Modelpublic

mit-han-lab/svdq-int4-sana-1600m

sourceHugging Faceotherupdated 1y agoView on Hugging Face

3likes110downloads

Model Card

This repository has been deprecated and will be hidden in December 2025. Please use https://huggingface.co/nunchaku-tech/nunchaku-sana.

Model Card for svdq-int4-sana-1600m

Model Details

Model Description

—Developed by: Nunchaku Team
—Model type: text-to-image
—License: NVIDIA License
—Quantized from model: Sana_1600M_1024px

Model Sources

—Inference Engine: nunchaku
—Quantization Library: deepcompressor
—Paper: SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
—Demo: svdquant.mit.edu

Usage

See sana1.6b.py.

Performance

performance

Citation

bibtex

@inproceedings{
  li2024svdquant,
  title={SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models},
  author={Li*, Muyang and Lin*, Yujun and Zhang*, Zhekai and Cai, Tianle and Li, Xiuyu and Guo, Junxian and Xie, Enze and Meng, Chenlin and Zhu, Jun-Yan and Han, Song},
  booktitle={The Thirteenth International Conference on Learning Representations},
  year={2025}
}
@article{
  xie2024sana,
  title={Sana: Efficient high-resolution image synthesis with linear diffusion transformers},
  author={Xie, Enze and Chen, Junsong and Chen, Junyu and Cai, Han and Tang, Haotian and Lin, Yujun and Zhang, Zhekai and Li, Muyang and Zhu, Ligeng and Lu, Yao and others},
  journal={arXiv preprint arXiv:2410.10629},
  year={2024}
}