ZeroHour
Hugging Face daily paperspublished ()ingested Jintao Zhang, Kai Jiang, Jintao Chen

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

infoModel releaseimportance 40
AI summary · glm-5.3

Vidu S2 delivers real-time 720p interactive avatar generation plus real-time video editing with style, clothing, character, and background replacement.

Vidu S2 comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model. S2-Avatar supports real-time 720p generation, dynamic references updatable at any moment, and stronger instruction following such as dancing, while S2-Editing performs real-time style rendering, clothing replacement, character replacement, and background replacement. The work also explores real-time spatial video generation for both models, reports outperforming all baselines, and offers a playable online demo at vidu.com.

  • Real-time 720p interactive avatar video generation
  • Real-time editing supports style, clothing, character, and background changes
  • Extends both models to real-time spatial video generation
Full article103 words · extracted from huggingface.co · click to collapse

We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model. Moreover, we explore the feasibility of real-time spatial video generation for both Vidu S2-Avatar and Vidu S2-Editing. Compared with Vidu S1, Vidu S2-Avatar supports real-time 720p video generation, generation with dynamic references that can be updated at any moment, and stronger instruction following, such as dancing. Vidu S2-Editing supports editing a video stream in real time, including style rendering, clothing replacement, character replacement, and background replacement. Experiments show that Vidu S2 outperforms all baselines. A playable online demo is available at https://vidu.com/vidu-stream.

Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.11638