Aitrepreneur
patreon
1-Click INSTALL QWEN IMAGE EDIT AI IMAGE EDITING KING ComfyUI WebUI!
🕑 Added 2025-08-21 19:28:02 +0000 UTCHey everyone! I've created a 1-click installer for THE NEW MULTIMODAL AI KING!", called "QWEN IMAGE EDIT" made by the same team that created Qwen image. A multimodal model that is able to automatically edits images with incredible precision and that follows your prompt better than Kontext.
You can check out the video right here: https://youtu.be/6EVVV2lUMFU
The workflow: https://www.patreon.com/posts/137036479
The installer of course automates the entire install process for comfyUI and the models downloads!
LOCAL INSTALL!!! RECOMMENDED TO START FROM SCRATCH SINCE YOU NEED THE LATEST COMFYUI TORCH VERSION!!!
Download the QWEN-IMAGE-EDIT-COMFYUI-MANAGER_AUTO_INSTALL.bat
Run the bat file and select either option 1, 2 or 3 depending on your GPU vram.
Wait for the install to finish
The webui will launch, load the QWEN_IMAGE_EDIT_WORKFLOW.json file and there you goπ
DON'T FORGET TO GO UPDATE COMFYUI BY GOING INSIDE THE UPDATE FOLDER AND RUNNING THE COMFYUI UPDATE BAT FILE!!!!
IF YOU ALREADY HAVE COMFYUI INSTALLED USING A PREVIOUS INSTALLER:
Download the QWEN-IMAGE-EDIT-MODELS-NODES_INSTALL.bat and place it in the ComfyUI_windows_portable\ComfyUI folder
Run the bat file and select either option 1, 2 or 3 depending on your GPU vram.
Wait for the install to finish
???
Profit π
IF YOU GET AN ERROR WHEN LAUNCHING COMFYUI AFTER USING THIS INSTALLER SAYING "AssertionError: Torch not compiled with CUDA enabled" it's ok don't panic.
Just go inside the python embedded folder, click on the folder path, type cmd press enter, this will bring the command prompt window and there type:
python.exe -m pip uninstall torch
python.exe -s -m pip install --upgrade torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
--->replace cu128 by your cuda version (if you don't know your cuda version just open a new cmd window and type nvcc --version it will then tell you at the end Cuda compilation tools, release 12.8, V12.8.93 or something different like 12.6, in that case just use cu126 instead of cu128)
IF YOU ARE USING RUNPOD:
Create an account if you haven't already: Runpod
Click on Pod (on the left side) then click deploy
Choose a GPU with at least 24gb of VRAM (4090 is best), click here for the comfyui template (aitrepreneur/comfyui), then edit the template and choose 100gb for both the container and volume disk, then deploy on demand
Go to my pods, wait for everything to finish and then click "connect", then "Connect to HTTP SERVICE port 3000" and click on the manager to update comfyui and restart it
Then go to the port 8888, go inside the comfyui folder and then drag and drop the QWEN-IMAGE-EDIT-AUTO_INSTALL-RUNPOD.sh file on the left side of the UI then click on the "Terminal" icon on the right side on the UI
Copy and paste these two lines then press enter:
chmod +x QWEN-IMAGE-EDIT-AUTO_INSTALL-RUNPOD.sh
./QWEN-IMAGE-EDIT-AUTO_INSTALL-RUNPOD.sh
Wait for everything to be installed
Go back to the port 3000 and click on the manager, choose the Nightly build and restart it
Load the QWEN_IMAGE_EDIT_WORKFLOW.json file and there you goπ
Also use the command:
tail -f comfyui.log
inside the workspace/logs to get the real time logs so that you always know when the install is done. It will then ask you to restart, so click on that restart button, wait for the webui to reboot, click refresh once it's done and there you go.
IF YOU ARE USING RUNPOD AND YOU WANT TO STOP THE POD THEN RESTART IT:
Go inside your pod
SERVICE port 8888
Go inside the Comfyui folder, open a terminal icon and re copy and paste those two lines:
chmod +x QWEN-IMAGE-EDIT-AUTO_INSTALL-RUNPOD.sh
./QWEN-IMAGE-EDIT-AUTO_INSTALL-RUNPOD.sh
And then in a few seconds it will reinstall all the requirements for the nodes
Go back to comfyui port 3000, click on manager, click update all, wait for everything to be updated then restart.
Re drag and drop the QWEN_IMAGE_EDIT_WORKFLOW.json file inside and there you goπ
As always, supporting me on Patreon allows me to keep creating helpful resources like this for the community. Thank you for your support - now go have some funπ!
Comments
Matthew
What version of nunchaku do I need? I installed 3 different versions of nunchaku trying to get the plugin to work. 0.32 1.0.0 and 1.0.1 install_wheel.json node NUnchakuWheelInstaller says its missing. I think I am screwed.
Pat Johnson
Hi, maybe I'm doing something wrong, but I just can't seem to figure this out. I've followed the tutorial video repeatedly, did the instructions in the post, deleted the folder and reinstalled, and did it all over again. I just can't seem to get this to work. I click Run and I get an error. I'm using a Geforce 1050 ti. Here's the error I get: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions. I even googled the issue and tried to install nightly pytorch. At one point I got a wrong numpy version? In any case, that's the error I get for now. Any help would be appreciated.
Foxy
try different browser/ private browser
Cezary Laska
stopped working :(
Gintukas VerikΕ³
Runpod comfyui don't have manager
Michael Collins
damn, the update option is expired.
Russell Richardson
the dl link is to thr right
bigsk1
anytime i get that, and it was today is because the clip is set to the wrong model.
Joseph Cheng
Hi anyone getting this with qwen image editTextEncodeQwenImageEdit mat1 and mat2 shapes cannot be multiplied (5476x1280 and 3840x1280)
Darkwan75
What is the Nodes Install bat file for? I thought install missing custom nodes would do that. Is this in case that doesn't work?
Blue
Hello, I'm getting an error the installer is not compatible with Windows 64 bit. Anyone else have this issue?
BigHomie
Runpod was picked up as a Trojan Virus by my antivirus . Threat name 'BV:Miner-LO[Trj]'
Hamdi Hirzalla h
it's very likely a corrupted model. the download may have interrupted while the Bat file was running. when it happened to me I redownloaded the model and it ran fine after that. just take the model name and look it up and download and replace it. better than a full reinstall.
Neker Play
cannot reshape array of size 14392122 into shape (18944,2940) I get this problem , how could i resolve it?
Euchale
Going to post here as it is semi related: With Kontext and Qwen Edit, and Res4Lyf, what is currently the best way to do style transfer (so give 2 images and say Image 1 in style of image 2)?
Koray Birand
Getting Unexpected text model architecture type in GGUF file: 'qwen2vl' for Qwen2.5-VL-7B-Instruct-UD-Q8_0.gguf
Crux Riajuu
I'm noob to this comfy ui stuff but is it possible to use illustrious models with it for this or the other one you posted before with the img to video?
