88Z AI, 16 September — Shengshu Technology has released the Vidu S2 video model, featuring an Avatar version for real-time interaction and an Editing version with four editing capabilities, significantly improving image quality and dynamic consistency.
At a glance
- Vidu S2-Avatar supports dynamic reference image updates, upgrades real-time output to 720P, and maintains action continuity.
- Vidu S2-Editing provides four real-time editing functions: style transfer, virtual try-on, character replacement, and background replacement.
The update
Shengshu Technology has officially launched the Vidu S2 video generation model series, which includes two core models: Vidu S2-Avatar and Vidu S2-Editing. The Vidu S2-Avatar focuses on conversational interaction scenarios, supporting dynamic updates of reference images during interactions. Its real-time output resolution has been upgraded from 540P to 720P, enabling precise execution of continuous actions such as putting on or taking off hats while maintaining high consistency in character states. The other model, Vidu S2-Editing, focuses on real-time video editing tasks, specifically supporting four functional modules: style transfer, virtual try-on, character replacement, and background replacement, providing users with efficient video content modification capabilities.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 生数科技Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.