antgroup/ditto-talkinghead
realtime talking head synthesis using motion-space diffusion
View on index · View in 3D Map
Related repos
- audio-driven talking head video generation using diffusion models
- audio-driven portrait animation with editable facial landmarks
- JavaScript class for real-time 3D avatar lip-sync
- Generates talking faces from audio at 40 FPS
- Uses a photo, audio, and hand poses to make an animation video with talking and gestures
- generates synchronized talking head videos from audio and reference images
- Audio-driven synthesis for portrait image animation
- Transcribes audio streams in real-time
- Generates talking faces from audio with motion transfer
- Lip-sync videos to audio using a diffusion model
