Instructions to use junchaoh-cs/SolarWM-Wan2.2-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Wan2.2
How to use junchaoh-cs/SolarWM-Wan2.2-14B with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
SolarWM-Wan2.2-14B
Wan2.2 I2V-A14B checkpoints for SolarWM
Project Page · GitHub · SolarWM Collection · Dataset · Paper
SolarWM is an open foundation for building interactive video world models from data preparation through scalable training and long-horizon inference. This repository contains only the Wan2.2 I2V-A14B family.
Checkpoints
| Directory | Stage | Frames | Release contents |
|---|---|---|---|
SolarWM-14B-base-high |
Base | — | High-noise expert and runtime assets |
SolarWM-14B-bid-stage0p5-81f |
Stage0.5 | 81 | Bidirectional camera-conditioned checkpoint |
Download
hf download junchaoh-cs/SolarWM-Wan2.2-14B --local-dir ./SolarWM-models
Keep the directory layout unchanged. SolarWM configurations resolve the base and staged checkpoint paths from these release directories.
Inference
Install SolarWM from the source repository, activate the Wan runtime environment, and follow the Wan2.2 I2V-A14B guide.
License
SolarWM code is released under Apache-2.0. Model weights and bundled backbone assets remain subject to the license and notices included in each release directory; they are not relicensed by SolarWM.
Citation
@misc{huang2026solarwmopendatascalable,
title={SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models},
author={Junchao Huang and Guian Fang and Shengju Qian and Xianghao Kong and Zhuoran Zhao and Wei Huang and Yihua Du and Zixin Zhang and Justin Cui and Yuchao Gu and Yukang Chen and Xinting Hu and Tianyu He and Shaoshuai Shi and Zhuotao Tian and Xin Wang and Mike Zheng Shou and Li Jiang},
year={2026}, eprint={2609.02886}, archivePrefix={arXiv}, primaryClass={cs.CV},
url={https://arxiv.org/abs/2609.02886}
}