EA-WM checkpoints

Official checkpoints for EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields.

• Paper: https://arxiv.org/abs/2605.06192
• Code and documentation: https://github.com/Shownx-c/EA-WM
• Base model: https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B

Files

File	Contents	Intended use
stage1.safetensors	Main-DiT LoRA, KVAF-branch LoRA, KVAF head	Initialize Stage 2
stage2.safetensors	Stage 1 components and event-aware bidirectional fusion	Inference and evaluation

These files contain EA-WM adapters and auxiliary branch weights, not the Wan2.2 base weights. Follow the repository README to install the code, download the base model, and run training or inference.

Download

hf download shown21/EA-WM \
  stage1.safetensors stage2.safetensors \
  --local-dir weights

Checkpoint metadata

Both files use the public EA-WM parameter names and record the architecture, stage, base model, LoRA rank (32), and fusion interval (5) in their safetensors metadata.

Citation

@article{yang2026eawm,
  title   = {EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields},
  author  = {Yang, Zhaoyang and Jin, Yurun and Qi, Lizhe and Chen, Kai and Huang, Cong},
  journal = {arXiv preprint arXiv:2605.06192},
  year    = {2026}
}

License

The EA-WM code and released checkpoint files are provided under Apache-2.0. Use of the Wan2.2 base model and datasets remains subject to their respective terms.