About Us
Real-time face swap and one-click video deepfake with only a single image
What is Deep-Live-Cam?
Deep-Live-Cam is an open-source AI tool that enables real-time face swapping and video deepfake creation using cutting-edge artificial intelligence technology. With just a single source image, users can transform faces in videos or live webcam feeds, creating stunning visual effects and virtual avatars.
The project has gained significant recognition in the developer and creator communities, with over 76,000 stars on GitHub and thousands of active users worldwide.
Our Mission
Deep-Live-Cam aims to democratize access to advanced AI face-swapping technology while maintaining strict privacy and ethical standards. We believe that powerful AI tools should be:
- Accessible: Free and open-source for everyone
- Private: Processing happens locally, no data collection
- Transparent: Open source code for verification
- Ethical: Designed for creative and legitimate purposes
Technology Stack
Deep-Live-Cam is built on cutting-edge AI and computer vision technologies:
InsightFace
Advanced face recognition and analysis models
ONNX Runtime
Optimized inference engine supporting multiple execution providers
GFPGAN
Face restoration and enhancement technology
FFmpeg
Video processing and encoding library
Python
Primary programming language
PyTorch
Deep learning framework
Community & Contributors
Deep-Live-Cam is made possible by a vibrant community of developers, contributors, and users. The project welcomes contributions from anyone interested in improving the tool.
Key contributors include:
- hacksider: Project maintainer and primary developer
- Henry: Major contributor
- vic4key: Core contributor and supporter
- pereiraroland26: Multiple faces support
- kier007: User experience improvements
- qitianai: Multi-lingual support
- And many more contributors from the open-source community
Credits & Acknowledgments
Deep-Live-Cam acknowledges the following projects and contributors:
- deepinsight: InsightFace project providing excellent face recognition library and models
- havok2-htwo: Webcam integration code
- GosuDRM: Open version of roop
- ffmpeg: Video processing capabilities
- All developers behind the libraries used in this project
- The 76,000+ users who have starred and supported the project
Note: The base author of the code is s0md3v.
License
Deep-Live-Cam is released under the AGPL-3.0 license. This means:
- You are free to use, modify, and distribute the software
- If you modify and distribute, you must share your changes
- Commercial use is allowed under the license terms
- Please note that InsightFace models are for non-commercial research purposes only
Press & Recognition
Deep-Live-Cam has been featured in various tech publications and media:
- "Deep-Live-Cam goes viral, allowing anyone to become a digital doppelganger" - Ars Technica
- "Thanks Deep Live Cam, shapeshifters are among us now" - Dataconomy
- "This free AI tool lets you become anyone during video-calls" - NewsBytes
- "OK, this viral AI live stream software is truly terrifying" - Creative Bloq
- "Deepfake AI Tool Lets You Become Anyone in a Video Call With Single Photo" - PetaPixel
- Featured by content creators including IShowSpeed, SomeOrdinaryGamers, and TechLinked
Get Involved
Want to contribute to the future of AI-powered media? Here's how you can help our open-source community grow.
Report Issues
Help improve the project by identifying and reporting bugs or performance bottlenecks you encounter.
Contribute Code
Submit pull requests with new features, optimizations, or bug fixes to help the application evolve.
Improve Documentation
Help make the project more accessible by refining guides, tutorials, and technical documentation.
Share Feedback
Provide suggestions and ideas to help us shape the roadmap and user experience of the tool.
Star the Project
Show your support on GitHub! Stars help more people discover the project and boost community morale.
Spread the Word
Share the application with others on social media or in developer communities to help us grow.