Alibaba just announced OmniAvatar, a new audio-driven model that takes full-body, expressive human animation to a whole new level.
natural movement, controllable emotions, and ultra-accurate lip-sync.
10 examples:
OmniAvatar can generate lifelike speaking avatar videos that the characters' actions and expressions are natural and rich, with audio perfectly synchronized to their lip movements.
Human-object Interaction
OmniAvatar is able to interact with objects while speaking, significantly broadening the application scenarios for audio-driven digital avatars.