SDXL
Collection
2 items • Updated • 3
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("nunchaku-ai/nunchaku-sdxl", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]
Model Card for nunchaku-sdxl
This repository contains Nunchaku-quantized versions of stable-diffusion-xl-base-1.0, designed to generate high-quality images from text prompts. It is optimized for efficient inference while maintaining minimal loss in performance.
No recent news. Stay tuned for updates!
Model Details
Model Description
- Developed by: Nunchaku Team (thank @devgdovg)
- Model type: text-to-image
- License: openrail++
- Quantized from model: stable-diffusion-xl-base-1.0
Model Files
svdq-int4_r32-sdxl.safetensors: SVDQuant quantized INT4 SDXL model. For users with non-Blackwell GPUs (pre-50-series).
Model Sources
- Inference Engine: nunchaku
- Quantization Library: deepcompressor
- Paper: SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
- Demo: demo.nunchaku.tech
Usage
Performance
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
- 99
Model tree for nunchaku-ai/nunchaku-sdxl
Base model
stabilityai/stable-diffusion-xl-base-1.0