🚀 [CVPR 2026]WaDi: Weight Direction-aware Distillation for One-step Image Synthesis

Lei Wang¹, Yang Cheng¹, Senmao Li¹, Ge Wu¹, Yaxing Wang^1,3† Jian Yang^1,2†

¹ PCA Lab, VCIP, College of Computer Science, Nankai University    ² PCA Lab, School of Intelligence Science and Technology, Nanjing University    ³ Shenzhen Futian, NKIARI   

†Corresponding authors

📦 Model Weights

Model	Hugging Face	ModelScope
WaDi-SD2.1
WaDi-SD1.5
WaDi-PixArt

🎬 Inference

# inference sd model
python infer_sd_model.py

# inference pixart
python infer_pixart.py

Training SwiftBrushV2

An unofficial implementation of SwiftBrushV2

Citation

If you find WaDi useful, please consider giving our repository a star (⭐) and citing our paper.

@article{wang2026wadi,
  title={WaDi: Weight Direction-aware Distillation for One-step Image Synthesis},
  author={Wang, Lei and Cheng, Yang and Li, Senmao and Wu, Ge and Wang, Yaxing and Yang, Jian},
  journal={arXiv preprint arXiv:2603.08258},
  year={2026}
}
@inproceedings{li2025one,
      title={One-Way Ticket: Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models}, 
      author={Li, Senmao and Wang, Lei and Wang, Kai and Liu, Tao and Xie, Jiehang and van de Weijer, Joost and Khan, Fahad Shahbaz and Yang, Shiqi and Wang, Yaxing and Yang, Jian},
      booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, 
      year={2025},
}

Acknowledgement

This project is based on Diffusers. Thanks for their awesome works. We sincerely acknowledge the excellent and inspiring prior work, TiUE and SwiftBrush.

Contact

If you have any questions, please feel free to reach out to me at scitop1998@gmail.com.