LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
This is the model for https://github.com/GAIR-NLP/LiveTalk
LiveTalk enables real-time multimodal interactive avatar video generation through an improved on-policy distillation approach. By distilling bidirectional diffusion models into causal, few-step autoregressive models, LiveTalk achieves over 20× speedup, enabling seamless real-time interactive experience.
- Downloads last month
- 31
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support