worstcoder/rcm-Wan

rCM: Score-Regularized Continuous-Time Consistency Model

Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models

Paper Paper2 | Website | Code

This repo holds unofficial rCM and Causal-rCM models for Wan, reproduced by Tsinghua University.

The Wan2.2 rCM checkpoints are obtained by merging Wan2.1 rCM weights to Wan2.2 checkpoints, no extra training included. Should have the same effect as directly using the Wan2.1 rCM LoRAs (https://huggingface.co/Kijai/WanVideo_comfy/tree/main/LoRAs/rCM) and adjusting the strength.

Citation

@article{zheng2025rcm,
  title={Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency},
  author={Zheng, Kaiwen and Wang, Yuji and Ma, Qianli and Chen, Huayu and Zhang, Jintao and Balaji, Yogesh and Chen, Jianfei and Liu, Ming-Yu and Zhu, Jun and Zhang, Qinsheng},
  journal={arXiv preprint arXiv:2510.08431},
  year={2025}
}
@article{zheng2026causal,
  title={Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models},
  author={Zheng, Kaiwen and He, Guande and Zhao, Min and Zhang, Jintao and Chen, Huayu and Chen, Jianfei and Lin, Chen-Hsuan and Liu, Ming-Yu and Zhu, Jun and Ma, Qianli},
  journal={arXiv preprint arXiv:2606.25473},
  year={2026}
}