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 avatars and streaming video editing(9 posts)→
More from Multimodal
- Pika's pika-h3-flex Space Trends on Hugging Face — Pika-Labs · 2026-11-02
- awa-video-reel: free Claude Code skill auto-edits shorts and records website B-roll — TawohAwa · 2026-11-02
- Hobbyist 3D-scans Yokohama's abandoned Negishi racecourse grandstand with 3DGS — janusch_patas · 2026-11-02
- Drone-captured 400-ft guyed tower rebuilt as 3DGS via Metashape and LichtFeld Studio — janusch_patas · 2026-11-02
- TBC launches brain-cell-inspired AI video model Mischief at $0.005 per second — danfaggella · 2026-11-02
- Even a skeptic almost fell for an AI fruit cartoon reel — menhguin · 2026-11-02