Video
OmniHuman 2
Use it ↗Animate a person, pet or character from a single image so they speak or sing to your audio track, with lip sync, gestures and camera moves you direct in the prompt.
OmniHuman 2 brings one image to life with your audio: speech in many languages or a sung track, from 4 seconds to 5 minutes. Lip sync follows the audio closely, and the optional Prompt directs the camera, gestures and emotion, timed to the lines. It works with photos, 3D characters, anime, pixel art, oil paintings, marble statues and animals, and handles two-person scenes such as a podcast. The video lasts as long as the audio. Ideal for presenters, ads, NPC dialogue, music videos and localized content.