Published by Video Runtime · Source check 2026-09-14 · Evidence method · Suggest a correction
EDITORIALLY VERIFIED PRODUCT INFORMATION
About SolarWM
An open data, training and inference stack for building long-horizon interactive video world models. Trains causal video generators on short sequences, then rolls them out autoregressively with action conditioning across Wan, LTX and MiniMax-H3 backbones.
Key features
Publishes data preparation, scalable training, inference code, evaluation assets and multiple model-stage checkpoints.
Getting started
Install the backbone-specific environment, download the matching checkpoints, use the standalone test set or request prepared data, then run the repository's example inference configuration before training.
Real-time interaction
Trains causal video generators on short sequences, then rolls them out autoregressively with action conditioning across Wan, LTX and MiniMax-H3 backbones.
Pricing
Apache-2.0 code; self-hosted compute costs extra Repository code is published under Apache-2.0. Confirm separate model, dataset and dependency terms before reuse. No hosted price is inferred. Budget for the documented GPU, storage and setup requirements.
Limitations
Prepared training data requires an access request, the standalone evaluation set is about 77.4 GB, and full training examples use multi-GPU execution.
EDITORIAL VIEW
Editor's Verdict
SolarWM 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
- Trains causal video generators on short sequences, then rolls them out autoregressively with action conditioning across Wan, LTX and MiniMax-H3 backbones.
What We Like
- Publishes data preparation, scalable training, inference code, evaluation assets and multiple model-stage checkpoints.
Current Limitations
- Prepared training data requires an access request, the standalone evaluation set is about 77.4 GB, and full training examples use multi-GPU execution.
Pricing & Access
- Repository code is published under Apache-2.0. 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
- Maintainers say models trained on five-second sequences can roll out interactively for minutes to hours. Video Runtime has not reproduced that claim.
Technical Notes
- The September 2026 release adds MiniMax-H3 training and inference paths; backbone packages and weights retain their own licences.
Sources
- Official GitHub repository ↗github · accessed 2026-09-14
- Code licence ↗github · accessed 2026-09-14
- Official project page ↗official-docs · 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
CONTINUE EXPLORING
Related projects & models
Selected by research links and category, not by popularity.
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 required
Train playable action-conditioned video world models with an open progressive causal recipe.
Another frame streaming option in this section.Public repository; self-hosted setup and compatible GPU required
Learn and reproduce the full pipeline for converting video diffusion backbones into interactive world models.
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 requiredRead how official-source and hands-on records stay separate in our Methodology.