Qwen-Image-Edit by Comfy-Org

Qwen-Image-Edit by Comfy-Org

Repackaged Qwen-Image-Edit model files and LoRAs for ComfyUI, with workflows that edit a picture from a written instruction. For ComfyUI users who retouch and restyle images.

Made by Comfy-Org on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: This repository holds Qwen-Image-Edit model files repackaged by Comfy-Org so they load in ComfyUI. It is based on Qwen/Qwen-Image-Edit. It has ten diffusion model files in several precisions, six LoRA files, and workflow templates that show an image before and after an edit.

Who it suits: ComfyUI users who want to change an existing picture from a written instruction, on their own computer. The card is short and lists file locations and workflows, so it assumes you already know ComfyUI.

Title: Who uses it, and how
Industry | Who uses it | How they use it | Example
Photo editing | Hobby retouchers | Change part of a picture with a text instruction | Ask for a different outfit colour on a portrait
Design | Designers | Restyle a draft, or change its lighting | Apply a relight LoRA to a product photo
Content creation | Creators | Show one subject from another angle | Use the multiple angles LoRA on a character picture
AI research | ComfyUI tinkerers | Compare the model file precisions | Swap bf16 for fp8 and compare the output

Skip it if you do not use ComfyUI, because the files are packaged for that program.

Where to use it:

• ComfyUI, on Windows, macOS or Linux
• The workflow templates the card lists, such as Qwen Image Edit 2509
• Windows, macOS or Linux for downloading the files, with Python

Use case | Who | What they get back
Instruction editing | Retouchers | An edited version of the picture you load
Lighting changes | Designers | The same scene with different lighting, using a LoRA
Style changes | Creators | A picture restyled with one of the LoRA files
Precision tests | Tinkerers | Output from different model file versions

How to set it up: You need ComfyUI installed, plus Python and pip to download. Then you copy each file into the matching folder inside ComfyUI's models directory.

• ComfyUI
• Python and pip
• Disk space for the model files you choose

1. Install the Hugging Face hub library.
2. Download the repository.
3. Copy the files into ComfyUI folders, then open a workflow.

pip install -U huggingface_hub
hf download Comfy-Org/Qwen-Image-Edit

Title: Where each kind of file goes
Folder | Files
diffusion_models | qwen_image_edit in bf16 and fp8, versions 2509 and 2511 in bf16, fp8mixed and int8 convrot, and firered_image_edit_1.0_bf16
loras | Multiple-angles, Anything2RealAlpha, Fusion, Light-Migration, Relight and White_to_Scene

How to use it: Open one of the card's workflow templates in ComfyUI, load a picture, write your instruction and run it. Pick a diffusion model file that matches your memory, and add a LoRA file only when you want its effect.

Tool | What it does
Qwen Image Edit 2509 workflow | Edits a loaded picture from a text instruction
Qwen Image Edit 2511 Int8 workflow | Runs the 2511 model in its int8 form
LoRA files | Add one extra effect, such as relighting or a new angle
diffusion_models folder | Holds the main edit model file

Example: You load a portrait into the Qwen Image Edit 2509 workflow and write an instruction to change the background. You run the graph and it returns the edited picture. The card shows before and after thumbnails for each workflow.

For newcomers and experts: If you are new, learn the basics of ComfyUI first, then place one diffusion model file and open the 2509 workflow. Run it once with a short instruction before adding any LoRA.

For people in the field, the repository repackages several editing releases, with bf16, fp8 and int8 convrot files. Most LoRAs come from other authors, whom the card credits. The card does not rank the variants or give benchmark figures.

Download the repository
Copy files into ComfyUI folders
Open a Qwen Image Edit workflow
Load a picture and write an instruction
Get the edited picture

Good to know:

• License: Apache 2.0
• Cost to run: none named, you use your own computer
• Data it reaches: it downloads files from Hugging Face, and the card names nothing else it touches
• Not for: use outside ComfyUI, since the card only describes that setup
• The LoRA files come from other authors, so check each one's own terms
• The card gives no benchmark scores or hardware notes

On Hugging Face, 13 November 2026

• Library: diffusion-single-file
• Downloads in the last 30 days: 1,898,657
• Likes: 521
• License: apache-2.0
• Based on: Qwen/Qwen-Image-Edit
• Quantized versions: 4
• Tags: diffusion-single-file, comfyui

Links

• Model: https://huggingface.co/Comfy-Org/Qwen-Image-Edit
• Files: https://huggingface.co/Comfy-Org/Qwen-Image-Edit/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download Comfy-Org/Qwen-Image-Edit

Then follow the usage in its model card. Nothing in this kit runs by itself.