A team from Alibaba has released an audio-driven portrait video generation framework, EMC (Emote Portrait Alive), which was published simultaneously in arXiv. Inputting a reference image and sound audio, the framework is able to generate audio portrait videos with rich facial expressions and head poses.
Ali Releases Portrait Video Generation Framework EMO
Previous: Pika推出“对口型”功能
Next: 李想谈苹果放弃造车转向人工智能：绝对正确