--- base_model: Efficient-Large-Model/Sana_1600M_1024px base_model_relation: quantized datasets: - mit-han-lab/svdquant-datasets language: - en library_name: diffusers license: other license_link: https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px/blob/main/LICENSE.txt license_name: nvidia-license pipeline_tag: text-to-image tags: - text-to-image - SVDQuant - SANA - Diffusion - Quantization - ICLR2025 ---

Nunchaku Logo

# Model Card for nunchaku-sana ![visual](https://huggingface.co/datasets/nunchaku-tech/cdn/resolve/main/nunchaku/app/sana/t2i.jpg) This repository contains Nunchaku-quantized versions of [SANA-1.6B](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px), designed to generate high-quality images from text prompts. It is optimized for efficient inference while maintaining minimal loss in performance. ## Model Details ### Model Description - **Developed by:** Nunchaku Team - **Model type:** text-to-image - **License:** [NVIDIA License](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px/blob/main/LICENSE.txt) - **Quantized from model:** [Sana_1600M_1024px](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px) ### Model Files - [`svdq-int4_r32-sana1.6b.safetensors`](./svdq-int4_r32-sana1.6b.safetensors): SVDQuant quantized INT4 SANA-1.6B model. For users with non-Blackwell GPUs (pre-50-series). ### Model Sources - **Inference Engine:** [nunchaku](https://github.com/nunchaku-tech/nunchaku) - **Quantization Library:** [deepcompressor](https://github.com/nunchaku-tech/deepcompressor) - **Paper:** [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](http://arxiv.org/abs/2411.05007) - **Demo:** [svdquant.mit.edu](https://svdquant.mit.edu) ## Usage See [sana1.6b.py](https://github.com/nunchaku-tech/nunchaku/blob/main/examples/sana1.6b.py). ## Performance ![performance](https://huggingface.co/datasets/nunchaku-tech/cdn/resolve/main/nunchaku/assets/efficiency.jpg) ## 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} } ```