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

Industry leading face manipulation platform

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Wav2Lip UHQ extension for Automatic1111

Live real-time avatars from your webcam in the browser. No dedicated hardware or software installation needed. A pure Google Colab wrapper for live First-order-motion-model, aka Avatarify in the browser. And other Colabs providing an accessible interface for using FOMM, Wav2Lip and Liquid-warping-GAN with your own media and a rich GUI.

Industry leading face manipulation platform

Industry leading face manipulation platform

Avatar Generation For Characters and Game Assets Using Deep Fakes

Customized fork of Rope Deepfake software featuring live streaming capabilities and support for Deepfacelive models

The pytorch implementation of our WACV23 paper "Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis".

real time face swap and one-click video deepfake with only a single image. You can use one face or two faces to replace in realtime.

Deepstory turns a text/generated text into a video where the character is animated to speak your story using his/her voice.

Lip Synchronization (Wav2Lip).

Swap faces in images and videos. Create face embeddings. Enhance face image quality. Deploy as a web api.

SMILE: Semantically-guided Multi-attribute Image and Layout Editing, ICCV Workshops 2021.

Using a single image and just 10 seconds of sample audio, our project enables you to create a video where it appears as if you're speaking the desired text.

Talking Face Generation system

This is an official implementation for "Not with my name! Inferring artists' names of input strings employed by Diffusion Models".

From Gradient Leakage to Adversarial Attacks in Federated Learning