awesome-gpt-image-2
Prompt as Code | GPT Image 2 / 2.5 提示词与案例库，530+ 个案例、20+ 套工业级模板与可复用 Skills，新增 2.5 同提示词对比专区，附完整提示词与生成记录，持续更新。
原始仓库简介 · 中文摘要待补充 · agents / ai-image-generation / chatgpt / dsh-plugin / gpt-image-2 / image-prompts
README / 项目原文
Prompt as Code | GPT-Image2 Industrial Prompt Engine & Template Library, 500+ Reverse-Engineered Cases, 20+ Industrial Templates
)
GPT Image 2.5 Spotlight
Explore the 2.5 spotlight: learn about Sunburst and Flare, then explore a shared-prompt comparison with a draggable divider, side-by-side view, image enlargement, and generation settings.
- Sunburst: image generation and precise editing.
- Flare: fast, high-quality everyday image generation.
- 4 real recreations: #532 lemon campaign, #527 Rio diorama, #523 Manhattan watercolor, and #510 Bichon Shop icon. Each preserves its original gallery image and uses the full gallery prompt for one new built-in image generation, without a reference image. A case selector opens any example directly. Images, prompts and generation records. Original generation conditions and exact tool model IDs remain unverified; demonstration examples are labeled separately.
The spotlight runs independently. Existing GPT-Image2 cases, templates, Skill, and generation tools remain available. This update does not add live 2.5 image generation.
🌐 Visual Website
Use the live site at gpt-image2.canghe.ai to browse the gallery as a product experience: open large previews, copy full prompts, filter by style or scenario, test generation after Google sign-in, and jump back to the source case on GitHub.
Community 交流群
Join the GPT-Image2 discussion group to exchange prompts, workflows, and creative ideas with other users. Visit the community page to join.
Follow the WeChat official account 苍何 or scan the QR code below to receive project updates, new cases, and practical tutorials.
❤️ Sponsors
Want to appear here? Support the project through GitHub Sponsors, or search 苍何 on WeChat and send your product name plus a short sponsorship note.
| Sponsor | Description |
|---|---|
 |
Thanks to APIMart for sponsoring this project! APIMart is a low-cost API platform for AI image & video generation — GPT-Image-2 from $0.006/image, 160+ images per dollar. One async API covers both image and video: submit a task, get an ID, fetch results via polling or callback. Batch tens of thousands of images without timeouts, switch models without changing code. Pay-as-you-go with no monthly fee — sign up here to get started. |
 |
Thanks to HiAPI for sponsoring this project! HiAPI brings GPT Image 2.5 Flare and Sunburst alongside other image, video, and audio models into one API platform. Choose Flare for fast everyday creation or Sunburst for detailed generation and editing; both support 1K, 2K, and 4K outputs. Try them in the Playground before integrating. Media generation uses an async task API; each model's input parameters are documented separately. Results are delivered through HiAPI's CDN, with optional paid persistent storage when you need to keep an output long-term. Remote MCP and Agent Skills also connect HiAPI to coding agents. New users receive 200 Credits on signup; check Billing for current top-up bonuses. Sign up here. |
 |
Thanks to PackyCode for sponsoring this project! PackyCode is a stable, high-performance API relay provider for Claude Code, Codex, Gemini, and more. Automatic failover, smart routing, and unlimited concurrency help turn AI coding into a reliable productivity tool. Register here to get started. |
 |
Project sponsor. PPToken provides API relay and key distribution for ChatGPT, Claude, Gemini, and other mainstream AI models, with low-latency access, high availability, pay-as-you-go billing, and flexible subscription plans. |
 |
Thanks to Liqiu API for sponsoring this project! Liqiu API is a stable, transparent, dedicated AI API relay offering access to ChatGPT, Claude, Grok, Gemini, and more. It uses pay-as-you-go billing, with multipliers starting at 0.1x, and emphasizes reliable service with around-the-clock maintenance for developers. Register here to get started. |
 |
One gateway to access and manage the world's leading AI models Sidrune AI serves individual developers, engineering teams, and enterprises with a unified API for accessing and managing the world's leading AI models. Multi-route dynamic scheduling improves availability, while model performance, response time, and cost remain transparent and verifiable. Depending on the model and route, API call costs can be 40%–98% lower than official or baseline prices. Visit and register now to receive $3 in API credits. |
⚡️ Project Vision
After GPT-Image2 became widely available, AI image generation moved from "can it make an image?" to "can it make stable, controllable, reusable images?" This project turns scattered community examples into Prompt-as-Code assets that are easier for agents and automation workflows to reuse.
The core goal is simple: compress prose-style prompts into structured protocols. When you need batch generation, template systems, or production workflows, this structure is more valuable than a pile of isolated examples.
- 🧱 Atomic schema: split subjects, lighting, materials, layout, and visual details into composable parts
- ⚙️ Workflow friendly: designed for agents, scripts, and automation systems
- 🧬 Structured control: improve controllability for layout, copy, and information hierarchy
📖 Quick Links
- Full case gallery
- Gallery Part 1: cases 1-165
- Gallery Part 2: cases 166-544
- Industrial prompt templates and pitfalls guide
- Agent skill: GPT-Image2 Style Library
- MIT License
- Full disclaimer
🗂️ Category Overview
Start with the case album to find a visual direction, then open the prompt template categories to turn that direction into reusable structure.
🖼️ Case Album
|
🧩 UI & Interfaces  Apps, websites, dashboards, social screenshots, and product interfaces. View Cases |
📊 Charts & Infographics  Infographics, knowledge maps, technical explainers, and structured diagrams. View Cases |
📰 Posters & Typography  Event posters, covers, type-driven visuals, and strong layout compositions. View Cases |
|
🛍️ Products & E-commerce  Product shots, detail pages, packaging, selling points, and ads. View Cases |
🏷️ Brand & Logos  Logos, identity systems, brand touchpoints, and campaign visuals. View Cases |
🏛️ Architecture & Spaces  Architecture renders, interiors, city maps, and spatial concepts. View Cases |
|
📷 Photography & Realism  Portraits, phone photography, film texture, and commercial photography. View Cases |
🎨 Illustration & Art  Illustration, art styles, material experiments, and decorative images. View Cases |
🧍 Characters & People  Character design, pose references, cards, and 3D toys. View Cases |
|
🎬 Scenes & Storytelling  Storyboards, narrative scenes, livestream frames, and worldbuilding. View Cases |
🏮 History & Classical Chinese Themes  Classical scrolls, historical figures, traditional themes, and poetry visuals. View Cases |
📚 Documents & Publishing  White papers, manuals, encyclopedic plates, and publishing layouts. View Cases |
|
🧪 Other Use Cases  Creative experiments, special tasks, mixed workflows, and practical cases. View Cases |
🖼️ Full Gallery Browse all 544 cases by gallery part and category. Open Gallery |
⭐ Latest Additions The newest community cases and workflows collected in the repo. View Latest |
🧩 Prompt Template Categories
The prompt body remains in the original template document for now. This homepage only adds an English navigation layer.
Template Page 1 / 4: Design & Information
| Category | Template Entry | Core Capability |
|---|---|---|
| 🧩 UI & Interfaces | View Prompts | Components, page hierarchy, screenshot texture |
| 📊 Charts & Infographics | View Prompts | Modules, arrows, data structure, readability |
| 📰 Posters & Typography | View Prompts | Layout, headline systems, people, visual impact |
Template Page 2 / 4: Commerce & Space
| Category | Template Entry | Core Capability |
|---|---|---|
| 🛍️ Products & E-commerce | View Prompts | Product selling points, packaging, detail-page structure |
| 🏷️ Brand & Logos | View Prompts | Logos, identity, brand touchpoint systems |
| 🏛️ Architecture & Spaces | View Prompts | Perspective, materials, indoor and outdoor lighting |
Template Page 3 / 4: Imaging & Characters
| Category | Template Entry | Core Capability |
|---|---|---|
| 📷 Photography & Realism | View Prompts | Lenses, lighting, realistic textures |
| 🎨 Illustration & Art | View Prompts | Brushwork, materials, art styles |
| 🧍 Characters & People | View Prompts | Character design, pose sheets, consistency |
Template Page 4 / 4: Narrative & Extensions
| Category | Template Entry | Core Capability |
|---|---|---|
| 🎬 Scenes & Storytelling | View Prompts | Storyboards, worldbuilding, emotional pacing |
| 🏮 History & Classical Chinese Themes | View Prompts | Dynasties, clothing, scroll-style narrative |
| 📚 Documents & Publishing | View Prompts | Page systems, tables of contents, layout rules |
| 🧪 Other Use Cases | View Prompts | Mixed tasks, experimental workflows, special outputs |
🤖 Agent Skill
This repository includes an agent skill for choosing GPT-Image2 styles, templates, categories, and scene tags from the same data used by the website.
Package links: npm / GitHub Packages
Example output from a city-life-system-map request using the style library skill.
Quick Install for Agent Skills
Recommended for Claude Code, Codex, Cursor, and other tools supported by skills:
npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library --agent claude-code codex --global --yes --copy
Install to every supported local agent:
npx skills add freestylefly/awesome-gpt-image-2 --global --all --copy
Claude Code Plugin Marketplace
Run these commands inside Claude Code:
/plugin marketplace add freestylefly/awesome-gpt-image-2
/plugin install gpt-image-2-style-library@awesome-gpt-image-2
npm CLI
If you prefer npm, install the CLI and then sync the skill into local agent folders:
npm install -g gpt-image-2-style-library
gpt-image-2-style-library install all
You can also run it without a global install:
npx gpt-image-2-style-library install all
Install from GitHub Packages:
npm login --scope=@freestylefly --registry=https://npm.pkg.github.com
npm install -g @freestylefly/gpt-image-2-style-library --registry=https://npm.pkg.github.com
gpt-image-2-style-library install all
install all writes the skill to the common local folders used by Codex and Claude Code, including ~/.codex/skills, ~/.claude/skills, and ~/.agents/skills. Restart the agent session after installing.
Use it with a request like:
Use gpt-image-2-style-library to create an infographic prompt about Codex.
For local source development:
npm run generate:style-skill
npm run install:skill
The skill source lives at agents/skills/gpt-image-2-style-library. Its generated reference comes from data/style-library.json, so the website and Agent workflow share one style library.
🔐 Website Auth & Generation
The visual site supports direct APIMart generation with a personal browser-only API key. Without a personal key, signed-in users continue through Supabase Auth, platform credits, and the server-side APIMart key.
Required Vercel environment variables:
VITE_SUPABASE_URL=
VITE_SUPABASE_ANON_KEY=
SUPABASE_SERVICE_ROLE_KEY=
SUPER_ADMIN_EMAILS=2689458656@qq.com,canghe0818@gmail.com
APIMART_API_KEY=
APP_URL=https://gpt-image2.canghe.ai
STRIPE_SECRET_KEY=
STRIPE_WEBHOOK_SECRET=
VITE_GA_MEASUREMENT_ID=
GA4_PROPERTY_ID=
GOOGLE_ANALYTICS_CLIENT_ID=
GOOGLE_ANALYTICS_CLIENT_SECRET=
GOOGLE_ANALYTICS_REFRESH_TOKEN=
Setup checklist:
- Apply
supabase/migrations/202605090001_user_credits.sqlto the Supabase project. - Apply
supabase/migrations/20260509090000_membership_billing.sqlto add membership plans, credit packs, Stripe order records, and credit adjustment RPCs. - Apply
supabase/migrations/20260721090000_alipay_webpay.sqlbefore enabling Alipay website payments, then configure each credit pack's reviewed CNY price. See Alipay website payment setup. - Apply
supabase/migrations/20260722090000_paid_community.sqlbefore enabling the paid community. KeepCOMMUNITY_PAYMENT_ENABLED=falseuntil the protected QR, Alipay onboarding, and production payment/refund checks are complete. See the paid community runbook. - Apply
supabase/migrations/20260512090000_google_account_center.sqlto add account usage summaries and forced credit charging for super admins. - Apply
supabase/migrations/20260512143000_pricing_admin_metrics.sqlto update the$5 / 300 creditscatalog and add admin dashboard metrics. - Apply
supabase/migrations/20260515090000_case_favorites.sqlto add per-user case favorites. - Apply
supabase/migrations/20260828090000_apimart_generation_tasks.sqlto add APIMart task IDs, actual USD costs, expiring result URLs, and provider indexes. - Add
https://gpt-image2.canghe.aiand local dev URLs such ashttp://127.0.0.1:5173to Supabase Auth redirect URLs. - Enable the Google Provider after adding Google OAuth credentials in the Supabase Dashboard.
- To force Google-only sign-in, disable the Email Provider in Supabase Auth settings.
- Keep
SUPABASE_SERVICE_ROLE_KEYonly in server-side environments such as Vercel Environment Variables. - Configure Stripe Checkout with the webhook URL
https://gpt-image2.canghe.ai/api/billing/webhook. - Subscribe the Stripe webhook to
checkout.session.completed,invoice.payment_succeeded,customer.subscription.updated, andcustomer.subscription.deleted. - Keep
STRIPE_SECRET_KEYandSTRIPE_WEBHOOK_SECRETonly in server-side Vercel Environment Variables. - Create a GA4 property for
gpt-image2.canghe.ai, add the measurement ID toVITE_GA_MEASUREMENT_ID, and copy the numeric property ID toGA4_PROPERTY_ID. - Create a Google OAuth Web Client with
http://localhost:8080/oauth2callbackas an authorized redirect URI, then addGOOGLE_ANALYTICS_CLIENT_IDandGOOGLE_ANALYTICS_CLIENT_SECRETto local.env.local. - Run
npm run ga4:oauth, open the generated URL, approve theanalytics.readonlypermission, paste the callback URL into the terminal, then add the returnedGOOGLE_ANALYTICS_REFRESH_TOKENto Vercel as a Sensitive environment variable.
🖼️ Featured Cases
Case 1: Infographic Visualization
An engineering-whitepaper-style infographic case for studying modular structure, information hierarchy, and bilingual labels. View full case
Case 2: Social Media Interface Screenshot
A mixed "product interface + social content screenshot" case for controlling text blocks, UI frames, and content cards. View full case
Case 6: Illustration Art
A Japanese fantasy illustration example for studying atmosphere, color, and large-scene composition. View full case
Case 17: Interaction Design Diagram
A classic "structured breakdown + explanatory layout" case for product diagrams and poster-like technical explainers. View full case
Case 166: Twelve Gold Saints Card Set
A multi-card, unified-style case for studying batch generation and series design. View full case
Case 310: Snack Brand Technical Breakdown
A strong hybrid of brand narrative, structural breakdown, and commercial presentation. Useful as an "infographic + brand visual" reference. View full case
Canghe Original Tests
|
Case 330: Moonlit Livestream Scene A high-fidelity livestream screenshot reference for UI atmosphere, comments, and realistic people. View Case |
Case 334: RAG Technical Explainer A reference for technical concepts, process arrows, and Chinese explanation modules. View Case |
Case 338: Red Cliff Classical Scroll A complete example of scroll format, classical Chinese narrative, and full-text layout. View Case |
|
Case 331: Hand-Drawn Xi'an Watercolor Map  A lightweight reference for city maps, hand-drawn routes, and landmark labels. View Case |
Case 332: Tea Pi Product Poster  A beverage product image combining Chinese selling points and a clean commercial poster style. View Case |
Case 339: Apple-Style Nature Science Poster  Minimal studio photography, a natural subject, and science-poster information layout. View Case |
Latest Community Additions
Only the latest collection and import run is shown here. Older imports stay in the full gallery.
|
Case 539: Raw Sketchy Portrait Poster  A customizable rough-ink portrait poster prompt combining an oversized subject, close companion, minimal scenery, restrained palette, and intentionally imperfect print texture. View Case |
Case 540: Dreamlike Futuristic World Poster  A vertical editorial art-poster prompt for surreal future cities with sculptural architecture, oversized plants, tiny people, vintage travel texture, and luxury pacing. View Case |
Case 541: 50/50 Mixed-Media Memory Card  A reference-photo editing prompt that keeps the top photo intact and converts the lower half into a handmade paper memory card with wax-crayon sketching. View Case |
|
Case 542: Black-and-White Typographic Portrait Poster  A high-contrast monochrome typographic portrait prompt that fuses side-profile silhouettes, rough ink texture, microtext, and a large readable text block. View Case |
Case 543: Travel Souvenir Enamel Pin Badge  A product-design prompt that turns a travel photo into a glossy enamel pin badge with gold dividers, scene hierarchy, simplified figure rules, and fabric backdrop. View Case |
Case 544: Preschool Vocabulary Learning Card A preschool learning-card prompt for clean object-and-part vocabulary layouts with realistic produce, dotted arrows, simple illustration, and clear labels. View Case |
🧩 Template Entry
The full template library lives in docs/templates.md. Use the Prompt Template Categories above for quick category jumps, or open Industrial prompt templates and pitfalls guide for the complete template text.
🚀 How To Use This Repository
- Start from the featured cases and decide what output type you want to imitate.
- Open the full gallery and find nearby cases. Copy structure first, then style words.
- Return to the template page and fill your business variables into the general or JSON templates.
📄 Notes & Disclaimer
Acknowledgements & Sources
During collection and research, this project references public prompt-library content from YouMind and OpenNana for learning, summarization, and methodology research. Copyright belongs to the original authors or platforms. If any content is infringing or inappropriate, please contact us and we will correct or remove it promptly.
Disclaimer
This project only organizes publicly accessible community prompts and example images for learning and research. It does not claim ownership of any third-party original content.
All prompt cases and generated images in this repository were initially inspired by public community sources, especially YouMind and OpenNana. The project aims to break down strong examples into reusable structured protocols for learning, summarization, and automated testing with large-model agents.
- We make every effort to preserve original sources, including author profiles, original post links, and source repository links.
- For third-party content, we follow source repository statements, licenses such as
CC BY 4.0, and the relevant platform rules. - If you are the original author or rights holder and believe an entry should not be displayed, please open an Issue with the entry link. We will review it and remove it quickly when appropriate.
- This repository does not guarantee that third-party content can be used commercially. Please obtain authorization from the original rights holder before commercial use.
If this library helps you, please star the repository.
Star History
📜 License
This project is open source under the MIT License. You can use, modify, distribute, and build on it freely while preserving the license notice.
Prompt as Code | GPT-Image2 工业级提示词引擎与模板库，500+ 个案例逆向工程，20+ 套工业级模板
GPT Image 2.5 专区
进入 2.5 专区：先了解 Sunburst 与 Flare，再通过共享 Prompt、滑动 / 并排对照、原图放大和参数说明体验新旧模型的对比方式。
- Sunburst：面向精细图片生成与编辑。
- Flare：面向快速、高质量的日常图片生成。
- 已加入 4 组真实案例复现：532 柠檬广告、527 里约纸雕、523 曼哈顿水彩、510 Bichon Shop 图标。每组保留图库原图，复用站内完整提示词，通过内置生图生成一次新结果，不输入参考图；可用案例下拉框直接切换。查看图片、提示词与生成记录。原图生成条件与工具具体模型 ID 未核验，其他示意案例继续单独标注。
专区独立运行；原有 GPT-Image2 案例、模板、Skill 和在线生成入口继续保留。本次更新未接入 2.5 在线生图。
🌐 可视化网站
访问 gpt-image2.canghe.ai 可以用产品化方式浏览案例：查看大图、复制完整 Prompt、按风格或场景筛选、配置个人 APIMart Key 或登录后测试生成，并快速跳回 GitHub 源案例。
交流群
欢迎加入 GPT-Image2 交流群，与其他用户分享提示词、创作方法和使用经验。点击交流群链接查看加入方式。
关注微信公众号 苍何 或扫描下方二维码，及时获取项目更新、最新案例与实用教程。
❤️ 赞助方
想出现在这里？ 可以通过 GitHub Sponsors 支持项目，也可以在微信搜索苍何并发送产品名与简短赞助说明。
| 赞助方 | 说明 |
|---|---|
|
感谢 APIMart 赞助了本项目！APIMart 是专注 AI 图片/视频生成的低价 API 平台，GPT-Image-2 低至 $0.006/张，1 美元可出图 160+ 张。图片、视频一套异步 API 通吃，提交任务拿 ID、回调取结果，跑批万张不超时、换模型不改代码。按量付费、无月费，通过此注册链接注册即可开用。 |
|
感谢 HiAPI 赞助本项目！HiAPI 在一个 API 平台提供 GPT Image 2.5 Flare、Sunburst 等图片、视频和音频模型。Flare 适合日常快速创作，Sunburst 适合更精细的生成和编辑；两者支持 1K、2K、4K 输出，也可以先在 Playground 试用。媒体生成使用异步任务 API，具体输入参数按各模型文档填写。生成结果通过 HiAPI CDN 交付；需要长期保留时，可选择付费持久存储。Remote MCP 和 Agent Skills 也支持将 HiAPI 接入 AI 编程工具。新用户注册赠送 200 Credits，充值赠送档位请以 Billing 页面当前显示为准。通过此注册链接开始使用。 |
|
感谢 PackyCode 赞助本项目！PackyCode 是一家稳定、高效的 API 中转服务商，提供 Claude Code、Codex、Gemini 等多种中转服务，具备自动故障转移、智能路由和无限并发等功能，帮助 AI 编程提升生产效率。通过此注册链接即可开始使用。 |
|
项目赞助方。PPToken 提供 ChatGPT、Claude、Gemini 等主流 AI 模型的 API 中转和 Key 分发能力，支持低延迟、高可用、按量付费和灵活订阅。 |
|
感谢立秋 API 赞助本项目！自古逢秋悲寂寥，我言秋日胜春朝。立秋 API 是一家稳定、透明、纯血的 AI 中转站，提供 ChatGPT、Claude、Grok、Gemini 等 AI 中转服务，按量付费，倍率低至 0.1x 起。大家都炸我不炸，凌晨依然在线维护，欢迎各位开发者注册使用。 |
|
一个入口，接入并管理全球主流AI模型 Sidrune AI面向个人开发者、技术团队与企业，通过统一API接入并管理全球主流AI模型；通过多线路动态调度提升可用性，模型表现、响应时间与费用透明可查。根据不同模型与线路，API调用成本较官方或基准价格可降低40%—98%。 立即访问并注册，即可获得 $3 API 额度。 |
⚡️ 项目愿景
GPT-Image2 全量开放后，AI 画图从“能不能出图”变成了“能不能稳定、可控、可复用地出图”。这个项目关注的是把零散案例逆向整理成一套更适合 Agent 和自动化工作流调用的 Prompt-as-Code 资产，而非单纯堆提示词。
核心目标只有一个：把“散文式提示词”压缩成“结构化协议”。当你需要批量出图、做模板系统、接进生产流程时，这种整理方式比单纯堆案例更有价值。
- 🧱 原子化 Schema：把主体、光影、材质、排版等视觉要素拆成可组合组件
- ⚙️ 工作流友好：面向 Agent、脚本和自动化系统，而不是只给人肉复制
- 🧬 结构化控制：尽量提高版式、文案、信息层级的可控性
📖 快速入口
- 完整案例总览
- 案例画廊 Part 1：例 1-165
- 案例画廊 Part 2：例 166-544
- 工业级提示词模板与防坑指南
- Agent Skill：GPT-Image2 风格库
- MIT License
- 完整声明页
🗂️ 分类概览
先看案例画册，快速找到你想参考的视觉类型；再看提示词模板，把对应类型拆成可复用结构。
🖼️ 案例分类画册
|
🧩 UI与界面 App、网页、仪表盘、社媒截图与产品界面。 查看案例 |
📊 图表与信息可视化 信息图、知识图谱、技术解释与结构化图解。 查看案例 |
📰 海报与排版 活动海报、封面、字体视觉和强排版画面。 查看案例 |
|
🛍️ 商品与电商 商品图、详情页、包装卖点和商业广告。 查看案例 |
🏷️ 品牌与标志 Logo、VI、品牌触点和 Campaign 视觉系统。 查看案例 |
🏛️ 建筑与空间 建筑表现、室内空间、城市地图和空间概念。 查看案例 |
|
📷 摄影与写实 人像、手机纪实、胶片质感和商业摄影。 查看案例 |
🎨 插画与艺术 插画、艺术风格、材质实验和装饰画面。 查看案例 |
🧍 人物与角色 角色设定、动作参考、卡牌和 3D 玩具。 查看案例 |
|
🎬 场景与叙事 分镜、故事场景、直播画面和世界观叙事。 查看案例 |
🏮 历史与古风题材 古风长卷、历史人物、传统题材和诗词画面。 查看案例 |
📚 文档与出版物 白皮书、手册、百科图鉴和出版页设计。 查看案例 |
|
🧪 其他应用场景 创意实验、特殊任务、混合玩法和实用场景。 查看案例 |
🖼️ 完整画廊按分册浏览全部 544 个案例和代表案例入口。 进入画廊 |
⭐ 最新新增最近收录的 X 社区案例和新玩法。 查看最新 |
🧩 提示词模板分类
模板 Page 1 / 4：设计与信息
| 分类 | 模板入口 | 核心能力 |
|---|---|---|
| 🧩 UI与界面 | 查看提示词 | 组件、页面层级、截图质感 |
| 📊 图表与信息可视化 | 查看提示词 | 模块、箭头、数据结构、可读性 |
| 📰 海报与排版 | 查看提示词 | 版式、标题、人物和视觉冲击 |
模板 Page 2 / 4：商业与空间
| 分类 | 模板入口 | 核心能力 |
|---|---|---|
| 🛍️ 商品与电商 | 查看提示词 | 产品卖点、包装、详情页结构 |
| 🏷️ 品牌与标志 | 查看提示词 | Logo、品牌身份、触点系统 |
| 🏛️ 建筑与空间 | 查看提示词 | 透视、材质、室内外光线 |
模板 Page 3 / 4：影像与角色
| 分类 | 模板入口 | 核心能力 |
|---|---|---|
| 📷 摄影与写实 | 查看提示词 | 镜头、光线、真实纹理 |
| 🎨 插画与艺术 | 查看提示词 | 笔触、材质、艺术风格 |
| 🧍 人物与角色 | 查看提示词 | 人设、动作表、角色一致性 |
模板 Page 4 / 4：叙事与扩展
| 分类 | 模板入口 | 核心能力 |
|---|---|---|
| 🎬 场景与叙事 | 查看提示词 | 分镜、世界观、情绪铺陈 |
| 🏮 历史与古风题材 | 查看提示词 | 朝代、服饰、长卷叙事 |
| 📚 文档与出版物 | 查看提示词 | 页面系统、目录、版面规范 |
| 🧪 其他应用场景 | 查看提示词 | 混合任务、实验玩法、特殊输出 |
🤖 Agent Skill
仓库内提供了 agent skill，用同一份风格库数据为 Claude Code、Codex 等 Agent 选择 GPT-Image2 模板、分类、风格和场景标签。
包地址：npm / GitHub Packages
示例：用 gpt-image-2-style-library 生成“城市生命系统图谱”。
Agent 一键安装
推荐给 Claude Code、Codex、Cursor，以及其他 skills 支持的本地 Agent：
npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library --agent claude-code codex --global --yes --copy
安装到所有支持的本地 Agent：
npx skills add freestylefly/awesome-gpt-image-2 --global --all --copy
Claude Code 插件市场
在 Claude Code 中运行：
/plugin marketplace add freestylefly/awesome-gpt-image-2
/plugin install gpt-image-2-style-library@awesome-gpt-image-2
npm CLI
如果你习惯 npm，可以先安装 CLI，再同步到本地 Agent 技能目录：
npm install -g gpt-image-2-style-library
gpt-image-2-style-library install all
也可以不全局安装，直接运行：
npx gpt-image-2-style-library install all
从 GitHub Packages 安装：
npm login --scope=@freestylefly --registry=https://npm.pkg.github.com
npm install -g @freestylefly/gpt-image-2-style-library --registry=https://npm.pkg.github.com
gpt-image-2-style-library install all
install all 会写入 Codex 和 Claude Code 常用的本地技能目录，包括 ~/.codex/skills、~/.claude/skills、~/.agents/skills。安装后重启 Agent 会话。
这样调用：
使用 gpt-image-2-style-library 技能，帮我生成介绍 Codex 的信息图
本地源码开发时使用：
npm run generate:style-skill
npm run install:skill
skill 源码位于 agents/skills/gpt-image-2-style-library。生成索引来自 data/style-library.json，网站和 Agent 工作流共用这一份风格库。
🔐 网站登录与生成测试
可视化网站支持使用仅保存在当前浏览器的个人 APIMart Key 直接生成。没有配置个人 Key 时，登录用户继续使用 Supabase Auth、平台积分和服务端 APIMart Key。
Vercel 需要配置这些环境变量：
VITE_SUPABASE_URL=
VITE_SUPABASE_ANON_KEY=
SUPABASE_SERVICE_ROLE_KEY=
SUPER_ADMIN_EMAILS=2689458656@qq.com,canghe0818@gmail.com
APIMART_API_KEY=
APP_URL=https://gpt-image2.canghe.ai
STRIPE_SECRET_KEY=
STRIPE_WEBHOOK_SECRET=
VITE_GA_MEASUREMENT_ID=
GA4_PROPERTY_ID=
GOOGLE_ANALYTICS_CLIENT_ID=
GOOGLE_ANALYTICS_CLIENT_SECRET=
GOOGLE_ANALYTICS_REFRESH_TOKEN=
配置清单：
- 将
supabase/migrations/202605090001_user_credits.sql应用到 Supabase 项目。 - 将
supabase/migrations/20260509090000_membership_billing.sql应用到 Supabase 项目，添加会员套餐、积分包、Stripe 订单记录和积分调整 RPC。 - 启用支付宝网站支付前，应用
supabase/migrations/20260721090000_alipay_webpay.sql，并为需要销售的积分包配置经业务确认的人民币价格。详见支付宝网站支付接入说明。 - 启用付费交流群前，应用
supabase/migrations/20260722090000_paid_community.sql。在新群码、支付宝签约和生产付款退款验收完成前，保持COMMUNITY_PAYMENT_ENABLED=false。详见付费交流群上线手册。 - 将
supabase/migrations/20260512090000_google_account_center.sql应用到 Supabase 项目，添加账户用量统计和超级管理员强制扣积分逻辑。 - 将
supabase/migrations/20260512143000_pricing_admin_metrics.sql应用到 Supabase 项目，更新$5 / 300 credits价格体系，并添加管理员数据看板指标。 - 将
supabase/migrations/20260515090000_case_favorites.sql应用到 Supabase 项目，添加用户案例收藏表。 - 将
supabase/migrations/20260828090000_apimart_generation_tasks.sql应用到 Supabase 项目，保存 APIMart 任务 ID、实际美元成本、限时结果地址和服务商索引。 - 在 Supabase Auth Redirect URLs 里加入
https://gpt-image2.canghe.ai，以及http://127.0.0.1:5173等本地开发地址。 - 在 Supabase Dashboard 填入 Google OAuth 凭据并启用 Google Provider。
- 如需强制只允许 Google 登录，可以在 Supabase Auth settings 里关闭 Email Provider。
SUPABASE_SERVICE_ROLE_KEY只放在 Vercel Environment Variables 这类服务端环境里。- 配置 Stripe Checkout Webhook：
https://gpt-image2.canghe.ai/api/billing/webhook。 - Stripe Webhook 订阅
checkout.session.completed、invoice.payment_succeeded、customer.subscription.updated、customer.subscription.deleted。 STRIPE_SECRET_KEY和STRIPE_WEBHOOK_SECRET只放在 Vercel Environment Variables 这类服务端环境里。- 为
gpt-image2.canghe.ai创建 GA4 property，把 measurement ID 填到VITE_GA_MEASUREMENT_ID，把数字版 property ID 填到GA4_PROPERTY_ID。 - 创建 Google OAuth Web Client，Authorized redirect URI 填
http://localhost:8080/oauth2callback，然后把GOOGLE_ANALYTICS_CLIENT_ID和GOOGLE_ANALYTICS_CLIENT_SECRET写入本地.env.local。 - 运行
npm run ga4:oauth，打开脚本生成的授权链接，同意analytics.readonly权限，把回跳 URL 粘贴回终端，再把得到的GOOGLE_ANALYTICS_REFRESH_TOKEN作为 Sensitive 环境变量加到 Vercel。
🖼️ 首页精选
例 1：信息图可视化设计
工程白皮书气质的信息图案例，适合看结构化信息图如何组织模块、层级和双语标签。 查看完整案例
例 2：社媒界面截图
偏“产品界面 + 社媒内容截图”的混合场景，适合看文字区域、UI 框架和内容卡片的控制方式。 查看完整案例
例 6：插画艺术创作图
日系奇幻插画范例，适合观察氛围、色彩和大场景构图的描述方式。 查看完整案例
例 17：界面交互设计图
典型的“结构分解图 + 说明排版”场景，适合做产品示意图、海报化技术讲解图。 查看完整案例
例 166：十二黄金圣斗士卡牌合集
多卡面、多元素统一风格的案例，适合参考批量生成与系列化设计。 查看完整案例
例 310：零食品牌技术分解图
品牌叙事、分解结构和商业化呈现结合得比较完整，适合作为“信息图 + 品牌视觉”混合参考。 查看完整案例
苍何新增实测
|
例 330：月下美女直播画面 高仿直播截图，适合参考界面氛围、弹幕和人物写实结合。 查看案例 |
例 334：RAG 技术详解图 技术概念、流程箭头和中文说明模块的结构参考。 查看案例 |
例 338：《赤壁怀古》长卷图 长卷尺寸、古风叙事和整篇文字排版结合完整。 查看案例 |
|
例 331：西安手绘水彩城市地图 城市地图、手绘路线和地标标注的轻量参考。 查看案例 |
例 332：茶π产品宣传海报 饮品商品图、中文卖点和清爽商业海报组合。 查看案例 |
例 339：Apple 风格自然科普海报 极简棚拍、自然主体和科普信息排版。 查看案例 |
近 24 小时 X 社区新增
|
例 539：粗粝手绘搭档肖像海报 粗粝墨线人物海报，组合半身主体、近景搭档、极简背景、受控配色和纸张印刷质感。 查看案例 |
例 540：梦幻未来城市编辑艺术海报 竖版编辑艺术海报，组织未来城市、雕塑建筑、巨型植物、小人物、复古旅行海报质感。 查看案例 |
例 541：50/50 混合媒介回忆卡 把参考照片做成上下 50/50 回忆卡，上半区保留照片，下半区转为手工纸与蜡笔线稿。 查看案例 |
|
例 542：黑白排版侧脸肖像海报 黑白高反差排版肖像，控制侧脸剪影、粗糙墨迹、小字信息和大号可读标题块。 查看案例 |
例 543：旅行纪念珐琅徽章 把旅行照片转成场景型珐琅徽章，控制金色分隔线、人物比例、光泽和深色布纹背景。 查看案例 |
例 544：幼儿词汇拆解学习卡 幼儿词汇学习卡，控制大物体、局部拆解、虚线箭头、简笔提示和清晰英文标签。 查看案例 |
🧩 模板入口
完整模板已移到 docs/templates.md。如果你想按分类快速跳转，直接使用上方的 提示词模板分类；如果想看完整模板正文，进入 工业级提示词模板与防坑指南。
🚀 怎么用这个库
- 先在精选案例里确定你要模仿的输出类型。
- 再去完整画廊里找相近案例，抄结构，不要只抄风格词。
- 最后回到模板页，把你的业务变量填进通用模板或 JSON 模板。
📄 声明与补充
致谢与来源说明
本项目在整理与研究过程中，参考并使用了 YouMind 与 OpenNana 的公开提示词库内容，仅用于学习、归纳与方法论研究。相关内容版权归原作者或原平台所有，如有侵权或不当使用请联系处理，我们将第一时间修正或下线。
声明 (Disclaimer)
本项目仅整理公开可访问的社区提示词与示例图片，默认用于学习与研究，不主张对第三方原创内容的任何所有权。
本项目里的所有提示词案例和生成的图片，最初的灵感和数据来源均来自公开社区，特别是 YouMind 与 OpenNana。我们做这个项目，主要是想把好看的案例拆解成可复用的结构化协议，用于学习、归纳和大模型 Agent 接入的自动化测试。
- 我们尽最大努力保留原始来源，包括作者主页、原帖链接与原仓库链接。
- 涉及第三方内容时，遵循来源仓库声明、
CC BY 4.0等许可及对应平台规则。 - 若你是原作者或权利人，认为某条内容不应展示，请在本仓库发起 Issue 并附上条目链接，我们将在核验后快速下架。
- 本仓库不保证第三方内容可用于商业用途；商业使用前请自行取得原权利方授权。
如果你觉得这个库帮到了你，请点亮右上角的 Star ⭐。
Star 趋势图
📜 开源协议
本项目采用 MIT License 开源。你可以在保留许可声明的前提下自由使用、修改、分发与二次开发。