What it does
Faceswap is a program that learns to recognise two faces and then replaces one with the other in pictures and video. This is often called a "deepfake".
The process has three steps: extract faces from your images, train a model on them, then convert the video using the trained model. There's a graphical interface as well as command-line tools, and it runs on Windows, Linux and macOS.
Its makers publish an ethics statement: they say it's not for inappropriate content or for changing faces without consent or to hide that it's been used, and that it's meant for learning about AI, commentary, film work and other ethical uses.
Who it's for
Hobbyists, visual-effects artists and people who want to learn hands-on how face-swapping AI works.
Can I use it without coding?
With some setup. There's a graphical interface, but you install it by following a setup guide, and a powerful graphics card helps a lot. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Windows, Linux, Mac
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Gather photos or videos of the faces you want to use.
- Use the app to extract faces, train a model, then convert your pictures.
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
Where people are talking about it
- Github restricts public Faceswap repo to logged-in usersHacker News · Feb 2019