GPT-Image2 Prompt System

Prompt as Code | GPT-Image2 Industrial Prompt Engine & Template Library, 400+ Reverse-Engineered Cases, 20+ Industrial Templates

Stars Forks Cases Original

English | ็ฎ€ไฝ“ไธญๆ–‡

> Updated irregularly with new workflows. Stars are welcome. > This project is sponsored by [Ciyuan API](https://ciyuan.today/), an AI aggregation platform for cost-effective GPT Image 2 access. ## ๐ŸŒ Visual Website Use the live site at [gpt-image2.canghe.ai](https://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.

GPT-Image2 Gallery website preview

## WeChat Official Account Search **่‹ไฝ•** on WeChat or scan the QR card below. To join the GPT-Image2 community group, follow the account and reply with **gpt-image-2ไบคๆต็พค**.

Canghe WeChat community QR card

## โšก๏ธ 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. - ๐Ÿงฑ Atomic schema: split subjects, lighting, materials, layout, and visual details into composable parts - โš™๏ธ Workflow friendly: designed for agents, scripts, and automation systems - ๐Ÿงฌ Structured control: improve controllability for layout, copy, and information hierarchy ## ๐Ÿ“– Quick Links - [Full case gallery](docs/gallery.md) - [Gallery Part 1: cases 1-165](docs/gallery-part-1.md) - [Gallery Part 2: cases 166-456](docs/gallery-part-2.md) - [Industrial prompt templates and pitfalls guide](docs/templates.md) - [Agent skill: GPT-Image2 Style Library](agents/skills/gpt-image-2-style-library/SKILL.md) - [MIT License](LICENSE) - [Full disclaimer](docs/disclaimer.md#section-disclaimer) ## ๐Ÿ—‚๏ธ 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. ### ๐Ÿ–ผ๏ธ Case Album

๐Ÿงฉ UI & Interfaces
73 cases

UI and interfaces
Apps, websites, dashboards, social screenshots, and product interfaces.
View Cases

๐Ÿ“Š Charts & Infographics
48 cases

Charts and infographics
Infographics, knowledge maps, technical explainers, and structured diagrams.
View Cases

๐Ÿ“ฐ Posters & Typography
71 cases

Posters and typography
Event posters, covers, type-driven visuals, and strong layout compositions.
View Cases

๐Ÿ›๏ธ Products & E-commerce
34 cases

Products and e-commerce
Product shots, detail pages, packaging, selling points, and ads.
View Cases

๐Ÿท๏ธ Brand & Logos
22 cases

Brand and logos
Logos, identity systems, brand touchpoints, and campaign visuals.
View Cases

๐Ÿ›๏ธ Architecture & Spaces
11 cases

Architecture and spaces
Architecture renders, interiors, city maps, and spatial concepts.
View Cases

๐Ÿ“ท Photography & Realism
57 cases

Photography and realism
Portraits, phone photography, film texture, and commercial photography.
View Cases

๐ŸŽจ Illustration & Art
45 cases

Illustration and art
Illustration, art styles, material experiments, and decorative images.
View Cases

๐Ÿง Characters & People
21 cases

Characters and people
Character design, pose references, cards, and 3D toys.
View Cases

๐ŸŽฌ Scenes & Storytelling
17 cases

Scenes and storytelling
Storyboards, narrative scenes, livestream frames, and worldbuilding.
View Cases

๐Ÿฎ History & Classical Chinese Themes
16 cases

History and classical Chinese themes
Classical scrolls, historical figures, traditional themes, and poetry visuals.
View Cases

๐Ÿ“š Documents & Publishing
10 cases

Documents and publishing
White papers, manuals, encyclopedic plates, and publishing layouts.
View Cases

๐Ÿงช Other Use Cases
28 cases

Other use cases
Creative experiments, special tasks, mixed workflows, and practical cases.
View Cases

๐Ÿ–ผ๏ธ Full Gallery

Full gallery
Browse all 456 cases by gallery part and category.
Open Gallery

โญ Latest Additions

Latest additions
The newest community cases and workflows collected in the repo.
View Latest
### ๐Ÿงฉ 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 | |---|---|---| | ๐Ÿงฉ UI & Interfaces | [View Prompts](docs/templates.md#tpl-ui) | Components, page hierarchy, screenshot texture | | ๐Ÿ“Š Charts & Infographics | [View Prompts](docs/templates.md#tpl-infographic) | Modules, arrows, data structure, readability | | ๐Ÿ“ฐ Posters & Typography | [View Prompts](docs/templates.md#tpl-poster) | Layout, headline systems, people, visual impact |
Template Page 2 / 4: Commerce & Space | Category | Template Entry | Core Capability | |---|---|---| | ๐Ÿ›๏ธ Products & E-commerce | [View Prompts](docs/templates.md#tpl-product) | Product selling points, packaging, detail-page structure | | ๐Ÿท๏ธ Brand & Logos | [View Prompts](docs/templates.md#tpl-brand) | Logos, identity, brand touchpoint systems | | ๐Ÿ›๏ธ Architecture & Spaces | [View Prompts](docs/templates.md#tpl-architecture) | Perspective, materials, indoor and outdoor lighting |
Template Page 3 / 4: Imaging & Characters | Category | Template Entry | Core Capability | |---|---|---| | ๐Ÿ“ท Photography & Realism | [View Prompts](docs/templates.md#tpl-photo) | Lenses, lighting, realistic textures | | ๐ŸŽจ Illustration & Art | [View Prompts](docs/templates.md#tpl-illustration) | Brushwork, materials, art styles | | ๐Ÿง Characters & People | [View Prompts](docs/templates.md#tpl-character) | Character design, pose sheets, consistency |
Template Page 4 / 4: Narrative & Extensions | Category | Template Entry | Core Capability | |---|---|---| | ๐ŸŽฌ Scenes & Storytelling | [View Prompts](docs/templates.md#tpl-scene) | Storyboards, worldbuilding, emotional pacing | | ๐Ÿฎ History & Classical Chinese Themes | [View Prompts](docs/templates.md#tpl-history) | Dynasties, clothing, scroll-style narrative | | ๐Ÿ“š Documents & Publishing | [View Prompts](docs/templates.md#tpl-document) | Page systems, tables of contents, layout rules | | ๐Ÿงช Other Use Cases | [View Prompts](docs/templates.md#tpl-other) | Mixed tasks, experimental workflows, special outputs |
## ๐Ÿค– 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](https://www.npmjs.com/package/gpt-image-2-style-library) / [GitHub Packages](https://github.com/freestylefly/awesome-gpt-image-2/pkgs/npm/gpt-image-2-style-library)

City life system map generated with the GPT-Image2 style library skill

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`](https://www.npmjs.com/package/skills): ```bash 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: ```bash npx skills add freestylefly/awesome-gpt-image-2 --global --all --copy ``` ### Claude Code Plugin Marketplace Run these commands inside Claude Code: ```text /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: ```bash npm install -g gpt-image-2-style-library gpt-image-2-style-library install all ``` You can also run it without a global install: ```bash npx gpt-image-2-style-library install all ``` Install from GitHub Packages: ```bash 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: ```text Use gpt-image-2-style-library to create an infographic prompt about Codex. ``` For local source development: ```bash npm run generate:style-skill npm run install:skill ``` The skill source lives at [`agents/skills/gpt-image-2-style-library`](agents/skills/gpt-image-2-style-library/SKILL.md). Its generated reference comes from [`data/style-library.json`](data/style-library.json), so the website and Agent workflow share one style library. ## ๐Ÿ” Website Auth & Generation The visual site includes login-gated case generation powered by Supabase Auth, Supabase Postgres, and a Vercel Function proxy for the GPT Image 2 API. Required Vercel environment variables: ```bash VITE_SUPABASE_URL= VITE_SUPABASE_ANON_KEY= SUPABASE_SERVICE_ROLE_KEY= SUPER_ADMIN_EMAILS=2689458656@qq.com,canghe0818@gmail.com CIYUAN_API_KEY= CIYUAN_BASE_URL=https://ciyuan.today 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.sql`](supabase/migrations/202605090001_user_credits.sql) to the Supabase project. - Apply [`supabase/migrations/20260509090000_membership_billing.sql`](supabase/migrations/20260509090000_membership_billing.sql) to add membership plans, credit packs, Stripe order records, and credit adjustment RPCs. - Apply [`supabase/migrations/20260512090000_google_account_center.sql`](supabase/migrations/20260512090000_google_account_center.sql) to add account usage summaries and forced credit charging for super admins. - Apply [`supabase/migrations/20260512143000_pricing_admin_metrics.sql`](supabase/migrations/20260512143000_pricing_admin_metrics.sql) to update the `$5 / 300 credits` catalog and add admin dashboard metrics. - Apply [`supabase/migrations/20260515090000_case_favorites.sql`](supabase/migrations/20260515090000_case_favorites.sql) to add per-user case favorites. - Add `https://gpt-image2.canghe.ai` and local dev URLs such as `http://127.0.0.1:5173` to 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_KEY` only 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`, and `customer.subscription.deleted`. - Keep `STRIPE_SECRET_KEY` and `STRIPE_WEBHOOK_SECRET` only in server-side Vercel Environment Variables. - Create a GA4 property for `gpt-image2.canghe.ai`, add the measurement ID to `VITE_GA_MEASUREMENT_ID`, and copy the numeric property ID to `GA4_PROPERTY_ID`. - Create a Google OAuth Web Client with `http://localhost:8080/oauth2callback` as an authorized redirect URI, then add `GOOGLE_ANALYTICS_CLIENT_ID` and `GOOGLE_ANALYTICS_CLIENT_SECRET` to local `.env.local`. - Run `npm run ga4:oauth`, open the generated URL, approve the `analytics.readonly` permission, paste the callback URL into the terminal, then add the returned `GOOGLE_ANALYTICS_REFRESH_TOKEN` to Vercel as a Sensitive environment variable. ## ๐Ÿ–ผ๏ธ Featured Cases ### Case 1: Infographic Visualization [![Urban Metabolism Atlas](data/images/case1.jpg)](docs/gallery-part-1.md#case-1) An engineering-whitepaper-style infographic case for studying modular structure, information hierarchy, and bilingual labels. [View full case](docs/gallery-part-1.md#case-1) ### Case 2: Social Media Interface Screenshot [![Ailln AI](data/images/case2.jpg)](docs/gallery-part-1.md#case-2) A mixed "product interface + social content screenshot" case for controlling text blocks, UI frames, and content cards. [View full case](docs/gallery-part-1.md#case-2) ### Case 6: Illustration Art [![Japanese fantasy illustration](data/images/case6.jpg)](docs/gallery-part-1.md#case-6) A Japanese fantasy illustration example for studying atmosphere, color, and large-scene composition. [View full case](docs/gallery-part-1.md#case-6) ### Case 17: Interaction Design Diagram [![Interaction design diagram](data/images/case17.jpg)](docs/gallery-part-1.md#case-17) A classic "structured breakdown + explanatory layout" case for product diagrams and poster-like technical explainers. [View full case](docs/gallery-part-1.md#case-17) ### Case 166: Twelve Gold Saints Card Set [![Twelve Gold Saints card set](data/images/case166.jpg)](docs/gallery-part-2.md#case-166) A multi-card, unified-style case for studying batch generation and series design. [View full case](docs/gallery-part-2.md#case-166) ### Case 310: Snack Brand Technical Breakdown [![Snack brand technical breakdown](data/images/case310.jpg)](docs/gallery-part-2.md#case-310) A strong hybrid of brand narrative, structural breakdown, and commercial presentation. Useful as an "infographic + brand visual" reference. [View full case](docs/gallery-part-2.md#case-310) ### Canghe Original Tests

Case 330: Moonlit Livestream Scene

Moonlit livestream scene
A high-fidelity livestream screenshot reference for UI atmosphere, comments, and realistic people.
View Case

Case 334: RAG Technical Explainer

RAG technical explainer
A reference for technical concepts, process arrows, and Chinese explanation modules.
View Case

Case 338: Red Cliff Classical Scroll

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

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

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

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 454: Travel-Food Chips Poster

Travel-food chips poster
A tourism-flavored product ad prompt with spiraling sauce ribbons, local landmarks, miniature travelers, and premium package layout.
View Case

Case 455: Oversized Comfort Clog Campaign

Oversized comfort clog campaign
A clean commercial product prompt combining a giant shoe, athleisure model, reflective studio floor, and bold campaign typography.
View Case

Case 456: Historical Events 2x2 Visual Map

Historical events 2x2 visual map
A weighted prompt formula for turning famous historical events into diorama maps, first-person UI, and period newspaper panels.
View Case
## ๐Ÿงฉ Template Entry The full template library lives in [`docs/templates.md`](docs/templates.md). Use the **Prompt Template Categories** above for quick category jumps, or open [Industrial prompt templates and pitfalls guide](docs/templates.md) for the complete template text. ## ๐Ÿš€ How To Use This Repository 1. Start from the featured cases and decide what output type you want to imitate. 2. Open the full gallery and find nearby cases. Copy structure first, then style words. 3. Return to the template page and fill your business variables into the general or JSON templates. ## ๐Ÿ“„ Notes & Disclaimer ## Acknowledgements & Sources During collection and research, this project references public prompt-library content from [YouMind](https://youmind.com/) and [OpenNana](https://opennana.com/) 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](https://youmind.com/) and [OpenNana](https://opennana.com/). 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 [![Star History Chart](https://api.star-history.com/svg?repos=freestylefly/awesome-gpt-image-2&type=Date)](https://star-history.com/#freestylefly/awesome-gpt-image-2&Date) ## ๐Ÿ“œ License This project is open source under the [MIT License](LICENSE). You can use, modify, distribute, and build on it freely while preserving the license notice.