Shengshu releases ViduS2: real-time costume, scene and prop switching driven by chat

生数科技 · wechat · 2026-09-22

Shengshu (Vidu) has released ViduS2, a new real-time interactive and editing model that breaks the previous limitation of fixed visuals in its Empresses in the Palace interactive demo. A single sentence can now drive real-time visual changes: scene switching with natural lighting adaptation, real-time prop generation (e.g. a sword in hand), costume changes with synced accessories, and instant dialogue responses with coherent micro-expressions.

ViduS2 decomposes character fidelity into four verifiable dimensions: persona consistency across long multi-turn dialogues, stability over sessions extended from 1 minute to 2 hours without quality decay, layered emotional expression with configurable action libraries, and real-time appearance/scene changes mid-session without restart. The solution targets gaming, brand livestreams, cultural tourism and enterprise training, with lightweight SaaS/MaaS access and support for 100+ languages and dialects.

Original post →

More from Multimodal

Multimodal channel →