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

2026-09-10

AI Summary

本文介绍Vidu S2系统，通过实时交互式数字角色模型和视频编辑模型解决实时生成及编辑720p视频的问题，支持动态参考更新与多种编辑功能。

Abstract

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.

Problem

• real-time
• interactive
• editable
• spatial video generation
• video editing

Innovation

• real-time interactive
• editable video generation
• spatial video generation
• dynamic references