Preprint
Aug 2026
Omni-LiveAvatar: Minute-Level Real-Time Streaming Joint Audio-Video Avatar Generation
Omni-LiveAvatar is presented, the first framework for minute-level, real-time streaming joint audio-video avatar generation and proposes a progressive autoregressive distillation pipeline that transfers a large bidirectional joint audio-video diffusion model into a few-step autoregressive generator without auxiliary stabilization mechanisms.
Lu Zhu, Xingtong Ge, Fangyu Lin et al.
· 0 citations