Vidu launches S2: real-time AI video generation you can talk to and edit live
Scobleizer · x · 2026-09-15
Vidu has announced the S2 series, centered on real-time, interactive, editable video generation:
- S2-Avatar: real-time interactive characters at 720p and 25–42 FPS with voice conversation and voice-controlled motion (including dancing). New reference images can be introduced mid-conversation to change outfits, interact with objects, or switch scenes/backgrounds.
- S2-Editing: live editing of incoming video streams while preserving motion and timing — style transfer, virtual try-on, character replacement, and background replacement via reference images.
- Spatial video: converts generated characters and live edits into stereoscopic video for immersive VR.
Vidu claims SOTA results across all five public benchmarks in its evaluation. The model is available via web demo and API, with a technical report published.
Related event: Shengshu releases Vidu S2: real-time interactive video generation(4 posts)→
More from Multimodal
- Blender kinetic typography restyled by MiniMax H3: full workflow with prompt — Hailuo_AI · 2026-09-15
- GPT Image 2.5 demoed in two speeds: Flare for rapid exploration, Sunburst for delivery — AIwithGhotai · 2026-09-15
- GPT Image 2.5 targeted edit: six e-commerce colorways without reshooting the listing — AIwithGhotai · 2026-09-15
- MiniMax launches Design: an agent-driven canvas that turns one brief into a full video production — Hailuo_AI · 2026-09-15
- Suno admits in court filing it ingested YouTube audio in UMG and Sony lawsuit — emmanuelvivier · 2026-09-15
- Seedance 2.5 generates 30s photorealistic 4K AAA-style stealth gameplay — SimplyAnnisa · 2026-09-15