Video Runtime
Developer-onlyFrame-StreamingOfficial source

Self Forcing

A research baseline for streaming video generation that trains models on their own autoregressive outputs.

Open Documentation ↗View GitHub ↗

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

EDITORIAL VIEW

Editor's Verdict

Consider Self Forcing if its documented workflow matches your experiment; start from the linked repository rather than an unofficial mirror.

Check the licence and run a small local evaluation before choosing it for production. No ratings or measured results are inferred from its publication.

How It Works

  • Simulates autoregressive inference during training and reuses attention state to reduce the mismatch between training and generation.

What We Like

  • Publishes inference, training and a local interactive demo, providing a useful baseline for streaming-video research.

Current Limitations

  • Authors specify Linux, at least 24 GB of NVIDIA GPU memory and 64 GB system RAM. This is not a hosted one-click consumer service.

Pricing & Access

  • Repository code: Apache-2.0. Model weights and dependencies may have separate terms.
  • No hosted price is estimated here. Budget for your own GPU or cloud usage after testing a representative workload.

Verification Summary

  • Official repository and licence reviewed on 2026-09-05. Video Runtime has not installed or benchmarked this project.
  • This is a source review, not verification of demo uptime, output quality or performance on your hardware.
Technical notes & official performance

Official Performance Data

  • The authors report real-time streaming on a single RTX 4090. This is an author claim, not a Video Runtime hands-on measurement.

Technical Notes

  • Requires the documented Wan components and Self Forcing checkpoints. Lightweight decoding and lower precision can trade quality for speed.

Sources

  1. Official GitHub repository ↗github · accessed 2026-09-05
  2. Code licence ↗github · accessed 2026-09-05
  3. Official project documentation ↗official-docs · accessed 2026-09-05

FROM PEOPLE WHO HAVE TRIED IT

User experiences

Reviewed community contributions, kept separate from our research and hands-on tests.

No published experiences yet. Tried this project? Share what worked and what didn’t.

Sharing experiences will open once email sign-in and submission protection are ready. You can still send a correction.

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