Faceswap
faceswap.dev
- Free plan
- Windows
- macOS
- Linux
What Faceswap is
Faceswap is a free, open source tool for recognizing and swapping faces in pictures and videos using deep learning. Its workflow moves from extracting faces in source media to training a model, then converting media with that model. Users can work through a graphical interface or command line scripts. The project says it is powered by TensorFlow, Keras, and Python, and runs on Windows, macOS, and Linux. The site links to a Windows installer and Linux install script, and directs users on other platforms to its GitHub repository. For best performance, the project recommends a modern GPU with CUDA support; it also says many AMD GPUs are supported through ROCm on Linux. A video conversion tool is included, and the documentation describes using FFmpeg to convert video to images and back. The project directs users to forums for questions, guides, and tutorials, while its repository points to a Discord server for help. Faceswap is free, and the maker welcomes donations through Patreon and PayPal. The project says it is not intended for non-consensual face changes or illicit or unethical purposes.
Who it suits
Faceswap may suit users seeking a free tool for face swapping in pictures or videos who are comfortable with a multi-step extract, train, and convert workflow. It runs on Windows, macOS, and Linux.
Good to know, and what to watch
- Free and open source
- Offers a graphical interface and command line scripts
- Runs on Windows, macOS, and Linux
- Includes a video conversion tool
- A modern CUDA-capable GPU is recommended for best performance
- Other-platform users are directed to the GitHub repository
Plans
Every plan and priceFaceswap
Free plan
The verdict
Faceswap provides a defined workflow for face swapping in still images and video, with both graphical and command-line options. Users should note the GPU recommendation and the project’s stated restrictions on non-consensual or unethical use.
What the maker publishes
- Commercial contact
- The website invites inquiries about commercial projects, custom development, and media through its listed contact email. source
- Donations
- The maker says the software is free and open source, welcomes donations, and offers Patreon and PayPal donation links. source
- Downloads
- The site links to a Windows installer and a Linux install script, and directs users on other platforms to the GitHub repository. source
- Ethical use
- The project says Faceswap is not for inappropriate content, non-consensual face changes, or illicit or unethical purposes. source
- Hardware
- The project says a modern GPU with CUDA support is recommended for best performance, and many AMD GPUs are supported through ROCm on Linux. source
- Integrations
- The project documentation names FFmpeg as an option for converting video to images and back. source
- Interface
- Faceswap can be run through a graphical user interface or command line scripts. source
- Operating systems
- Faceswap runs on Windows, macOS, and Linux. source
- Privacy
- The website privacy policy says comments may include the visitor's IP address and browser user agent for spam detection, and visitor comments may be checked by an automated spam service. source
- Purpose
- Faceswap uses deep learning to recognize and swap faces in pictures and videos. source
- Support
- The maker directs users to its forums for questions, guides, and tutorials, and its repository also points to a Discord server for help. source
- Technology
- The maker says Faceswap is powered by TensorFlow, Keras, and Python. source
- Video conversion
- The project includes a video conversion tool and also describes using FFmpeg to convert video to images and back. source
- Workflow
- The project workflow includes extracting faces, training a model, and converting source media with that model. source
Checked against the maker's pages on 9 Oct 2026.