nunchaku qwen image edit 2509
by nunchaku-ai
Open source · 9k downloads · 287 likes
3.1
(287 reviews)ImageAPI & LocalAbout
The *nunchaku qwen image edit 2509* model is an optimized and quantized version of the Qwen-Image-Edit-2509 model, specialized in text-based image editing. It enables precise modifications to existing images, such as style adjustments, element additions, or corrections, while maintaining high visual quality. Its key features include fast inference through lightweight versions (4 or 8 steps) and compatibility with various GPUs, including recent models like the 50 series. This model stands out for its energy efficiency and lightweight design, making it ideal for users looking to integrate image-editing capabilities into applications or workflows without overburdening resources. It is particularly well-suited for content creators, graphic tool developers, or platforms requiring automated retouching. Its 4-bit quantization approach ensures optimized performance without sacrificing quality, while offering customization options based on needs—whether prioritizing speed or precision.
Documentation
Model Card for nunchaku-qwen-image-edit-2509
This repository contains Nunchaku-quantized versions of Qwen-Image-Edit-2509, an image-editing model based on Qwen-Image, advances in complex text rendering. It is optimized for efficient inference while maintaining minimal loss in performance.
News
- [2025-11-15] 🚀 Release new quantized qwen-image-edit-2509 4/8-step lightning models, fused with lightx2v Qwen-Image-Edit-2509 lightning lora. All models are available in the
lightning-251115folder. - [2025-09-25] 🔥 Release 4-bit 4/8-step lightning Qwen-Image-Edit!
- [2025-09-24] 🚀 Release 4-bit SVDQuant quantized Qwen-Image-Edit-2509 model with rank 32 and 128!
Model Details
Model Description
- Developed by: Nunchaku Team
- Model type: image-to-image
- License: apache-2.0
- Quantized from model: Qwen-Image-Edit-2509
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-edit-2509.safetensors | |
| r128 | svdq-int4_r128-qwen-image-edit-2509.safetensors | ||
| NVFP4 | r32 | svdq-fp4_r32-qwen-image-edit-2509.safetensors | |
| r128 | svdq-fp4_r128-qwen-image-edit-2509.safetensors |
4-Step Distilled Models
4-step distilled models fused with Qwen-Image-Lightning-4steps-V2.0 LoRA or Qwen-Image-Edit-2509-Lightning-4steps-V1.0 LoRA using LoRA strength = 1.0
8-Step Distilled Models
8-step distilled models fused with Qwen-Image-Lightning-8steps-V2.0 LoRA or Qwen-Image-Edit-2509-Lightning-8steps-V1.0 LoRA using LoRA strength = 1.0
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
- Diffusers Usage: See qwen-image-edit-2509.py. Check this tutorial for more advanced usage.
- ComfyUI Usage: See nunchaku-qwen-image-edit-2509.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}
}
Capabilities & Tags
diffusersimage-editingSVDQuantQwen-Image-Edit-2509DiffusionQuantizationICLR2025text-to-imageen
Links & Resources