Vidu S2 comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model. The system also explores the feasibility of real-time spatial video generation for both components.

  • Vidu S2-Avatar supports real-time 720p video generation with dynamic references that can be updated at any moment.
  • It features stronger instruction following capabilities, such as dancing.
  • Vidu S2-Editing allows real-time editing of a video stream, including style rendering and replacements for clothing, characters, and backgrounds.

Experiments show that Vidu S2 outperforms all baselines.