Instinct AI

Prompt Library

AI Prompt Library

Curated image, video and web design prompts from creators around the world. Copy any prompt, swap the subject or style, and generate with the latest models.

15,630 prompts · Updated daily · 100% free

126 prompts

E-commerce Main Image - GPT Image Perfume Bottle Prompt
GPT Image 2

E-commerce Main Image - GPT Image Perfume Bottle Prompt

A giant, rounded, light green transparent glass perfume bottle, containing a miniature mossy valley, bonsai trees, rocks, and small waterfalls sealed inside. Placed in a brutalist raw concrete space covered by water; cold daylight enters through architectural openings from the upper left, while warm sunset light forms a rim light from the back right. The glass exhibits real refraction, caustics, tiny water droplets, and highlight distortion; the water surface creates natural reflections. Low-angle product photography, subject positioned slightly to the right, large negative space, realistic optical depth of field, high-end fragrance advertising quality, no text, no logo, no plastic CGI look.

@Dry Seven
Infographic / Edu Visual - UGC Style Marketing Panel Grid
GPT Image 2

Infographic / Edu Visual - UGC Style Marketing Panel Grid

Create a full-sheet 3x3 grid of realistic UGC-style panels featuring this {argument name="category" default="provision store"} using GPT Image 2. Split the video into 3 continuous sections. Each panel must contain a cinematic visual frame plus readable production notes printed directly inside the panel. The goal isn't just to show the product. It’s to help customers imagine a reason to buy it. The business name is {argument name="business name" default="Zioraa Ventures"}. Embedded the business name in the background.

@Olatunde AI
Product Marketing - ChatGPT Image 2 Autumn Casual Outfit Prompt
GPT Image 2

Product Marketing - ChatGPT Image 2 Autumn Casual Outfit Prompt

OUTFIT: A soft oversized mohair sweater in dusty rose, worn slightly off-shoulder and layered over a thin white turtleneck, paired with high-waisted cream wide-leg corduroy pants with tiny embroidered floral patches on the pockets. Styled with chunky platform Mary Janes and a small leather crossbody bag. Soft, cozy, feminine casual fashion aesthetic. Dusty rose, white, and cream color scheme. No extra decorations.

@のぞむ*AIイラスト
Profile / Avatar - GPT Image 2 Purple Hair Fashion Portrait Prompt
GPT Image 2

Profile / Avatar - GPT Image 2 Purple Hair Fashion Portrait Prompt

Create a hyper-realistic medium full-body fashion portrait of the same young adult female character from the reference image, preserving her signature vivid violet-purple chin-length straight bob with soft bangs, fair porcelain skin, natural freckles across her nose and cheeks, hazel/light-brown eyes, delicate facial features, glossy lips, and slim physique. She is sitting in a relaxed crouching pose against a warm terracotta textured wall, with her head resting gently on one hand while looking calmly and directly at the camera. She wears a terracotta rust-orange cropped hoodie, beige high-waisted cargo jogger pants, and brown leather lace-up combat boots. Add a patterned satin bow headband and a small orange butterfly hair clip. Use soft natural daylight with warm earthy autumn tones. Keep the composition intimate and editorial with realistic skin texture, detailed purple hair, natural fabric and leather textures, subtle shadows, cinematic depth of field, photorealistic quality, ultra-detailed 8K, premium fashion photography.

@Wareen AI 💟
Social Media Post - Travel Memory Scrapbook Poster
GPT Image 2

Social Media Post - Travel Memory Scrapbook Poster

Transform the uploaded photo into a premium travel-memory scrapbook poster. Keep the original photo as the main visual reference and preserve the important subjects, objects, environment, composition, colors, and recognizable details accurately. Do not change the identity or structure of the main subject. Create a vertical 3:4 editorial scrapbook layout divided horizontally into two equal sections: TOP 50%: Place the original photograph prominently, enhanced with warm, natural, slightly cinematic color grading. Keep it realistic, detailed, and photographic. Do not over-edit or make it look artificial. BOTTOM 50%: Create a beautiful hand-drawn illustrated journal page inspired directly by the photograph. Extract 6–9 of the most recognizable visual elements from the original image and turn each into a small individual colored-pencil / ink / watercolor-style sketch arranged in a clean 3×3 scrapbook grid. Use: - textured warm ivory/off-white paper background - subtle paper grain - hand-drawn pencil and ink outlines - loose colored-pencil and watercolor shading - slightly imperfect handmade strokes - soft muted but cheerful colors - tiny doodles such as stars, hearts, leaves, sparkles, waves and arrows - thin, delicate hand-drawn grid dividers - cozy travel-journal aesthetic - sophisticated editorial composition - authentic handmade imperfections Add a handwritten title at the top of the illustrated section, customized to the photo's theme, such as "{argument name="location" default="[LOCATION]"} Memories", "{argument name="theme" default="[THEME]"} Moments", "Sweet Moments", "Blue Sky Memories", etc. Under each illustrated element, add a short handwritten label describing it, for example: “street lamp”, “soft clouds”, “colorful lights”, “tea”, “old walls”, “sweet treat”, “green moments”, etc. At the very bottom, add a small handwritten sentimental caption related to the photo, such as: “a perfect day to remember ♡” or “same place, different feelings ♡” The final result should feel like a luxury travel scrapbook / visual diary page created by hand, combining a real photograph with charming illustrated memories. IMPORTANT: - One original photo + one illustrated memory section - Clean 50/50 horizontal division - Vertical 3:4 composition - Preserve the original photo realistically - Illustrations must clearly originate from objects in the uploaded photo - No photorealistic illustrations - No 3D rendering - No excessive graphic-design effects - No borders around individual illustrations - No random objects unrelated to the photo - Keep typography minimal, elegant, and handwritten - Make the entire page cohesive, warm, nostalgic, artistic, and premium

@Sairah
E-commerce Main Image - Minimalist Fashion E-Commerce Grid
GPT Image 2

E-commerce Main Image - Minimalist Fashion E-Commerce Grid

[Brand & Product Information] - Brand Name: {argument name="brand name" default="Tsubaki, Modern Japan Apparel"} - Collection Name: {argument name="collection" default="A/W 2026 COLLECTION"} - Representative Item Price: {argument name="price" default="¥18,000 + TAX"} [Image Quality/Direction/Composition] - Style: Lookbook photography for an e-commerce site of a minimalist and sophisticated Japanese fashion/lifestyle brand. - Composition: A flat lay or orderly display of apparel items (bags, outerwear, shoes, etc.) carefully arranged on a studio flooring or concrete floor with natural light shining in. - Typography Placement (for GPT-image / Nano Banana Pro): The brand name {argument name="brand name" default="Tsubaki, Modern Japan Apparel"}, collection text {argument name="collection" default="A/W 2026 COLLECTION"}, and price {argument name="price" default="¥18,000 + TAX"} are placed discreetly in the corners in an ultra-thin font. - Lighting/Color: Very soft light like natural light on a cloudy day, low contrast, and calm tones based on earth colors (beige, olive, charcoal gray, off-white). [Strict Layout and Output Constraints (Required)] - Output the finished design itself filling the entire screen. Background and scene depictions (walls, spaces, shadows, etc.) inside the design may follow the instructions in the text. - Prohibited items: Photos of the finished poster in a frame, on a wall, mockup photos on a desk/paper, perspective warp, 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 1:1" or "--ar 4:3"

@AI Guide-Note - 実務で使えるAI活用メディア
E-commerce Main Image - Subtle Rose Nail Edit
GPT Image 2

E-commerce Main Image - Subtle Rose Nail Edit

Using REFERENCE_0 as the base image, perform an extremely subtle product-style edit: change only the visible fingernails on the hand holding the strawberries into a delicate {argument name="nail design" default="pale pink rose-themed manicure with tiny floral nail art and a glossy finish"}. Keep the entire composition, face, pose, dress, bonnet, bouquet, strawberries, roses, wallpaper, lighting, color palette, and the headline text {argument name="headline text" default="PINK EDEN"} as close to the reference as possible. Do not alter the character, background, typography, cropping, or overall mood. The edit should affect exactly 2 visible nail areas: the main thumb nail and the small partially visible fingernail beside it; all other details should remain unchanged.

@のえる
YouTube Thumbnail - Cinematic Badminton Smash GPT Image 2
GPT Image 2

YouTube Thumbnail - Cinematic Badminton Smash GPT Image 2

Ultra-realistic cinematic sports photograph of a strikingly handsome young male badminton athlete in his early 20s, captured at the peak of a powerful overhead smash. He has thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a defined sculpted jawline, subtle natural stubble, realistic skin texture, visible pores, and refined masculine facial features. He is jumping explosively above the badminton court, body dynamically twisted, one arm fully extended overhead with a professional badminton racket aimed aggressively toward the camera. His expression is intensely focused and determined. A shuttlecock is extremely close to the lens in the foreground, dramatically enlarged with razor-sharp feather details, creating powerful depth and perspective. Modern indoor badminton arena, polished court floor, subtle net visible in the background, dramatic overhead stadium lights, strong rim lighting, atmospheric haze, realistic shadows, tiny sweat droplets frozen in motion, cinematic motion energy, shallow depth of field, dynamic low-angle perspective, 85mm sports photography aesthetic, ultra-detailed skin and clothing, photorealistic textures, HDR, high contrast, frozen action, premium sports campaign photography. Large bold “SMASH” typography subtly integrated into the background, clean athletic editorial design, no logos, no watermark, no other people. 9:16 vertical composition, 8K, photorealistic, cinematic, professional sports advertising campaign, extremely sharp subject and shuttlecock, dramatic depth of field.

@HeisenLegacy
Social Media Post - Minecraft Character in Sunflower Field
GPT Image 2

Social Media Post - Minecraft Character in Sunflower Field

A hyper-realistic, cinematic close-up shot of a Minecraft-style character standing in a vibrant field of sunflowers during a golden sunset. The character is constructed from blocky voxels, featuring dark skin, a full black beard, and wearing a green cap with a white t-shirt and green pants. He is holding a large, blocky bee gently against his face. Surrounding him are numerous other flying bees with translucent wings, rendered with realistic motion blur and depth of field. In the background, there is a pixelated rainbow arching across an orange sky filled with blocky clouds, a distant tree line, and a small white pickup truck on a dirt road. The lighting is warm and volumetric, creating a nostalgic and peaceful atmosphere.

@Jxsfly
Infographic / Edu Visual - Japanese Game Dev Banner
GPT Image 2

Infographic / Edu Visual - Japanese Game Dev Banner

A horizontal banner image with a light beige background. On the left side, there is Japanese text in purple and yellow: '制作記録 #2 敵キャラ編' (Production Record #2 Enemy Character Edition), followed by large bold text '生成AIの「あるある」がモンスターに!' (Generative AI's "Common Occurrences" become monsters!), and smaller text below 'ジェネコの冒険 ~ノイズの大迷宮~ 敵キャラ制作の2日間' (Geneko's Adventure ~ The Labyrinth of Noise ~ Two Days of Enemy Character Creation). To the right of the text, there are two small chibi characters: a girl with brown hair wearing glasses and a school uniform holding an open book, and a blue cat-like creature with pink ears reading over her shoulder. The rest of the image is filled with a collage of various colorful monster designs arranged in rows. Top row includes a shiny green sphere with eyes, a muscular blue furry beast with glowing purple eyes, a purple insectoid robot with green wings, and a multi-limbed robotic figure. Middle section features a red beetle-like creature with warning signs on its shell, a wizard character wearing a rainbow-colored pointed hat and robe holding a staff, a white moth-like creature with blue eye patterns on its wings, a black spider-tank hybrid with red lights, and a pink abstract shape resembling a face or symbol. Bottom row shows a green goblin-like creature with glowing yellow eyes, a brown spiky turtle-like monster, a pale humanoid figure with blank facial features, a split-faced doll character (half pink/half grey) holding a knife, and a purple blob monster with angry eyes.

@Ryu
Product Marketing - Broken Mirror Fashion Editorial Prompt
GPT Image 2

Product Marketing - Broken Mirror Fashion Editorial Prompt

Ultra-realistic cinematic high-fashion editorial photograph of a strikingly handsome young man in his early 20s, with thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a sharply defined sculpted jawline, subtle natural stubble, and realistic skin texture with visible pores. Concept: His face is seen through several large, irregularly broken mirror fragments, each piece reflecting a slightly different angle of his face — one showing his intense eyes, another capturing his sharp side profile, another revealing his jawline and lips, and the central fragment showing his face staring directly into the camera. The fractured mirror pieces create a mysterious, artistic composition, with sharp geometric edges and realistic reflections. Expression & Pose: Calm, mysterious and emotionally intense expression, deep captivating gaze directed toward the camera through the mirror fragments, head slightly tilted, with a subtle sense of introspection and hidden identity. Outfit: Elegant black high-neck shirt beneath a tailored black blazer, minimal luxury styling, sophisticated and timeless. Lighting: Dramatic low-key cinematic lighting, deep shadows, subtle cool blue highlights along the mirror edges, soft light illuminating his eyes and facial features, realistic reflections and delicate specular highlights on the broken glass. Background: Dark minimalist interior with a charcoal-black background, subtle atmospheric haze, faint reflections and a sophisticated noir aesthetic. Photography: Extreme attention to facial details, photorealistic skin texture, natural facial proportions, 85mm portrait lens, shallow depth of field, cinematic color grading, high contrast, ultra-detailed 8K HDR, luxury fashion magazine editorial, masterpiece composition. Mood: Mysterious, introspective, dark, elegant, psychologically intriguing and cinematic. Vertical 9:16 composition, close-up portrait, face occupying the central area, mirror fragments artistically arranged around the face, realistic glass reflections, perfectly coherent facial features within each reflection, professional editorial photography. No text, no typography, no watermark, no extra faces, no distorted facial features, no artificial-looking skin, no cartoon effects.

@HeisenLegacy
Profile / Avatar - Mirror Selfie White Tulle Prompt
GPT Image 2

Profile / Avatar - Mirror Selfie White Tulle Prompt

Subject: White tulle in front of mirror. Main Subject: The protagonist is a woman sitting and taking a selfie in front of a floor mirror wearing a white tulle dress, positioned centrally. Character & Expression: Small oval face, large dark brown eyes, thin eyebrows, neat nose, glossy pale peach lips. Expression is calm, facing lower left with gaze falling onto smartphone screen. Hair near black tied in low bun, leaving thin bangs and stray hairs along cheeks. Clothing & Pose: Long dress with white strapless bodice and multiple layers of sheer tulle, thin silver gem anklets on both ankles. Sitting on white long-pile rug, knees raised high toward chest, holding black smartphone vertically in front of face with right hand. Background & Light: From left to right background: black leather chair inside mirror frame, warm lamp and flowers upper left, dark curtains around. Soft warm light from upper left illuminates face, white cloth, and legs. Composition & Camera: 2:3 vertical portrait, full-body shot from top of head to reflected feet tips via floor mirror frontal camera. Place person very large centrally, occupying most of screen height. Naturally crop feet tips and mirror frame at screen edges, focus on face, phone, and white tulle, lightly blur background. Texture & Style: Photorealistic real photo. High definition of natural skin, hair, clothing material, and surrounding props, maintaining indoor colors of white, black, and gold. Negative: Change mirror shot and knee position; omit white tulle

@Prompt アトリエ|AI画像プロンプト
Social Media Post - Surreal Miniature Coral Diorama
GPT Image 2

Social Media Post - Surreal Miniature Coral Diorama

A vertical, high-resolution macro photograph of a surreal miniature diorama. The scene is dominated by complex, fuzzy organic structures resembling coral or moss in shades of beige and rust-orange. In the center stands a small, cylindrical lighthouse with orange walls and a red roof, nestled within the textured growth. To the right, a cluster of stylized green palm trees sits atop a mossy island. A white analog clock face with Roman numerals is embedded in the upper-right coral structure. On the left, a tiny hot air balloon floats near a looped branch. At the bottom, a dark grey, granular surface serves as the ground, where a small blue toy boat rests on the left and a tiny green lizard-like figure stands on the right. The depth of field is extremely shallow, creating a strong bokeh effect that blurs the background and foreground elements into soft washes of color.

@Lynn Cole
YouTube Thumbnail - Anime Girl in Snowy European Street
GPT Image 2

YouTube Thumbnail - Anime Girl in Snowy European Street

Create a vertical digital illustration in a semi-realistic anime style depicting a young woman standing on a snowy cobblestone street during twilight. The subject has long, dark hair with bangs, dusted with white snowflakes, and fair skin with soft pink blush on her cheeks and nose. She is looking upward to the right with a gentle, wistful expression, exhaling a visible puff of white breath into the cold air. She wears a thick, textured beige wool coat and a matching chunky scarf wrapped around her neck. In her arms, she clutches a vintage brown leather-bound book with gold detailing on the cover. To the left, a classic black iron street lamp glows with a warm yellow light. The background features blurred European-style brick buildings with snow-covered roofs and distant church spires against a sky transitioning from deep blue to purple and orange. Falling snowflakes are scattered throughout the scene.

@空想AI
Comic / Storyboard - Neo-Naive Style Character Fight Illustration Prompt
GPT Image 2

Comic / Storyboard - Neo-Naive Style Character Fight Illustration Prompt

[Character A] and [Character B], neo-naïve painting × outsider art × primitive figurative painting × children's drawing style character translation. The two characters are composed of a small number of irregular geometric color blocks, retaining only their strongest identity markers: primary color, head silhouette, hairstyle or ears, eyes, representative clothing color blocks, signature accessories. The two are fighting intensely but comically, bodies pressed close and entangled. Randomly design actions such as face-grabbing, head-pushing, hugging, pulling, slapping, pinning down, or mutual pouncing based on the characters; hand contact is clear, limbs intersect, center of gravity is unbalanced, making the fighting relationship instantly readable. Childish and inaccurate human anatomy: slender torsos, stiff straight limbs, inaccurate proportions, tilted heads, exaggerated hands and feet, incorrect perspective. Facial features compressed into a few rough color blocks, expressions angry, shocked, baring teeth, screaming, or aggrieved, possessing an absurd comedic feel. Rough opaque paint flat coloring, dry brush marks, frayed edges, uneven filling, shaky hand-drawn outlines, local underpainting exposure; body and clothing represented directly by flat color blocks. Warm gray-white or off-white paper background, large areas of blank space. The two characters are located in the center, entangled with each other forming a compact action mass, the picture focuses on expressing the relationship between the characters. Like a fight moment quickly drawn from memory by an untrained person: primitive, clumsy, direct, absurd, cute. Vertical format, extremely small "voxcat" signature in the bottom right corner.

@VoxCat
Product Marketing - Dark Portrait Cinematic
GPT Image 2

Product Marketing - Dark Portrait Cinematic

Ultra-realistic, cinematic, high-fashion close-up portrait of a strikingly handsome young man in his early 20s, with thick naturally wavy jet-black hair, strong masculine eyebrows, deep dark-brown eyes, a sharply defined sculpted jawline, subtle natural stubble, and realistic skin texture with visible pores. CONCEPT & COMPOSITION: His face emerges mysteriously from absolute, pitch-black darkness, creating a powerful and captivating visual. Only his intense dark-brown eyes, the bridge of his nose, and the sharp contours of his sculpted jawline are illuminated by extremely subtle, soft directional lighting. The rest of his face gradually disappears into deep, velvety shadows, creating a dramatic chiaroscuro effect. LIGHTING & MOOD: Extremely low-key cinematic lighting with delicate highlights reflecting in his eyes, a faint strip of soft light tracing the bridge of his nose, and subtle illumination defining his jawline. Deep blacks, rich shadows, dramatic contrast, and a mysterious, intense, sophisticated atmosphere. His expression is calm, confident, serious, and effortlessly masculine, with his eyes staring directly into the camera. PHOTOGRAPHY & QUALITY: Extreme close-up portrait, shot on an 85mm professional portrait lens, shallow depth of field, ultra-detailed natural skin texture, realistic facial features, cinematic shadows, luxury fashion editorial photography, professional studio lighting, 8K HDR, photorealistic quality, sophisticated monochromatic black aesthetic, and exceptionally sharp eye details. BACKGROUND & STYLE: Completely black, seamless background with no visible surroundings. Minimalist composition emphasizing the beauty of the face, eyes, and jawline. Dark luxury editorial campaign aesthetic, mysterious cinematic atmosphere, artistic use of negative space, deep blacks, and subtle silver-toned highlights. STRICT REQUIREMENTS: Maintain natural and realistic masculine facial proportions, anatomically accurate features, lifelike skin texture, and natural hair. No artificial glow, no excessive lighting, no visible background, no extra objects, no text, no logo, no watermark. Vertical 9:16 aspect ratio.

@HeisenLegacy
YouTube Thumbnail - Noir Telephone Booth Portrait
GPT Image 2

YouTube Thumbnail - Noir Telephone Booth Portrait

Ultra-realistic cinematic night photograph of a strikingly handsome young man in his early 20s sitting inside a vintage red telephone booth on a deserted city street at midnight. He has thick naturally wavy jet-black hair, strong eyebrows, deep dark-brown eyes, a defined sculpted jawline, subtle natural stubble, realistic skin texture, visible pores, and refined masculine facial features. He holds an old black telephone receiver close to his ear, with a mysterious, thoughtful expression as he looks slightly toward the rain-covered glass. Heavy rain falls outside, droplets streaming down the glass panels, while dense atmospheric fog surrounds the booth and softly obscures the empty street. Wet pavement reflects the warm amber glow of the booth and distant streetlights. Vintage urban architecture fades into the mist in the background. Subtle neon reflections, cinematic rim lighting, soft volumetric light beams, deep shadows, moody midnight-blue atmosphere, realistic reflections on wet surfaces, shallow depth of field, 85mm lens, f/1.4, dramatic film grain, high dynamic range, photorealistic skin, intricate fabric details, sophisticated noir aesthetic, mysterious and emotional atmosphere, premium editorial photography, 8K, ultra-detailed, natural proportions, no text, no watermark, no women.

@HeisenLegacy
Social Media Post - Interactive Mural Coffee Photo
GPT Image 2

Social Media Post - Interactive Mural Coffee Photo

Use the person in the reference image as the main character, suitable for both male and female subjects. Preserve the exact facial identity, facial structure, age, skin tone, and natural expression. Do not change the person’s identity or create an artificial/plastic-looking face. Create a 4:5 vertical street-editorial photograph set in a stylish urban café alley with a large black brick wall. On the wall, create a huge black-and-white realistic mural depicting the same person from the reference image, holding a metallic coffee pot and pouring coffee downward. The real person stands directly below the mural, holding a coffee cup positioned perfectly under the stream of coffee coming from the mural, creating a fun, artistic, interactive, and viral visual effect. For a female subject: Wear an oversized white shirt with a relaxed, slightly loose fit, youthful and modern styling, naturally tucked in, paired with jeans or dark-colored trousers and clean sneakers. Avoid a stiff corporate look or tight-fitting clothing. For a male subject: Use a modern urban-casual outfit that looks youthful, clean, stylish, and contemporary. The mural should have a realistic street-art aesthetic, featuring black and white tones with bold orange accents, expressive brush strokes, paint drips, and short graffiti typography such as “BỪNG NĂNG LƯỢNG” or “CÀ PHÊ MỖI NGÀY.” Use neutral daylight with natural skin tones and no excessive yellow color cast. Camera angle should be slightly low and editorial, showing the subject full-body with a relaxed, natural pose. Do not use a chin-on-hand pose. Ultra-photorealistic, cinematic depth of field, realistic hands, accurate coffee stream, natural body proportions, authentic skin texture, highly detailed, 8K quality. Do not copy the exact composition of the reference/sample image. Keep only the core concept of a real person interacting with a giant mural while creating a fresh, original, visually striking composition.

@Aiza
YouTube Thumbnail - Colossal MPD Robot Clearing Wreck
GPT Image 2

YouTube Thumbnail - Colossal MPD Robot Clearing Wreck

A cinematic, photorealistic image of a colossal bipedal police robot standing on a wet Tokyo highway at dusk. The robot is constructed from heavy black mechanical joints and white armored plating, with "警視庁" and "MPD" clearly printed in black text on its chest plates. It has red emergency lights mounted on its shoulders and a complex sensor array head. In its left hand, the robot is lifting a heavily crushed, mangled black sedan off the ground. The scene is chaotic but organized: in the foreground, a Japanese police car with flashing red lights sits on the left, while officers wearing dark uniforms and high-visibility yellow vests labeled "POLICE" direct traffic with glowing batons. Orange traffic cones line the wet asphalt, which reflects the city lights. In the background, green overhead highway signs display directions for "Shutoko Expwy," "Ginza," "Tokyo Sta.," and "Hamamatsucho." A large tow truck with an orange crane arm is visible to the right. The atmosphere is moody and industrial, with rain-slicked surfaces and a backdrop of blurred skyscrapers.

@カーブミラー
E-commerce Live Stream UI Mockup
GPT Image 2Featured

E-commerce Live Stream UI Mockup

{ "type": "live stream UI mockup", "subject": { "description": "portrait of {argument name=\"host name\" default=\"Elon Musk\"}, smiling, wearing a black t-shirt with a white technical schematic graphic", "background": "left side shows a screen with '{argument name=\"left background logo\" default=\"SPACEX\"}' text, right side shows a red '{argument name=\"right background logo\" default=\"Tesla T logo\"}' and a dark car" }, "ui_overlay": { "top_header": { "host_info": "avatar, name '{argument name=\"host name\" default=\"Elon Musk\"}', subtext '55.6万本场点赞', red '关注' button", "rank_badge": "gold coin icon with '全站第1名'", "viewer_stats": "3 top viewer avatars with '12.3w', '8.6w', '5.7w', total '68.7万', 'X' close button", "right_links": "'更多直播 >', '礼物展馆 0/24' with blue '经典' tag" }, "mid_left_gifts": { "count": 2, "items": [ "avatar '科技爱好者', '送小心心', heart icon x 1314", "avatar '星辰大海', '送火箭', rocket icon x 666" ] }, "bottom_left_chat": { "system_message": "level 37 badge '宇宙漫游者 加入了直播间'", "message_count": 7, "messages": [ "小火箭: 马斯克!未来可期!🚀", "future: 特斯拉Model 2什么时候出?", "星空梦想家: SpaceX今年能上火星吗?", "AI探索者: Neuralink进展如何?", "帅气的网友: 马总好!", "Mars: 第一次来你的直播,超激动!", "用户123: 讲讲AI吧,会取代人类吗?" ] }, "bottom_right_product_card": { "hot_tag": "orange '热卖 x 1888'", "image": "Tesla Cybertruck", "title": "{argument name=\"product name\" default=\"特斯拉Cybertruck 电动皮卡\"}", "price": "{argument name=\"product price\" default=\"¥ 1,618,000\"}", "button": "red '抢' button", "floating_animation": "translucent hearts floating up the right edge" }, "bottom_bar": { "input_field": "'说点什么...'", "icons": ["smiley face", "three dots", "shopping cart", "gift box", "share"] } } }

@神经病不想好转
Comic / Storyboard - Museum of Lost Tomorrows conceptual scene
GPT Image 2

Comic / Storyboard - Museum of Lost Tomorrows conceptual scene

{ "title": "The Museum of Lost Tomorrows", "image_description": "A vast {argument name=\"location\" default=\"underground museum hidden beneath a forgotten city\"}. The architecture is breathtaking, with endless marble hallways illuminated by warm golden light filtering through giant glass ceilings. Thousands of glass display cases stretch endlessly into the distance. Inside each case is a future that never happened. One contains a wedding dress that was never worn. Another holds a Nobel Prize medal that was never earned. Another displays a dusty guitar beside a sold-out world tour poster from a musician who gave up too soon. Visitors walk silently through the museum, staring at the exhibits with tears in their eyes.", "main_subject": { "character": "A young man standing alone", "appearance": "Dark overcoat, slightly worn shoes, tired eyes", "expression": "Shocked and emotional", "focus": "Sharp focus" }, "story_element": { "twist": "At the end of the museum, he discovers an entire room dedicated to his own abandoned dreams.", "question": "What would you do if you could see the life you almost lived?" }, "environment": { "location": "Underground Museum", "lighting": "Golden cinematic lighting", "atmosphere": "Silent, emotional, sacred" }, "cinematography": { "camera": "ARRI Alexa 65", "lens": "50mm anamorphic", "shot_type": "Wide cinematic shot", "depth_of_field": "Shallow", "composition": "Award-winning storytelling frame" }, "mood": [ "Heartbreaking", "Thought-provoking", "Melancholic", "Beautiful" ], "style": { "reference": "Christopher Nolan meets Denis Villeneuve", "quality": "Ultra photorealistic", "resolution": "8K", "film_grain": true, "volumetric_lighting": true } }

@Compound Learning - Tech | Science
Profile / Avatar - Vintage Portrait of Woman in Hoodie
GPT Image 2

Profile / Avatar - Vintage Portrait of Woman in Hoodie

A vintage-style portrait of a young woman standing in a traditional Japanese alleyway. She has short, curly dark brown hair and is wearing a cream-colored hooded sweatshirt with drawstrings and a plaid skirt. Her hands are raised to her head as she smiles gently at the camera. A brown leather shoulder bag hangs from her left side. The background features weathered wooden houses with tiled roofs, a utility pole, and an old bicycle leaning against a fence. The image has a nostalgic film grain texture with light leaks on the edges.

@拓斗
E-commerce Main Image - Macro Pink Beverage Photography
GPT Image 2

E-commerce Main Image - Macro Pink Beverage Photography

A photorealistic close-up of a {argument name="container" default="tall, crystal-clear cylindrical glass"} filled with a {argument name="drink color" default="vibrant translucent pink"} fruit drink and several large irregular ice cubes. Tiny bubbles and delicate foam gather naturally across the surface, with condensation and small droplets visible on the ice and glass. Soft diffused daylight illuminates the drink, creating beautiful pink reflections and realistic refractions through the ice. {argument name="background" default="Minimal clean white background with a softly blurred product/package backdrop"}, shallow depth of field, elegant beverage photography, macro details, natural highlights, realistic glass distortion, crisp focus, premium commercial photography, vertical composition, 8K, ultra-realistic

@Dua Fatima
E-commerce Main Image - LEGO Minifigure Transformation
GPT Image 2

E-commerce Main Image - LEGO Minifigure Transformation

Transform every visible person in the uploaded image into realistic LEGO-style minifigure toys while preserving each person’s recognizable identity, hairstyle, outfit, colors, accessories, relative height, pose, and relationship to each other. FORMAT LOCK — NON-NEGOTIABLE Vertical 3:4 aspect ratio. Full-body product composition. All figures must be fully visible from head to toe. Do not generate square, landscape, widescreen, close-up, cropped, or half-body compositions. PERSON COUNT LOCK — NON-NEGOTIABLE Detect all visible people in the uploaded image. If there is 1 person, create 1 LEGO-style minifigure. If there are 2 people, create 2 LEGO-style minifigures. If there are 3 or more people, create the same number of LEGO-style minifigures. Do not remove, merge, ignore, duplicate, or replace any person. Every person visible in the reference image must appear as their own separate LEGO-style minifigure. REFERENCE LOCK — NON-NEGOTIABLE Use the uploaded image as the only reference for all subjects. Preserve each person’s recognizable facial identity as much as possible within the simplified LEGO minifigure style. Maintain each person’s hairstyle and hair color, adapted into molded LEGO-style plastic hairpieces. Preserve each person’s facial expression, clothing colors, clothing design, visible patterns, accessories, and styling. The final figures must clearly represent the same people translated into LEGO-style toy form. Do not create generic minifigures. Do not redesign outfits or invent new accessories. CLOTHING DETAIL LOCK Recreate each person’s outfit as accurately as possible in LEGO minifigure form. Preserve the exact clothing color palette, layering, garment type, collar shape, neckline, sleeves, jacket shape, pants or skirt style, shoes, visible patterns, seams, buttons, zippers, belts, logos, jewelry, bags, glasses, hats, and accessories. Translate real clothing into printed LEGO torso and leg graphics with clean toy-style linework. Outerwear should appear as molded or printed LEGO-style clothing details. Shoes should be simplified into LEGO foot/leg prints while keeping the original color and style. Do not replace outfits with generic LEGO clothing. Do not simplify clothing so much that the original styling is lost. GROUP COMPOSITION Keep the same number of people from the uploaded image. Preserve the relationship between subjects. Preserve relative height differences. Preserve basic pose direction and body language. If the reference shows a couple, create a matching LEGO-style couple. If the reference shows a group, create the full group as separate minifigures. Arrange the figures naturally together in a clean product-style composition. LEGO MINIFIGURE STRUCTURE Use authentic LEGO-style minifigure proportions for every figure. Cylindrical heads. Simplified printed facial features. Block-shaped torsos. Printed clothing details on each torso. Sta

@Visual AI Club

Some prompts are collected from creators on X. Copyright belongs to the original authors.