SVDQuant
Collection
Models and datasets for "SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models" • 19 items • Updated • 64
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("mit-han-lab/nunchaku", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This repository has been migrated to https://huggingface.co/nunchaku-tech/nunchaku and will be hidden in December 2025.
Nunchaku Pre-built Wheels
This repository provides pre-built wheels for nunchaku for both Linux and Windows platforms. For detailed information about available wheels, please visit our GitHub Releases page.
Citation
@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}
}
- Downloads last month
- -