PixVerse R2 interactive world model: steer with WASD keys as audio-video generates live
SarahAnnabels · x · 2026-09-24
PixVerse's R2 generates a responsive world rather than isolated clips — you can control it with WASD keys, and it's not pre-rendered. Under the hood is what PixVerse calls Omni Causal AR: modeling past world state → current input → future world state, continuously generating the next synchronized audio+video segment as you move, making it feel entirely different from standard text-to-video.
More from Multimodal
- Ant Group's open-source Ming-3.0-tts-0.5B tops Open TTS Leaderboard with 0.88 WER — NielsRogge · 2026-11-12
- Llama app adds simultaneous voice, image and video input, running locally on LFM3-Omni — mervenoyann · 2026-11-12
- Seedance 2.5 can now generate 4K video directly, no upscaling needed — charis_ai · 2026-11-12
- codec.audio benchmarks neural audio codecs on noisy in-the-wild speech; MOSS tops — kastnerkyle · 2026-11-11
- State of AI video: Isaiah Ross's hyper-realistic showcase hailed as current peak — LinusEkenstam · 2026-11-11
- State of AI video: generative clips reach startling new realism — LinusEkenstam · 2026-11-11