AniTalker：一张照片和输入音频生成生动的能说话的面部视频

AniTalker通过一个静态的肖像画和输入音频，生成生动多样的说话面部动画视频。该框架不仅仅着重于嘴唇同步这样的言语线索，而且能够捕捉到面部表情和非言语线索的复杂动态。

AniTalker 能实现的效果包括：

Support authors and subscribe to content

This is premium stuff. Subscribe to read the entire article.
Login if you have purchased

Subscribe
Gain access to all our Premium contents.
More than 100+ articles.
Subscribe Now

via XiaoHu.AI学院 (author: 小互)

Invalid media: video