<ul><li>ByteDance researchers have developed OmniHuman, an AI system that can transform single photographs into realistic videos of people speaking and moving naturally.</li><li>OmniHuman generates full-body videos that match speech with gestures and movements, surpassing previous AI models.</li><li>The system was trained on over 18,700 hours of human video data using an innovative "omni-conditions" training approach.</li><li>This advancement in AI-generated media has the potential to reshape digital entertainment, educational content creation, and communications.</li></ul>

OmniHuman: ByteDance’s new AI creates realistic videos from a single photo

Discover more