Published by Video Runtime · Source check 2026-09-21 · Evidence method · Suggest a correction
EDITORIALLY VERIFIED PRODUCT INFORMATION
About AlayaVista
A camera-controllable streaming video world model that grows a 360° scene prior from a single perspective image. AlayaVista builds a 360° scene prior from one view, evolves camera-conditioned panoramic latent states, then synthesises the requested perspective through latent viewport rendering and local refinement. Chunk-autoregressive generation with few-step distillation concentrates high-fidelity synthesis on the viewport you choose.
Key features
The panoramic-state design keeps whole-scene context while rendering only the selected view. A technical report and project page document the method ahead of code.
Getting started
Read the project page and technical report while awaiting the roadmap's inference-code and checkpoint releases; there is nothing to install yet.
Real-time interaction
AlayaVista builds a 360° scene prior from one view, evolves camera-conditioned panoramic latent states, then synthesises the requested perspective through latent viewport rendering and local refinement. Chunk-autoregressive generation with few-step distillation concentrates high-fidelity synthesis on the viewport you choose.
Pricing
No released code, weights or licence yet; nothing to self-host Repository code is published under No licence declared yet. Confirm separate model, dataset and dependency terms before reuse. No hosted price is inferred. Budget for the documented GPU, storage and setup requirements.
Limitations
Inference code and pretrained weights are listed on the release roadmap but were not published at the time of this check. No licence has been declared in the repository, so reuse terms are currently undefined.
EDITORIAL VIEW
Editor's Verdict
AlayaVista is included as a source-available implementation relevant to real-time generative video or interactive world systems.
Run the supplied example on representative hardware and review every linked licence before production use.
How It Works
- AlayaVista builds a 360° scene prior from one view, evolves camera-conditioned panoramic latent states, then synthesises the requested perspective through latent viewport rendering and local refinement.
- Chunk-autoregressive generation with few-step distillation concentrates high-fidelity synthesis on the viewport you choose.
What We Like
- The panoramic-state design keeps whole-scene context while rendering only the selected view.
- A technical report and project page document the method ahead of code.
Current Limitations
- Inference code and pretrained weights are listed on the release roadmap but were not published at the time of this check.
- No licence has been declared in the repository, so reuse terms are currently undefined.
Pricing & Access
- Repository code is published under No licence declared yet. Confirm separate model, dataset and dependency terms before reuse.
- No hosted price is inferred. Budget for the documented GPU, storage and setup requirements.
Verification Summary
- Official repository and licence reviewed on 2026-09-21. Video Runtime has not installed or benchmarked this project.
- Performance and compatibility statements below are attributed to the maintainers and are not site measurements.
Technical notes & official performance
Official Performance Data
- The README describes efficient streaming via chunk-autoregressive generation and few-step distillation but publishes no FPS or latency figure. Video Runtime has not measured anything.
Technical Notes
- The paper is on arXiv (2609.14462); the repository currently ships the project page, paper link and roadmap.
Sources
- Official GitHub repository ↗github · accessed 2026-09-21
- Code licence ↗github · accessed 2026-09-21
- Official project page ↗official-docs · accessed 2026-09-21
Access, stage & mechanism
These are separate source-checked facts, not a live uptime monitor. Unverified fields are left open; transport and persistent sessions do not establish how frames are generated.
- Release stage
- Not verified
- Access mode
- Not verified
- Source availability
- Not verified
- Transport
- Not verified
- Interaction
- Not verified
- Session mode
- Not verified
- Generation mechanism
- Not verified
- Continuity method
- Not verified
- Licence status
- Not verified
- Tasks
- Not classified
CONTINUE EXPLORING
Related projects & models
Selected by research links and category, not by popularity.
Generate continuing interactive worlds with bounded external state, mid-rollout prompts and camera control.
Another frame streaming option in this section.Public repository; self-hosted setup and compatible GPU requiredBuild long-horizon playable video worlds with camera control, prompt switching and explicit spatial memory.
Another frame streaming option in this section.Public repository; self-hosted setup and compatible GPU required
Run an action-conditioned interactive world model with open-ended rollout on a single desktop GPU.
Another frame streaming option in this section.Public repository; self-hosted installation and compatible GPU required
Train few-step autoregressive video generators with frame-wise and chunk-wise Causal Forcing variants.
Another frame streaming option in this section.Public repository; self-hosted setup and compatible GPU requiredRead how official-source and hands-on records stay separate in our Methodology.