💡 🎬 Take it further with Seedance 2 — pair GPT Image 2 stills with Seedance for jaw-dropping AI videos, 2000+ prompts to explore 👉 awesome-seedance-2-prompts
🚀 Awesome GPT Image 2 Prompts
🎨 A curated collection of creative prompts for OpenAI's GPT Image 2
⚠️ Copyright Notice: All prompts are collected from the community for educational purposes. If you believe any content infringes on your rights, please open an issue and we will remove it promptly.
🌐 View in Web Gallery
👉 Browse on YouMind GPT Image 2 Prompts Gallery
Why use our gallery?
| Feature | GitHub README | youmind.com Gallery |
|---|---|---|
| 🎨 Visual Layout | Linear list | Beautiful Masonry Grid |
| 🔍 Search | Ctrl+F only | Full-text search with filters |
| 🤖 AI One-Click Generation | - | AI one-click generation |
| 📱 Mobile | Basic | Fully responsive |
| 🏷️ Categories | - | Category browsing |
🏷️ Browse by Category
- Use Cases
- Style
- Subjects
📖 Table of Contents
- 🌐 View in Web Gallery
- 🤔 What is GPT Image 2?
- 📊 Statistics
- 🔥 Featured Prompts
- 📋 All Prompts
- 🤝 How to Contribute
- 📄 License
- 🙏 Acknowledgements
- ⭐ Star History
🤔 What is GPT Image 2?
GPT Image 2 (codename "duct-tape") is OpenAI's next-generation image model. Community testing highlights a leap in these areas:
- 🎯 Pixel-Perfect Text Rendering — Native-quality text in Chinese, English, and Japanese, no typos or warped glyphs
- 🎨 Cross-Image Consistency — The same character, style, or IP stays identical across a series, down to the pixel
- ⚡ Commercial-Grade Illustration — Illustration output is ready to ship without manual polish
- 🌈 True Art Style Induction — Creatively evokes the feeling of a style rather than merely approximating references
- 🔧 Storyboard & Product Series — Ideal for storyboards, IP characters, and multi-panel product visuals
- 📐 Multi-Language Design — Social cards, banners, and posters with accurate multilingual typography in one shot
📚 Learn More: See community testing in our report summary
🚀 Raycast Integration
Some prompts support dynamic arguments using Raycast Snippets syntax. Look for the 🚀 Raycast Friendly badge!
Example:
A quote card with "{argument name="quote" default="Stay hungry, stay foolish"}"
by {argument name="author" default="Steve Jobs"}
When used in Raycast, you can dynamically replace the arguments for quick iterations!
📊 Statistics
| Metric | Count |
|---|---|
| 📝 Total Prompts | 18120 |
| ⭐ Featured | 6 |
| 🔄 Last Updated | Tuesday, November 17, 2026 at 8:11:08 PM UTC |
🔥 Featured Prompts
⭐ Hand-picked by our team for exceptional quality and creativity
No. 1: VR Headset Exploded View Poster
📖 Description
Generates a high-tech exploded view diagram of a VR headset with detailed component callouts and promotional text.
📝 Prompt
{
"type": "exploded view product diagram poster",
"subject": "VR headset",
"style": "clean high-tech 3D render, studio lighting, glowing accents",
"background": "{argument name=\"background color\" default=\"soft purple and blue gradient\"}",
"header": {
"logo": "∞ {argument name=\"product name\" default=\"Meta Quest 3\"}",
"subtitle": "{argument name=\"main catchphrase\" default=\"まったく新しい現実を、まったく新しい構造から。\"}"
},
"layout": {
"centerpiece": "vertically stacked exploded view of a VR headset showing 9 distinct layers of internal components: outer shell, camera sensors, motherboard with chip, pancake lenses, internal frame, battery packs, side straps, top strap, and facial interface cushion.",
"callout_labels": {
"count": 8,
"left_side": [
"Snapdragon® XR2 Gen 2\n圧倒的な処理性能でリアルタイムな体験を。",
"調整可能なIPD機構\n幅広いユーザーに快適なフィット感を。",
"精密設計されたヘッドストラップ\n快適さと安定性を追求したエルゴノミクス。"
],
"right_side": [
"フェイスプレート\n洗練されたデザインと最適な重量バランス。",
"トラッキングカメラ\n高精度な位置トラッキングと環境認識を実現。",
"パンケーキレンズ\n薄型設計で広い視野角と鮮明な映像を提供。",
"高性能バッテリー\n長時間駆動を支える最適化された電源設計。",
"柔らかなフェイスインターフェース\n長時間でも快適な装着感を実現。"
]
},
"footer": {
"left_text_block": {
"headline": "{argument name=\"bottom headline\" default=\"体験は、構造から進化する。\"}",
"body": "一つひとつのパーツに、没入体験を支える最先端テクノロジーとこだわりの設計。Meta Quest 3は、未来を感じさせる体験を内部から生み出しています。"
},
"right_logo": "∞ Meta"
}
}
}
🖼️ Generated Images
Image 1
📌 Details
- Author: wory@ホッピング中
- Source: Twitter Post
- Published: April 19, 2026
- Languages: en
No. 2: Illustrated City Food Map
📖 Description
Generates a hand-drawn, watercolor-style tourist map featuring numbered local food specialties, landmarks, and a legend.
📝 Prompt
{
"type": "illustrated map infographic",
"style": "{argument name=\"art style\" default=\"watercolor and ink hand-drawn illustration on vintage parchment\"}",
"title_section": {
"text": "{argument name=\"city name\" default=\"成都\"} {argument name=\"map title\" default=\"吃货暴走地图\"}",
"mascot": "cartoon red chili pepper wearing sunglasses and giving a thumbs up"
},
"border": "{argument name=\"border decoration\" default=\"vine of green leaves and red chili peppers\"}",
"layout": {
"background": "textured beige parchment paper with yellow roads, blue rivers, and green park areas",
"sections": [
{
"title": "landmarks",
"count": 6,
"illustrations": ["traditional pavilion", "traditional monastery", "modern skyscraper with climbing panda", "tall TV tower", "traditional gate", "industrial buildings"],
"labels": ["人民公园", "文殊院", "IFS", "339电视塔", "宽窄巷子", "东郊记忆"]
},
{
"title": "food_spots",
"count": 12,
"illustrations": ["mapo tofu", "dumplings in chili oil", "skewers in pot", "sticky rice balls", "egg baking cake", "nine-grid hotpot", "sweet potato noodles", "cold skewers", "spicy mixed dish", "covered tea bowl", "ice jelly dessert", "spicy rabbit heads"],
"labels": ["1 陈麻婆豆腐", "2 钟水饺", "3 春熙路", "4 宽窄巷子·三大炮", "5 建设路·叶婆婆蛋烘糕", "6 玉林路·小龙坎火锅", "7 香香巷·肥肠粉", "8 武侯祠大街·钵钵鸡", "9 东郊记忆·冒椒火辣", "10 人民公园·鹤鸣茶社", "11 锦里古街·冰粉", "12 双流老妈兔头"]
},
{
"title": "图例",
"position": "bottom-right",
"count": 5,
"items": ["red dot", "green house", "green tree", "blue line", "yellow double line"],
"labels": ["美食地点", "地标景点", "公园绿地", "河流湖泊", "主要道路"]
}
],
"centerpiece": "giant panda sitting and eating bamboo",
"bottom_right_extras": ["vintage compass rose with N, S, E, W", "disclaimer text '温馨提示:吃辣需谨慎,肠胃要保护~' with a red chili pepper icon"]
}
}
🖼️ Generated Images
Image 1
📌 Details
- Author: 皮皮特
- Source: Twitter Post
- Published: April 19, 2026
- Languages: en
No. 3: Momotaro Explainer Slide in Hybrid Style
📖 Description
A prompt that combines the simple, warm aesthetic of Irasutoya illustrations with the high-information density characteristic of Japanese government slides.
📝 Prompt
Create an explanatory slide ({argument name="format" default="ponchi-e diagram"}) for {argument name="theme" default="Momotaro"} that fuses the gentle atmosphere of "Irasutoya" with the overwhelming information density of "Kasumigaseki slides".
🖼️ Generated Images
Image 1
Image 2
📌 Details
- Author: やまもん
- Source: Twitter Post
- Published: April 19, 2026
- Languages: ja
No. 4: E-commerce Live Stream UI Mockup
📖 Description
Generates a realistic social media live stream interface overlaying a portrait, featuring customizable chat messages, gift popups, and a product purchase card.
📝 Prompt
{
"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"]
}
}
}
🖼️ Generated Images
Image 1
📌 Details
- Author: 神经病不想好转
- Source: Twitter Post
- Published: April 19, 2026
- Languages: en
No. 5: Anime Martial Arts Battle Illustration
📖 Description
Generates a dynamic, high-impact anime illustration of two female characters fighting in a traditional dojo with elemental energy effects.
📝 Prompt
An anime-style illustration of a {argument name="action type" default="high-impact martial arts battle"} between two young female fighters in a {argument name="setting" default="traditional wooden martial arts dojo"}. In the foreground, a girl with black hair in a high bun wears a {argument name="character 1 color theme" default="red and white"} Chinese-style martial arts outfit with baggy pants. She is in a dynamic, low, forward-thrusting stance, surrounded by swirling red energy and water splashes. In the background to the right, a girl with light purple hair in twin buns wears a {argument name="character 2 color theme" default="green and purple"} Chinese dress with gold embroidery and black tights. She is leaping through the air in a flying kick pose, surrounded by swirling blue energy. The wooden floorboards are splintering from the intense impact, with debris and dust flying through the air. Above them hangs a weathered wooden sign with the text "{argument name="sign text" default="武術会"}". The scene features dramatic lighting, a low-angle dynamic perspective, and intense action effects.
🖼️ Generated Images
Image 1
📌 Details
- Author: たねもみ 2.0 / Tanemomi Ver2.0
- Source: Twitter Post
- Published: April 20, 2026
- Languages: en
No. 6: 3D Stone Staircase Evolution Infographic
📖 Description
Transforms a flat evolutionary timeline into a realistic 3D stone staircase infographic with detailed organism renders and structured side panels.
📝 Prompt
{
"type": "evolutionary timeline infographic",
"instruction": "Using REFERENCE_0 as a structural base, transform the flat vector design into a highly realistic 3D infographic. Replace the smooth ramps with distinct stone steps and upgrade all organisms to photorealistic 3D models.",
"style": {
"background": "{argument name=\"background style\" default=\"vintage textured parchment paper\"}",
"staircase": "{argument name=\"staircase material\" default=\"realistic textured stone blocks\"}",
"subjects": "{argument name=\"organism style\" default=\"highly detailed photorealistic 3D renders\"}"
},
"layout": {
"main_title": "{argument name=\"main title\" default=\"人类演化\"}",
"sections": [
{
"position": "left sidebar",
"count": 8,
"labels": ["L0: 单细胞生命", "L1: 多细胞生物", "L2: 动物界", "L3: 脊索动物", "L4: 上陆革命", "L5: 哺乳纲", "L6: 人科演化", "L7: 智人纪元"]
},
{
"position": "top right",
"title": "获得的功能 / 失去的功能",
"description": "Legend with plus and minus icons"
},
{
"position": "bottom center",
"title": "演化关键里程碑",
"count": 6,
"description": "Timeline with a silhouette graphic of 6 figures showing ape-to-human evolution"
}
],
"centerpiece": {
"description": "Winding stone staircase with 25 numbered steps featuring specific organisms.",
"count": 25,
"notable_elements": [
"Step 07: Jellyfish",
"Step 09: Ammonite",
"Step 10: Trilobite",
"Step 24: Walking human",
"Step 25: {argument name=\"future evolution concept\" default=\"glowing cosmic silhouette with a question mark\"}"
]
}
}
}
🖼️ Generated Images
Image 1
📌 Details
- Author: 知识猫图解
- Source: Twitter Post
- Published: April 19, 2026
- Languages: en
📋 All Prompts
📝 Sorted by publish date (newest first)
No. 1: Profile / Avatar - Winter Scrapbook Collage Portrait Prompt for GPT Image 2
📖 Description
A detailed prompt for generating a hyper-realistic winter scrapbook collage portrait of a female character with violet hair, cozy streetwear, and boba drink, using GPT Image 2.
📝 Prompt
Create a hyper-realistic full-body winter scrapbook collage 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 almond-shaped eyes, delicate facial features, glossy lips, and slim physique.
She is seated sideways on a cardboard box with a relaxed, cozy posture, holding a pink iced strawberry boba drink topped with whipped cream in her left hand while cuddling a cute smiling strawberry plushie with her right arm. She wears a warm cream knitted turtleneck sweater underneath an oversized light-wash denim jacket decorated with colorful floral, gingham, polka-dot, and strawberry patchwork. Matching wide-leg patchwork denim jeans and chunky white platform sneakers complete her cozy winter streetwear look.
The cardboard box features handwritten "{argument name="box text" default="FRAGILE"}" text with a heart. The background is made of crumpled blue scrapbook paper decorated with torn notebook pages, handwritten words "{argument name="background words" default="Winter", "Slow", "dream", and "Sweet"}", red gingham washi tape, paperclips, strawberry stickers, white snowflake doodles, and a cute snowman wearing a red knitted hat and scarf. Add a handwritten "{argument name="message" default="Stay Cozy"}" message.
Use soft diffused winter studio lighting, cool pastel blue tones, warm cozy details, realistic skin texture, detailed purple hair strands, knitted fabric textures, cinematic depth, subtle shadows, photorealistic quality, ultra-detailed 8K, premium winter cottagecore Y2K scrapbook fashion editorial.
🖼️ Generated Images
Image 1
📌 Details
- Author: Wareen AI 💟
- Source: Twitter Post
- Published: November 17, 2026
- Languages: en
No. 2: Profile / Avatar - GPT Image 2 Prompt: Transform Photo into 3D Toy Couple
📖 Description
A detailed prompt to convert uploaded reference photos of a couple into ultra-detailed 3D collectible vinyl figurines in a café setting, preserving facial features while applying a stylized toy aesthetic.
📝 Prompt
Transform the people in the uploaded reference photo into an ultra-detailed 3D collectible toy couple scene at a stylish outdoor café. Preserve their recognizable facial features while recreating them as premium glossy vinyl figurines with polished plastic finishes, slightly exaggerated proportions, expressive faces, and realistic toy-like details.
The female character has dark brown hair styled in an elegant braided updo, black sunglasses, delicate gold hoop earrings, layered gold necklaces, and a white puff-sleeve blouse. She rests her chin gently on one hand while gazing affectionately at her partner with a soft smile.
The male character has thick, voluminous curly dark hair, neatly groomed facial hair, black sunglasses, and a crisp white button-down shirt with rolled-up sleeves. He wears a silver wristwatch and casually holds a small white ceramic coffee cup near his lips.
Both characters are seated closely together at a polished wooden café table. Include miniature white coffee cups, matching saucers, and elegant silver teaspoons.
Environment: A charming upscale European outdoor café with warm beige stone architecture, tall glass windows, lush green trees, blue patio umbrellas, wooden furniture, and softly blurred café guests in the background. Warm afternoon sunlight creates beautiful reflections and soft shadows.
Visual Style: Premium designer vinyl toys, glossy 3D figurines, adorable yet sophisticated character design, smooth sculpted surfaces, detailed hairstyles, realistic miniature accessories, high-end collectible toy photography, cinematic depth of field, warm golden color grading, ultra-realistic 3D rendering.
Composition: Vertical 4:5 portrait framing, eye-level front-facing camera, both characters prominently occupying the foreground, natural relaxed poses, intimate café atmosphere.
Render Quality: Ultra-detailed 3D modeling, realistic glossy reflections, ray-traced lighting, ambient occlusion, global illumination, physically based materials, cinematic shadows, professional product photography, 8K-quality finish.
Important: Maintain the couple's identity and distinctive facial characteristics from the reference photo. Both people must look like beautifully crafted physical collectible toys, not ordinary human photographs. No text, no watermark, no extra foreground characters.
🖼️ Generated Images
Image 1
📌 Details
- Author: Smiling Khan
- Source: Twitter Post
- Published: November 15, 2026
- Languages: en
No. 3: Profile / Avatar - GPT Image 2 Multi-View Character Consistency Prompt
📖 Description
A prompt for generating consistent character photos using reference images for face, clothing, and pose depth maps with GPT Image 2.
📝 Prompt
Please generate an image: Photorealistic vertical 2:3 aspect ratio, a solo photo of a fictional {argument name="age" default="20-year-old"} adult woman, youthful, like a college sophomore, not looking mature. Image 1 is the face reference: keep facial features, skin tone, hairstyle, and hair color consistent. Image 2 is the clothing reference: wear this outfit exactly as shown, keeping style, color, material, and accessories consistent. Image 3 is a grayscale depth map of a human model: only use it as a reference for body pose and camera angle; it is not a real person and does not provide clothing or face details. Scene: {argument name="scene_description" default="a tree-lined path in a park on a spring afternoon"}, with fresh green leaves and benches by the road, soft natural light, iPhone casual snapshot quality, realistic skin texture, slight film grain. Single image, no collage, no text or watermarks, hands naturally relaxed with all five fingers complete, face and limbs undistorted.
Please generate another image: Refer to the previous one: same person, hairstyle, clothing, scene, and lighting completely consistent, but change the body pose and camera angle to match the pose from this depth map (the depth map is just a human model, providing no clothing or face). Vertical 2:3 single image, no collage, no text or watermarks, fingers complete.
🖼️ Generated Images
Image 1
Image 2
📌 Details
- Author: Candy
- Source: Twitter Post
- Published: November 15, 2026
- Languages: zh











