hacksider/Deep-Live-Cam

real time face swap and one-click video deepfake with only a single image

What it solves

Deep-Live-Cam enables real-time face swapping and video deepfaking using only a single source image of the target face. It allows users to replace faces in live webcam feeds, pre-recorded videos, or images, making it a tool for digital content creation, animation, and entertainment.

How it works

The software uses AI models (such as GFPGAN and InsightFace) to map a source face onto a target subject. It supports multiple execution providers to accelerate processing across different hardware, including NVIDIA GPUs (CUDA), Apple Silicon (CoreML), Intel (OpenVINO), and Windows (DirectML), as well as standard CPUs.

Who it’s for

It is designed for AI-generated media artists, content creators, and performers who need to animate custom characters or create engaging visual content in real-time.

Highlights

  • Real-time performance: Supports live webcam face swapping for streaming or performances.
  • Single-image requirement: Only one photo of the source face is needed to perform the swap.
  • Many Faces: Ability to map different faces onto multiple subjects simultaneously.
  • Mouth Mask: A feature to retain the original mouth for more accurate movement.
  • Cross-platform acceleration: Optimized builds for Windows, macOS, and Linux with support for various GPU backends.

Related

  • Project
    deepfakes/faceswap

    A deep learning tool for recognizing and swapping faces in pictures and videos through an extract-train-convert pipeline.

  • Project
    VisoMasterFusion/VisoMaster-Fusion

    A desktop application for AI-powered face swapping and enhancement across images, videos, and live webcam feeds, featuring professional editing tools and GPU acceleration.

  • Project
    cmusatyalab/openface

    An open-source face recognition library using deep neural networks to identify people from images and real-time video streams.

  • Project
    Gourieff/ComfyUI-ReActor

    A fast and simple face-swapping extension for ComfyUI that allows users to replace faces in images and videos using various models and restoration tools.

  • Project
    BrokenSource/DepthFlow

    DepthFlow is an open-source image-to-video converter that transforms static pictures into 3D parallax animations using depth estimation and optimized shaders.