Interactive autoregressive world model generating minute-long playable video with real-time camera control and prompt events.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
AlayaWorld is a research world model from ALAYA Lab that generates playable video worlds from an input scene. It is autoregressive and supports real-time 6-DoF camera control, as well as chunk-level prompt switching so a new event (for example fireworks or a summoned creature) can be introduced mid-generation.
For consistency it combines an explicit 3D cache, reprojected to the queried view for spatial recall, with a compressed frame-history embedding for temporal continuity. For long-horizon stability it trains on drifted histories and uses an error bank that re-injects accumulated artifacts. Real-time speed comes from few-step DMD distillation and short temporal chunks. The project page shows clips of over a minute across several visual and game-style looks.
At the time of the provided material, only a project demo page was available. A YouTube creator reported 720p at 24 fps output with visible quality artifacts and said code and models are planned for release. No public weights, license, pricing or paper link were found.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Real-time interactive world generator from an image, with prompt-based edits and persistent memory. It outputs 720p at 24 fps for over a minute, with quality artifacts. Code and models are planned for release.
Closest neighbours by meaning, not just by category.
Model
14B autoregressive world model that generates interactive, camera-controlled video worlds in 3 denoising steps.
Model
Real-time interactive world model with compressed memory and hybrid action and semantic control, built on Wan 2.2.
Model
Interactive world model that generates action-conditioned video rollouts in real time on a single RTX 5090.
Model · Tencent
Tencent Hunyuan interactive world model generating real-time, controllable 720p video with memory for consistency.
Model · Runway
Runway's real-time interactive world model generating 720p/24fps video with audio, steered by text actions and camera input.
Model · Tencent ARC Lab
Video world model from Tencent ARC Lab that turns an image or text into camera-controlled explorable scenes with 3D-aware memory.