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

Source: https://huggingface.co/papers/2609.11638 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Vidu S2 introduces real-time interactive avatar and video editing models that support high-resolution spatial video generation and dynamic reference updates.

We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-timevideo editingmodel. Moreover, we explore the feasibility of real-timespatial video generationfor both Vidu S2-Avatar and Vidu S2-Editing. Compared with Vidu S1, Vidu S2-Avatar supports real-time 720p video generation, generation withdynamic referencesthat can be updated at any moment, and strongerinstruction following, such as dancing. Vidu S2-Editing supports editing a video stream in real time, includingstyle rendering, clothing replacement,character replacement, andbackground replacement. Experiments show that Vidu S2 outperforms all baselines. A playable online demo is available at https://vidu.com/vidu-stream.

View arXiv pageView PDFProject pageGitHubAdd to collection

Get this paper in your agent:

hf papers read 2609\.11638

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.11638 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.11638 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.11638 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.