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.
More from Multimodal
- Poolday Raises $11M for AI Video Agent That Navigates Your Live App to Build Demos — aryanXmahajan · 2026-09-16
- AI-Generated Series 'The Sage' Reaches Episode 7, Made Entirely With Invideo Agent — Kavanthekid · 2026-09-16
- GPT-6 Astra demos: playable games, robot demos and 3D pipelines built in hours — socialwithaayan · 2026-09-16
- The next low-budget horror blockbuster could be made entirely in tldraw — max__drake · 2026-09-16
- DGX Spark + TRELLIS.2 turns pencil sketches into 3D GLBs fully locally — jasonkneen · 2026-09-15
- Oxford's Anders Sandberg demos generative art combined with traditional media — anderssandberg · 2026-09-15