Create talking, singing, and animated videos from a photo and audio with OmniHuman 2.0. Guide actions and camera movement with prompts.

OmniHuman 2.0 is an audio-driven AI video generation model from ByteDance, designed to turn a single image and an audio track into an animated character video.

OmniHuman 2.0 can be used by content creators, educators, marketers, animators, storytellers, and creative teams.

Creators can make talking character videos and music performances. Educators can turn recorded lessons into presenter-style videos, while marketers can develop product presentations and promotional concepts.

Overall, OmniHuman 2.0 combines image animation, audio-driven lip sync, facial expressions, body movement, and prompt-based control in one online AI video generation workflow.