---
license: mit
library_name: pytorch
datasets:
  - YuCrazing/ClothTransformer-dataset
tags:
  - cloth-simulation
  - physics-simulation
  - transformer
---

# ClothTransformer Checkpoint

Pretrained weights for **ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation** (NeurIPS 2026).

- Paper: https://huggingface.co/papers/2605.27852 ([arXiv](https://arxiv.org/abs/2605.27852))
- Project page: https://yucrazing.github.io/clothtransformer/
- Code: https://github.com/YuCrazing/ClothTransformer
- Dataset: https://huggingface.co/datasets/YuCrazing/ClothTransformer-dataset

## Files

| File | Description |
| --- | --- |
| `ct-no-ccd-preview.pt` | Preview checkpoint used in the repository examples |

## Usage

Install the code following the [repository README](https://github.com/YuCrazing/ClothTransformer), then:

```bash
hf download YuCrazing/ClothTransformer-checkpoint ct-no-ccd-preview.pt --local-dir checkpoints
python scripts/download_data.py --file-list examples/showcase.txt
python main.py infer.ckpt=checkpoints/ct-no-ccd-preview.pt infer.sim=sims_garment_anim_all/sim_00005
```

## Citation

```bibtex
@inproceedings{zhang2026clothtransformer,
  title     = {ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation},
  author    = {Zhang, Yu and Shao, Yidi and Ouyang, Wenqi and Lan, Yushi and Liang, Zhexin and Wu, Chengrui and Xu, Xudong and Pan, Xingang},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2026},
  url       = {https://arxiv.org/abs/2605.27852}
}
```