---
base_model: Qwen/Qwen-Image
base_model_relation: quantized
datasets:
- mit-han-lab/svdquant-datasets
language:
- en
library_name: diffusers
license: apache-2.0
pipeline_tag: text-to-image
tags:
- text-to-image
- SVDQuant
- Qwen-Image
- Diffusion
- Quantization
- ICLR2025

---
<p align="center" style="border-radius: 10px">
  <img src="https://huggingface.co/datasets/nunchaku-tech/cdn/resolve/main/nunchaku/assets/nunchaku_v2.png" 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

![comfyui](https://huggingface.co/datasets/nunchaku-tech/cdn/resolve/main/ComfyUI-nunchaku/workflows/nunchaku-qwen-image.png)![visual](https://huggingface.co/datasets/nunchaku-tech/cdn/resolve/main/nunchaku/assets/qwen-image.jpg)
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

**Data Type**: `INT4` for non-Blackwell GPUs (pre-50-series), `NVFP4` for Blackwell GPUs (50-series).
**Rank**: `r32` for faster inference, `r128` for better quality but slower inference.





### Base Models

Standard inference speed models for general use


| Data Type | Rank | Model Name | Comment |
|-----------|------|----------|---------|
| INT4 | r32 | [`svdq-int4_r32-qwen-image.safetensors`](./svdq-int4_r32-qwen-image.safetensors) |  |
|  | r128 | [`svdq-int4_r128-qwen-image.safetensors`](./svdq-int4_r128-qwen-image.safetensors) |  |
| NVFP4 | r32 | [`svdq-fp4_r32-qwen-image.safetensors`](./svdq-fp4_r32-qwen-image.safetensors) |  |
|  | r128 | [`svdq-fp4_r128-qwen-image.safetensors`](./svdq-fp4_r128-qwen-image.safetensors) |  |





### 4-Step Distilled Models

4-step distilled models fused with [Qwen-Image-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors) using LoRA strength = 1.0


| Data Type | Rank | Model Name | Comment |
|-----------|------|----------|---------|
| INT4 | r32 | [`svdq-int4_r32-qwen-image-lightningv1.0-4steps.safetensors`](./svdq-int4_r32-qwen-image-lightningv1.0-4steps.safetensors) | Fused with [Qwen-Image-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors) |
|  | r128 | [`svdq-int4_r128-qwen-image-lightningv1.0-4steps.safetensors`](./svdq-int4_r128-qwen-image-lightningv1.0-4steps.safetensors) | Fused with [Qwen-Image-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors). Better quality, slower inference |
| NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-lightningv1.0-4steps.safetensors`](./svdq-fp4_r32-qwen-image-lightningv1.0-4steps.safetensors) | Fused with [Qwen-Image-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors) |
|  | r128 | [`svdq-fp4_r128-qwen-image-lightningv1.0-4steps.safetensors`](./svdq-fp4_r128-qwen-image-lightningv1.0-4steps.safetensors) | Fused with [Qwen-Image-Lightning-4steps-V1.0 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors). Better quality, slower inference |





### 8-Step Distilled Models

8-step distilled models fused with [Qwen-Image-Lightning-8steps-V1.1 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors) using LoRA strength = 1.0


| Data Type | Rank | Model Name | Comment |
|-----------|------|----------|---------|
| INT4 | r32 | [`svdq-int4_r32-qwen-image-lightningv1.1-8steps.safetensors`](./svdq-int4_r32-qwen-image-lightningv1.1-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V1.1 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors) |
|  | r128 | [`svdq-int4_r128-qwen-image-lightningv1.1-8steps.safetensors`](./svdq-int4_r128-qwen-image-lightningv1.1-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V1.1 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors). Better quality, slower inference |
| NVFP4 | r32 | [`svdq-fp4_r32-qwen-image-lightningv1.1-8steps.safetensors`](./svdq-fp4_r32-qwen-image-lightningv1.1-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V1.1 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors) |
|  | r128 | [`svdq-fp4_r128-qwen-image-lightningv1.1-8steps.safetensors`](./svdq-fp4_r128-qwen-image-lightningv1.1-8steps.safetensors) | Fused with [Qwen-Image-Lightning-8steps-V1.1 LoRA](https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V1.1-bf16.safetensors). Better quality, slower inference |





### 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:** [demo.nunchaku.tech](https://demo.nunchaku.tech)

## 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

![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}
}
```