Get the latest tech news
OmniHuman-1: Human Animation Models
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
OmniHuman significantly outperforms existing methods, generating extremely realistic human videos based on weak signal inputs, especially audio. * Note that to generate all results on this page, only any single image and audio are required, except for the demo showcasing video and combined driving signals. In terms of input diversity, OmniHuman supports cartoons, artificial objects, animals, and challenging poses, ensuring motion characteristics match each style's unique features.
Or read this on Hacker News