Vidu S2 Launches: Real-Time Talkable Avatars and Live Video Editing That Beats Offline Editors
iamaliveix · x · 2026-09-15
Vidu launched S2, a pair of real-time video models you can talk to, direct, and edit live:
- S2-Avatar: interactive characters at 720p, 25–42 FPS, with voice conversations and voice-controlled complex motions ("dance for me", "put on this hat"), plus reference-image-guided object interaction, outfit changes, and background switching that update anytime.
- S2-Editing: transforms live video streams — style rendering, character replacement, background replacement, virtual try-on — while preserving original motion. The team says the real-time editor outperforms the offline editors they benchmarked, with SOTA results across their paper's benchmarks.
- Also explored: real-time spatial video generation with synchronized stereo streams for VR. API and technical report are available now.
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