mirror of
https://www.modelscope.cn/nunchaku-tech/nunchaku-qwen-image.git
synced 2026-04-02 18:42:53 +08:00
92 lines
7.4 KiB
Markdown
92 lines
7.4 KiB
Markdown
---
|
|
base_model: Qwen/Qwen-Image
|
|
base_model_relation: quantized
|
|
datasets:
|
|
- mit-han-lab/svdquant-datasets
|
|
frameworks: PyTorch
|
|
language:
|
|
- en
|
|
license: Apache License 2.0
|
|
tags:
|
|
- text-to-image
|
|
- SVDQuant
|
|
- Qwen-Image
|
|
- Diffusion
|
|
- Quantization
|
|
- ICLR2025
|
|
tasks:
|
|
- text-to-image-synthesis
|
|
|
|
---
|
|
<p align="center" style="border-radius: 10px">
|
|
<img src="https://huggingface.co/datasets/nunchaku-tech/cdn/resolve/main/nunchaku/assets/nunchaku.svg" width="30%" alt="Nunchaku Logo"/>
|
|
</p>
|
|
|
|
<div align="center">
|
|
<a href=https://discord.gg/Wk6PnwX9Sm target="_blank"><img src=https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Finvites%2FWk6PnwX9Sm%3Fwith_counts%3Dtrue&query=%24.approximate_member_count&logo=discord&logoColor=white&label=Discord&color=green&suffix=%20total height=22px></a>
|
|
<a href=https://huggingface.co/datasets/nunchaku-tech/cdn/resolve/main/nunchaku/assets/wechat.jpg target="_blank"><img src=https://img.shields.io/badge/WeChat-07C160?logo=wechat&logoColor=white height=22px></a>
|
|
</div>
|
|
|
|
# Model Card for nunchaku-qwen-image
|
|
|
|
|
|
This repository contains Nunchaku-quantized versions of [Qwen-Image](https://huggingface.co/Qwen/Qwen-Image), designed to generate high-quality images from text prompts, advances in complex text rendering. It is optimized for efficient inference while maintaining minimal loss in performance.
|
|
|
|
## News
|
|
|
|
- [2025-08-27] 🔥 Release **4-bit [4/8-step lightning Qwen-Image](https://huggingface.co/lightx2v/Qwen-Image-Lightning)**!
|
|
- [2025-08-15] 🚀 Release 4-bit SVDQuant quantized Qwen-Image model with rank 32 and 128!
|
|
|
|
|
|
## Model Details
|
|
|
|
### Model Description
|
|
|
|
- **Developed by:** Nunchaku Team
|
|
- **Model type:** text-to-image
|
|
- **License:** apache-2.0
|
|
- **Quantized from model:** [Qwen-Image](https://huggingface.co/Qwen/Qwen-Image)
|
|
|
|
### Model Files
|
|
|
|
- [`svdq-int4_r32-qwen-image.safetensors`](./svdq-int4_r32-qwen-image.safetensors): SVDQuant INT4 (rank 32) Qwen-Image model. For users with non-Blackwell GPUs (pre-50-series).
|
|
- [`svdq-int4_r128-qwen-image.safetensors`](./svdq-int4_r128-qwen-image.safetensors): SVDQuant INT4 (rank 128) Qwen-Image model. For users with non-Blackwell GPUs (pre-50-series). It offers better quality than the rank 32 model, but it is slower.
|
|
- [`svdq-int4_r32-qwen-image-lightningv1.0-4steps.safetensors`](./svdq-int4_r32-qwen-image-lightningv1.0-4steps.safetensors): SVDQuant INT4 (rank 32) 4-step Qwen-Image model by fusing [Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors) using LoRA strength = 1.0. For users with non-Blackwell GPUs (pre-50-series).
|
|
- [`svdq-int4_r128-qwen-image-lightningv1.0-4steps.safetensors`](./svdq-int4_r128-qwen-image-lightningv1.0-4steps.safetensors): SVDQuant INT4 (rank 128) 4-step Qwen-Image model by fusing [Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors) using LoRA strength = 1.0. For users with non-Blackwell GPUs (pre-50-series).
|
|
- [`svdq-int4_r32-qwen-image-lightningv1.1-8steps.safetensors`](./svdq-int4_r32-qwen-image-lightningv1.1-8steps.safetensors): SVDQuant INT4 (rank 32) 8-step Qwen-Image model by fusing [Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors) using LoRA strength = 1.0. For users with non-Blackwell GPUs (pre-50-series).
|
|
- [`svdq-int4_r128-qwen-image-lightningv1.1-8steps.safetensors`](./svdq-int4_r128-qwen-image-lightningv1.1-8steps.safetensors): SVDQuant INT4 (rank 128) 8-step Qwen-Image model by fusing [Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors) using LoRA strength = 1.0. For users with non-Blackwell GPUs (pre-50-series).
|
|
- [`svdq-fp4_r32-qwen-image.safetensors`](./svdq-fp4_r32-qwen-image.safetensors): SVDQuant NVFP4 (rank 32) Qwen-Image model. For users with Blackwell GPUs (50-series).
|
|
- [`svdq-fp4_r128-qwen-image.safetensors`](./svdq-fp4_r128-qwen-image.safetensors): SVDQuant NVFP4 (rank 128) Qwen-Image model. For users with Blackwell GPUs (50-series). It offers better quality than the rank 32 model, but it is slower.
|
|
- [`svdq-fp4_r32-qwen-image-lightningv1.0-4steps.safetensors`](./svdq-fp4_r32-qwen-image-lightningv1.0-4steps.safetensors): SVDQuant NVFP4 (rank 32) 4-step Qwen-Image model by fusing [Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors) using LoRA strength = 1.0. For users with Blackwell GPUs (50-series).
|
|
- [`svdq-fp4_r128-qwen-image-lightningv1.0-4steps.safetensors`](./svdq-fp4_r128-qwen-image-lightningv1.0-4steps.safetensors): SVDQuant NVFP4 (rank 128) 4-step Qwen-Image model by fusing [Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors) using LoRA strength = 1.0. For users with Blackwell GPUs (50-series).
|
|
- [`svdq-fp4_r32-qwen-image-lightningv1.1-8steps.safetensors`](./svdq-fp4_r32-qwen-image-lightningv1.1-8steps.safetensors): SVDQuant NVFP4 (rank 32) 8-step Qwen-Image model by fusing [Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors) using LoRA strength = 1.0. For users with Blackwell GPUs (50-series).
|
|
- [`svdq-fp4_r128-qwen-image-lightningv1.1-8steps.safetensors`](./svdq-fp4_r128-qwen-image-lightningv1.1-8steps.safetensors): SVDQuant NVFP4 (rank 128) 8-step Qwen-Image model by fusing [Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors) using LoRA strength = 1.0. For users with Blackwell GPUs (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
|
|
|
|
- Diffusers Usage: See [qwen-image.py](https://github.com/nunchaku-tech/nunchaku/blob/main/examples/v1/qwen-image.py) and [qwen-image-lightning.py](https://github.com/nunchaku-tech/nunchaku/blob/main/examples/v1/qwen-image-lightning.py).
|
|
- ComfyUI Usage: See [nunchaku-qwen-image.json](https://nunchaku.tech/docs/ComfyUI-nunchaku/workflows/qwenimage.html#nunchaku-qwen-image-json).
|
|
|
|
## 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}
|
|
}
|
|
``` |