Published by Video Runtime · Source check 2026-09-14 · Evidence method · Suggest a correction
EDITORIALLY VERIFIED PRODUCT INFORMATION
About minWM
Learn and reproduce the full pipeline for converting video diffusion backbones into interactive world models. Provides staged bidirectional fine-tuning, autoregressive training, causal initialization and few-step distillation across multiple backbones.
Key features
Publishes a structured tutorial, training code, inference code, weights and example data for HunyuanVideo and Wan-based pipelines.
Getting started
Open the official repository, read its current README and licence, then follow the documented environment, checkpoint and inference steps. Start with the supplied example before using your own media or data.
Real-time interaction
Provides staged bidirectional fine-tuning, autoregressive training, causal initialization and few-step distillation across multiple backbones.
Pricing
Apache-2.0; compute costs extra 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.
Limitations
Reproducing the complete training path requires multiple large checkpoints, substantial storage and multi-GPU resources.
EDITORIAL VIEW
Editor's Verdict
Consider minWM 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
- Provides staged bidirectional fine-tuning, autoregressive training, causal initialization and few-step distillation across multiple backbones.
What We Like
- Publishes a structured tutorial, training code, inference code, weights and example data for HunyuanVideo and Wan-based pipelines.
Current Limitations
- Reproducing the complete training path requires multiple large checkpoints, substantial storage and multi-GPU resources.
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 2026-09-14. 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 released DMD checkpoints target four-step real-time inference. Actual FPS varies by backbone, resolution and hardware and was not measured here.
Technical Notes
- A September infrastructure revision changed the repository layout; users of older instructions should consult the migration guide.
Sources
- Official GitHub repository ↗github · accessed 2026-09-14
- 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
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 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 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
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.