinese text “牛顿喝了都说好的咖啡” with a casual underline.

Visual style: Elegant Chinese coffee retail poster, photorealistic storefront mockup combined with paper collage, torn paper edges, masking tape, soft shadows, warm lighting, subtle marble texture, coffee foam swirls, refined typography, balanced central alignment.

Constraints: Keep all listed text legible and in the same approximate positions. Use exactly 3 feature icons, exactly 3 participation steps, exactly 3 bottom information blocks, and exactly 5 visible collage areas on the storefront. No extra logos, no watermark, no QR code.
Social Media Post - Pink Gothic Floral Fantasy Portrait — output

Social Media Post - Pink Gothic Floral Fantasy Portrait

NIKKOGPT Image 2
Create a vertical 9:16 ultra-detailed fantasy fashion portrait of an anime-inspired young woman with {argument name="hair color" default="cotton-candy pink"} hair styled into exactly 2 long flowing twin tails, drifting dramatically left and right as if underwater or in zero gravity. Her face is intentionally hidden by a flat centered square censor block in muted dusty pink, covering the entire facial area. She wears a black gothic couture mini dress with sheer translucent sleeves, lace mesh, sparkling beadwork, and abundant pink floral appliqués. Include exactly 7 large prominent pink roses on the outfit and nearby foreground: one on the chest, three clustered at the waist, one lower on the skirt, one at the left edge, and one soft blurred rose in the lower right foreground. Add black-and-pink floral hair ornaments on both sides of her head, a black lace choker, delicate sheer arm ruffles, and tiny white bead strands. Surround her with a dreamy surreal background of floating translucent bubbles, glossy black pearls, pink pearls, black-and-pink patterned spheres, circular vinyl-record-like discs, and fine botanical line-art flowers. Make exactly 3 prominent circular disc motifs visible: one large at the upper right, one small at the lower left, and one partial at the bottom right. Make exactly 10 prominent floating glossy spheres visible in the foreground and midground, mixing pink, black, clear, and patterned surfaces, with additional tiny sparkle particles kept subtle. Use a luminous white and pale pink background, high-key lighting, shallow depth of field, soft bokeh, glossy reflections, delicate black ink filigree, and a luxurious hyperreal digital-art finish. Color palette: {argument name="accent palette" default="pastel pink, black, white, and pearl silver"}. Pose: upper body angled slightly left, one bare shoulder visible, right hand raised gracefully near the face, elegant and ethereal. No text, no watermark, no extra characters.
Browse by model, style or topic

Find your next direction

ASTORIE CANVAS

Take the idea further.

Bring your prompts, references and results together in one creative space.

Open your canvas ↗