GPT-Image2 工业级提示词模板库：470+案例逆向工程

Prompt as Code | GPT-Image2 Industrial Prompt Engine & Template Library, 500+ Reverse-Engineered Cases, 20+ Industrial Templates

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.

The GPT-Image2 discussion group is now a paid community. Sign in on the community page, make a one-time ¥9.90 Alipay payment, and the protected group QR will appear only after the server confirms payment.

For payment, access, refund, or product questions, follow the WeChat official account 苍何 or scan the card below and send a message.

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.

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

Gallery Part 1: cases 1-165

Gallery Part 2: cases 166-532

Industrial prompt templates and pitfalls guide

Agent skill: GPT-Image2 Style Library

🗂️ 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.

🧩 UI & Interfaces 73 cases

📊 Charts & Infographics 52 cases

📰 Posters & Typography 86 cases

🛍️ Products & E-commerce 41 cases

🏷️ Brand & Logos 27 cases

🏛️ Architecture & Spaces 12 cases

📷 Photography & Realism 77 cases

🎨 Illustration & Art 58 cases

🧍 Characters & People 29 cases

🎬 Scenes & Storytelling 20 cases

🏮 History & Classical Chinese Themes 16 cases

📚 Documents & Publishing 10 cases

🧪 Other Use Cases 28 cases

🧩 Prompt Template Categories

The prompt body remains in the original template document for now. This homepage only adds an English navigation layer.

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

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 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:

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=

Apply supabase/migrations/202605090001_user_credits.sql to the Supabase project.

Apply supabase/migrations/20260509090000_membership_billing.sql to add membership plans, credit packs, Stripe order records, and credit adjustment RPCs.

Apply supabase/migrations/20260721090000_alipay_webpay.sql before enabling Alipay website payments, then configure each credit pack's reviewed CNY price. See Alipay website payment setup.

Apply supabase/migrations/20260722090000_paid_community.sql before enabling the paid community. Keep COMMUNITY_PAYMENT_ENABLED=false until the protected QR, Alipay onboarding, and production payment/refund checks are complete. See the paid community runbook.

Apply 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 to update the $5 / 300 credits catalog and add admin dashboard metrics.

Apply 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.

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

Case 334: RAG Technical Explainer

Case 338: Red Cliff Classical Scroll

Case 331: Hand-Drawn Xi'an Watercolor Map

Case 332: Tea Pi Product Poster

Case 339: Apple-Style Nature Science Poster

Latest Community Additions

Only the latest collection and import run is shown here. Older imports stay in the full gallery.

Case 527: Rio Travel Ticket Pop-Up Diorama

Case 528: Chibi Portrait on a Real Holiday Street

Case 529: Cloud-Balloon Mountain Ridge Portrait

Case 530: Doodle Characters on Photo Background

Case 531: Crystal-Frame Country Travel Campaign

Case 532: Six-Panel Lemon Drink Micro Campaign

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.

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.

This project is open source under the MIT License. You can use, modify, distribute, and build on it freely while preserving the license notice.