OmniHuman 2.0

OmniHuman 2.0 turns one image and an audio track into an avatar video. Start with a portrait or character image, add speech or music, and use an optional prompt to guide the scene and movement. The tool can generate videos up to 720p and five minutes long. It may be useful for short explainers, presenter clips, creative scenes, and social content. Preview the result and review the audio, framing, and lip sync before sharing. OmniHuman 2.0 is an independent tool and is not affiliated with ByteDance or BytePlus.