Video Runtime
Developer-onlyFrame-StreamingOfficial source

MineWorld

A Minecraft-specific interactive video world model with downloadable checkpoints and a local web demo.

Access and release status are source-checked descriptions, not a live uptime check. A reachable website does not establish that video playback or interaction currently works.

View GitHub ↗

No rights-cleared product preview yet. See the official page for its latest interface.

Published by Video Runtime · Source check 2026-09-14 · Evidence method · Suggest a correction

EDITORIALLY VERIFIED PRODUCT INFORMATION

About MineWorld

A Minecraft-specific interactive video world model with downloadable checkpoints and a local web demo. Predicts the next Minecraft video state from an initial scene, previous frames and discrete player or camera actions.

Key features

Offers several model sizes, checkpoint links, local inference, a browser demo and scripts for reproducing the paper's evaluation metrics.

Getting started

Download the selected model and VAE checkpoints plus the sample scene files, launch mineworld.py for the web demo, and keep inputs within the documented Minecraft domain.

Real-time interaction

Predicts the next Minecraft video state from an initial scene, previous frames and discrete player or camera actions.

Pricing

MIT code; self-hosted compute costs extra Repository code is published under MIT. Confirm separate model, dataset and dependency terms before reuse. No hosted price is inferred. Budget for the documented GPU, storage and setup requirements.

Limitations

The model is trained only on Minecraft and maintainers warn that other domains, higher resolutions and production use are outside its intended scope.

Read the documentation ↗

EDITORIAL VIEW

Editor's Verdict

MineWorld 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

  • Predicts the next Minecraft video state from an initial scene, previous frames and discrete player or camera actions.

What We Like

  • Offers several model sizes, checkpoint links, local inference, a browser demo and scripts for reproducing the paper's evaluation metrics.

Current Limitations

  • The model is trained only on Minecraft and maintainers warn that other domains, higher resolutions and production use are outside its intended scope.

Pricing & Access

  • Repository code is published under MIT. 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 2026-09-14. 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 maintainers describe MineWorld as real-time, but the inspected README does not provide one hardware-normalised end-to-end latency figure.

Technical Notes

  • Configurations span 300M to 1.2B parameters and 16- or 32-frame variants; diagonal decoding is optional.

Sources

  1. Official GitHub repository ↗github · accessed 2026-09-14
  2. Code licence ↗github · accessed 2026-09-14

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

Read how official-source and hands-on records stay separate in our Methodology.