What it does
This tool finds the text in an image, such as a comic page, reads it, translates it and paints the translation back into the picture. It also removes the original text and re-typesets the new words.
It mainly targets Japanese, but also supports Chinese, English and around 20 other languages. It can run as a batch tool, a local web page or a service for other programs.
The README says the project is still early in development and has many rough edges.
Who it's for
Comic and manga readers, and fans who want to understand images in languages they can't read.
Can I use it without coding?
With some setup. It needs Python or Docker set up from a terminal; a graphics card speeds it up. New to this? Start here.
Can I run it?
- Runs on
- Windows, Linux, Mac
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- API key
- Not needed
Try it
- Install Python, or Docker, on your computer.
- Install the project following its README.
- Start its local web page and upload an image to translate.
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. Copies with similar names exist for many popular projects.
- License (GPL-3.0): Free to use; if you share a changed version, you must share your source code too.
- More on staying safe