eren23/openflipbook — reverse-engineered prompt

Reverse engineered prompt

GitHub

Build me an open source Flipbook style web app where the whole interface is an AI generated picture. A person should be able to start with a text prompt or upload an image, then the app creates an illustrated page. When they click anywhere on that picture, the app figures out what they clicked and generates the next related page so they can keep exploring deeper.

Please include the main play experience, shareable saved pages, a status page that shows whether required keys and services are configured, and support for bringing my own API keys for image generation, vision, storage, database, and backend hosting. Add the nice exploration features too, like pinning the current visual style, showing citations when the planner used web sources, shift dragging to circle a specific area, a simple timeline scrubber for past pages, and an optional animation toggle.

Use a modern web frontend with a Python API backend like this project suggests. Make it runnable locally with Docker, and look up current docs online if you need to.

Want more depth? Deep Reverse