What it does
This project collects hundreds of example images made with OpenAI's GPT-Image models, each with the full prompt used to create it. Cases cover posters, product shots, logos, charts, user interfaces and more.
It also offers reusable prompt templates that break a picture into parts, such as subject, lighting, materials and layout, so results are easier to control and repeat. There is a companion website for browsing, and a skill for AI agents.
Much of the material is in Chinese, with English and Japanese versions of the README.
Who it's for
Designers, marketers and anyone who wants better, more consistent results from AI image tools.
Can I use it without coding?
Yes. Browse the gallery on the website and copy any prompt. Using it needs access to an image model. New to this? Start here.
Can I run it?
- Cost
- Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.
- Runs on
- Web browser
- Computer
- An ordinary computer is fine
- Privacy
- Sends what you give it to an online service
- API key
- Not needed
Try it
- Browse the gallery on the project's website or in the repository.
- Copy the full prompt of an image you like.
- Paste it into a tool that uses OpenAI's GPT-Image models.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page or the official download page above. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- What you type or upload is sent to an online service. Avoid sharing private or sensitive information.
- More on staying safe