Home
Creators
Search Recent Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register Favorites Keys Review DMs Logout
Community
Telegram ThePornDude
Home Creators Posts Import Register Favorites Logout

1-Click INSTALL QWEN IMAGE EDIT 2509 (PLUS) ComfyUI WebUI! (Patreon)

Published:
2025-09-27 17:37:51
Edited:
2025-10-02 14:23:57
Imported:
2026-06
Tags:

Downloads

Content

EDIT 1st October: I updated the workflow (https://www.patreon.com/posts/qwen-image-edit-139876435) for the people who had those weird "ghosting" issues, this should solve the problem. DO NOT ALSO FORGET, to dl the Qwen-Image-Edit-Lightning-4steps lora (EDIT not NORMAL like before), either use this link :https://huggingface.co/Aitrepreneur/FLX/resolve/main/Qwen-Image-Edit-Lightning-4steps-V1.0.safetensors?download=trueto dl the lora into the ComfyUI_windows_portable\ComfyUI\models\loras folderor just use the nodes model installer if you need it.I explain it + color editing trick in this short update video: https://youtu.be/-DRDZZd2zKsI will update the workflow further once nunchaku get the lora support readyHey everyone! I've created a 1-click installer for "THE NEW OPEN-SOURCE NANO BANANA COMPETITOR!", called "QWEN IMAGE EDIT 2509 (PLUS)". And it’s basically Qwen image edit but much more powerful…A model that is able to automatically edits multiple images together with just a simple text prompt with insane precision!

You can check out the video right here: https://youtu.be/1VzPOLkcN64

The workflow: https://www.patreon.com/posts/139876435

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-PLUS-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-PLUS_ULTRA.json file and there you go😎

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-PLUS-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 😎

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 80gb 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-PLUS-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-PLUS-AUTO_INSTALL-RUNPOD.sh

./QWEN-IMAGE-EDIT-PLUS-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-PLUS_ULTRA.json file and there you go😎

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-PLUS-AUTO_INSTALL-RUNPOD.sh

./QWEN-IMAGE-EDIT-PLUS-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-PLUS_ULTRA.json file inside and there you go😎

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 fun😉!

Files

Comments

Aitrepreneur

This is a internet connection issue or vpn/proxy/antivirus blocking the download. Try disabling any of those above and try again, if need be you can always dm me

Sonic

Pues me da error cuando entro: Missing Node Types y una lista enorme.

Aitrepreneur

have you used the installer and updated comfyui like I showed?

Tommario Minor

Am I the only one whose comfy setup breaks every time I use a new one click installer? I mean now of the previous workflows which all worked fine last night now work. suddenly im missing all sorts of nodes that were previously there. I mean i was running the tts workflow fine last night. attempt to use the Qwen 1 click installer and now nothing works not even comfy. just wondering if im alone with this experience.

Sonic

Lo instalado y actualizar da error. Como puedo instalar los nodos faltantes?

Aitrepreneur

click on the blue manager button on the top right and click on install missing nodes

Sonic

sale este error: Failed to find the following ComfyRegistry list. The cache may be outdated, or the nodes may have been removed from ComfyRegistry. comfy-core comfy-core comfy-core comfy-core

Aitrepreneur

depends on what error exactly but that can happen yes, for some custom nodes it can break and conflict with other nodes, hence why I put that it's preferable to start a new install check if everything works

Mahmoud Alhashim

this is great. Can you add the best image generator so it will be complete

NIghtmareQueenJune

Is it possible to use the runpod installer for installing it locally on my Linux machine? Since .bat files are windows specific I always have to install your workflows manually. If I'd be able to use the runpod installers it would make installing way easier.

Troy Walton

RE Runpod: I notice the comfy manager seems to get uninstalled ( or at least never show up in the GUI again ) after following the first "update comfyui and restart it" instructions step, making any step during and after the auto installer not really do anything but inform me I'm missing a dozen custom nodes in the workflow :/ Goes without saying I've also never seen any option to select Nightly build, since I assume that's not native to the default manager-less comfyui. Any ideas what I'm doing wrong? I'm using the aitrepreneur/comfyui:2.3.5 template with the RTX 4090. I actually had the same problem with the older Qwen workflow, but weeks ago I could at least get it working by just following the instructions.

Tommario Minor

I understand, and that's exactly what i Did. So now Qwen image edit workflow is works fine but nothing else does! So now i cant use vibevoice. So i rerun the one click installer for vibevoice and then the qwen image workflow that was just working fine is now missing nodes

halloking123

Just set up ComfyUI on an RTX 5090... had to manually install the right PyTorch (CUDA 12.1) to get it running. Would be super nice if future releases or docs mentioned a prebuilt option for 5090 cards. :P thanks for the work btw

Manic

I am getting this Error when I try to run it with my GPU C:\AI\qwen\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py:63: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you. How do I fix this?

Tommario Minor

ImportError: IMPORTANT: PLEASE READ THIS FOR ADVICE ON HOW TO SOLVE THIS ISSUE! Importing the numpy C-extensions failed. This error can happen for many reasons, often due to issues with your setup or how NumPy was installed. We have compiled some common reasons and troubleshooting tips at: https://numpy.org/devdocs/user/troubleshooting-importerror.html Please note and check the following: * The Python version is: Python3.13 from "G:\ComfyUI_windows_portable\python_embeded\python.exe" * The NumPy version is: "2.1.3" and make sure that they are the versions you expect. Please carefully study the documentation linked above for further help. Original error was: cannot import name '_get_promotion_state' from 'numpy._core._multiarray_umath' (G:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\numpy\_core\_multiarray_umath.cp313-win_amd64.pyd) Press any key to continue . . .

Cristi Tanase

I have used QWEN-IMAGE-EDIT-PLUS-COMFYUI-MANAGER_AUTO_INSTALL and after I'm getting missing custom nodes error. When I try to update the missing nodes I'm getting this error: Alert ComfyUI is outdated, so some built-in nodes cannot be used. together with this: Failed to find the following ComfyRegistry list. The cache may be outdated, or the nodes may have been removed from ComfyRegistry. comfy-core comfyui-aspect-ratio-crop-node comfy-core comfy-core Is there a solution for this issue? I have no VPN installed.

Aitrepreneur

I guess it could be easily adapted to a linux install but I don't have linux so I can't make sure it works beforhand

Aitrepreneur

I got that issue as well but it's actually a browser issue, you probably got some extensions that are making that button disapear (like adblock or something like that) if you open the url with another browser in a private navigation, you'll see the button again

Aitrepreneur

yeah that can happen yes, for some custom nodes it can break and conflict with other nodes, hence why I put that it's preferable to start a new install check if everything works

Darkwan75

Well I almost got it working. Unfortunately the controlnet node can't be turned off because any position you put the switch complains that controlnet is off, yet somehow also on.

kaudlol

Yeah getting this same thing. Tried turning it off and running, which works, but the image output is very bad and doesn't represent much of the original.

Erwan Cozic

did you know why i have this error? : ______________ VAEEncode 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 have a 5070ti

Cristi Tanase

Oh, apparently the problem can be fixed if you change the set "COMFY_VER=v0.3.6" to set "COMFY_VER=v0.3.60" in the .bat installer file.

Aitrepreneur

portable version should work right out of the box for the 5000 series as well though :/

Aitrepreneur

as I said in the video use the comfyui update bat file to update comfyui

Aitrepreneur
>>188582532

F 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)

Julien Natter

I was confused not seeing the comfyUI folder after the installation, turn out the folder was in sytem32 folder for some reason

Cristi Tanase

I just read the instruction from the Patreon post, sorry, not even that one completely it seems, I was way to hyped for this one. Oh, and there's another error, on the .json workflow there is a Living_Spaces.webp file required on a widget. This will throw an error and stop everything. The solution is to add a random image in the ComfyUI_windows_portable\ComfyUI\input\ and rename it as Living_Spaces.webp .

Bob Doyle Media

Trying only the inpainting, I just keep getting TextEncodeQwenImageEditPlus mat1 and mat2 shapes cannot be multiplied (784x1280 and 3840x1280). I have Resize image turned off, and all models are set just like yours.

kaudlol

[[FIX FOR THIS ISSUE]] Prompt outputs failed validation: Switch any [Crystools]: - Required input is missing: on_true - Required input is missing: on_false So you just need to by pass the TRUE ---> OPEN POSE node for this to workflow. Aitrepreneur's workflow is different from this one, so when the workflow in the video has the Control switch off, it bypasses this node. The workflow we got is different, possibly updated/outdated so you'll have to manually bypass this node if you're not using the Control net function.

Ronald Tang

Im getting this error message UnetLoaderGGUF This model is not currently supported - (Model architecture not allowed for conversion! (i.e. reference VS diffusers format)) But I did a clean install.... using 1 click bat

Dennis Stolte

hi Aitrepreneur, thx for making there bat files. i just wish you would include one just for getting the models. This is the second time i used one of your installer bat files on a perfectly working comfyui installation and it just bricked it. while all i needed were the models. Last time i was able to get it fixed again with a backup this time however i did not make a backup. I started the bat file, choose the type of file for my vram that was asked and i went.. "shit! not again." uninstalling and reinstalling all kinds packages ruining my installation. Should have just found the models. Me sad now

Dennis Stolte

i have the same error. i am using a 5090

Dave Spicer

Apparently the Q5 model downloaded by the batch file was corrupted - another user said getting from Huggingface fixed the issue. Our overlord said he'd download it again so the batch file would use an uncorrupted copy.

Dragonbait

hmm, issues with this one. My images are coming out like weird double images, almost like 2 images slightly off from each other !?

bwild370

I love this, Could you make a short video on how to run Ai Tool Kit to train a Qwen image Edit Plus Lora? It would be an awesome video??? :D

Mr. Friendly

Mostly works. Just two weird parts, When using just one image like you did in the video on the three image workflow I get a error: Prompt outputs failed validation: Switch any [Crystools]: - Required input is missing: on_false - Required input is missing: on_true And when trying to use more then one sometimes the images try to blend instead of doing what I ask. Like change style of image 1 to that of image 2, then I get a bunch of people and elements that blend into the people in image 2. But maybe it just not as good at that yet. Anyone had similar issue? Thanks anyway its great to try it out. Hope we get normal qwen to with the controlnets.

Bowen Baars

Will you also make an install for wan 2.2 animate?

RenderDrgn

getting the same error, also have a 5090

kristopher ulley

I got this issue as well. Did you find afix?

kristopher ulley

Prompt execution failed Prompt outputs failed validation: Switch any [Crystools]: - Required input is missing: on_false - Required input is missing: on_true

kristopher ulley

i have a 4090 and tryed bypassing this in the q8 version and it stalls, in the q5 version it creates a blurry photo with bad contrast.

Ivan L

Yup same problem, when i do a 1 image edit (and turning off all the controlnet stuff, results in a ghosted image on image blurry effect. Regardless if I try different weights q8,6 or lighting 4step/8step. etc.

sai ram

Make wan2.2 animate video @aitrepreneur

Sonic

@aitrepreneur ayudame

Ronald Tang

Hey Dave, you are right getting the new Q5 model worked. having a 16Gb graphic's card would you recomend another Q model then Q5? I also don't know what the letters after it stands for.

CodeCrafters Collective

your at the very beginning of the comfyUI journey, I suggest watching many youtube videos to get the basics down.

FanArtFuseBeads

A algunos mecenas se nos olvida simplemente agradecer tu trabajo por facilitarnos la vida en el filo de la tecnología cuando no tenemos tiempo ni interés por estar todo el tiempo actualizados. GRACIAS.

phail216

Yeah, we need a fix here.

Super Assetto Corsa

How can I intall all this missing files/nodes ? ReferenceLatent CFGNorm TextEncodeQwenImageEditPlus ResizeMask GrowMaskWithBlur ImageResizeKJv2 PrimitiveStringMultiline That's it shows after running the COMFYUI MANAGER AUTO INSTALL BAT Same happenwith other pre installed COMFYUI that I had, it was updated and I've used the MODELS-NODES_INSTALL BAT ... After that, Same missing files/nodes

mnkjiu

No issues with the install. Working fine. Are there any LORAs we can use?

phail216

You need update comfyui from the update folder

Taylor Sheahan and The Dusty Desert Boys

This is absolutly Awesome! Is there a way to use DW pose? And when the heck are the VACE people gonna get the WAN 2.2 thing going... It's a very exciting time for Ai Creators.

Albion22

If you are not using Controlnet you have to deactivate the true/false box above the controlnet box otherwise you will get the missing input error

Troy Walton

Thanks! Disabling my adblock on the ComfyUI tab fixed it.

Albion22

If you are not using Controlnet you have to deactivate the true/false box above the controlnet box otherwise you will get the missing input error

Tommario Minor

same here. does any one know where to get the more simplistic workflow that does not incorporate all of these open pose nodes. ive disabled them and still get this same error.

Tommario Minor

Prompt execution failed Prompt outputs failed validation: Switch any [Crystools]: - Required input is missing: on_true - Required input is missing: on_false I'm getting the same errors, i have painstakingly deleted my complete comfy install and did a fresh install for the 4th time. I've ran the update.bat after the fresh install. I still encounter the same errors. please help, I appreciate what you do but i cant keep paying for this every month if i can not make use of the tool.

Tommario Minor

I had to manually bypass the True>openpose false >depth node. disabling the controlnet fast groups bypass does not disable this node and it is throwing an error when not using controlnet

Mr. Friendly

Tried a fresh install and turned of my antivirus I forgot to this time and updated with bat both comfy and python. //Got this error: ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. opencv-python 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= "3.9", but you have numpy 2.3.3 which is incompatible. opencv-python-headless 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= "3.9", but you have numpy 2.3.3 which is incompatible. This time i got the error in the description: AssertionError: Torch not compiled with CUDA enabled (Seems like a better error than an unknown) I also got this warning may times during install all the installations: WARNING: The scripts xxxxx are installed in 'G:\ComfyQwenEdit\ComfyUI_windows_portable\python_embeded\Scripts' which is not on PATH. Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.// Though after all that it started and there was less complains about nods, just controlnets it wanted me to install. Then tried running it with just one image without touching anything and got the same error: Prompt execution failed Prompt outputs failed validation: Switch any [Crystools]: - Required input is missing: on_false - Required input is missing: on_true

Mr. Friendly

Here is the error log: # ComfyUI Error Report ## Error Details - **Node ID:** N/A - **Node Type:** N/A - **Exception Type:** Prompt execution failed - **Exception Message:** Prompt outputs failed validation: Switch any [Crystools]: - Required input is missing: on_false - Required input is missing: on_true ## Stack Trace ``` Error: Prompt execution failed at ComfyApi.queuePrompt (http://127.0.0.1:8188/assets/index-3EinLPXI.js:101979:13) at async ComfyApi.queuePrompt_with_seed (http://127.0.0.1:8188/extensions/ComfyUI-Easy-Use/assets/extensions-D7E6yQLT.js:1:185739) at async PromptService.api.queuePrompt (http://127.0.0.1:8188/rgthree/common/prompt_service.js:88:28) at async ComfyApp.queuePrompt (http://127.0.0.1:8188/assets/index-3EinLPXI.js:306729:25) at async app.queuePrompt (http://127.0.0.1:8188/extensions/rgthree-comfy/rgthree.js:477:24) at async function (http://127.0.0.1:8188/assets/GraphView-DIPHp-Pl.js:12308:9) at async http://127.0.0.1:8188/assets/index-3EinLPXI.js:211862:14 at async Proxy.execute (http://127.0.0.1:8188/assets/index-3EinLPXI.js:234384:7) at async queuePrompt (http://127.0.0.1:8188/assets/GraphView-DIPHp-Pl.js:9458:7) ``` ## System Information - **ComfyUI Version:** 0.3.60 - **Arguments:** ComfyUI\main.py - **OS:** nt - **Python Version:** 3.12.7 (tags/v3.12.7:0b05ead, Oct 1 2024, 03:06:41) [MSC v.1941 64 bit (AMD64)] - **Embedded Python:** true - **PyTorch Version:** 2.8.0+cu128 ## Devices - **Name:** cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync - **Type:** cuda - **VRAM Total:** 25769279488 - **VRAM Free:** 24436015104 - **Torch VRAM Total:** 0 - **Torch VRAM Free:** 0 ## Logs ``` 2025-09-28T21:31:23.313913 - [START] Security scan2025-09-28T21:31:23.313913 - 2025-09-28T21:31:24.421927 - [DONE] Security scan2025-09-28T21:31:24.421927 - 2025-09-28T21:31:24.548583 - ## ComfyUI-Manager: installing dependencies done.2025-09-28T21:31:24.548583 - 2025-09-28T21:31:24.549090 - ** ComfyUI startup time:2025-09-28T21:31:24.549090 - 2025-09-28T21:31:24.549090 - 2025-09-28 21:31:24.5482025-09-28T21:31:24.549090 - 2025-09-28T21:31:24.549090 - ** Platform:2025-09-28T21:31:24.549090 - 2025-09-28T21:31:24.549090 - Windows2025-09-28T21:31:24.549606 - 2025-09-28T21:31:24.549606 - ** Python version:2025-09-28T21:31:24.549606 - 2025-09-28T21:31:24.549606 - 3.12.7 (tags/v3.12.7:0b05ead, Oct 1 2024, 03:06:41) [MSC v.1941 64 bit (AMD64)]2025-09-28T21:31:24.549606 - 2025-09-28T21:31:24.549606 - ** Python executable:2025-09-28T21:31:24.549606 - 2025-09-28T21:31:24.549606 - G:\ComfyQwenEdit\ComfyUI_windows_portable\python_embeded\python.exe2025-09-28T21:31:24.549606 - 2025-09-28T21:31:24.550112 - ** ComfyUI Path:2025-09-28T21:31:24.550112 - 2025-09-28T21:31:24.550112 - G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI2025-09-28T21:31:24.550112 - 2025-09-28T21:31:24.550112 - ** ComfyUI Base Folder Path:2025-09-28T21:31:24.550112 - 2025-09-28T21:31:24.550112 - G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI2025-09-28T21:31:24.550620 - 2025-09-28T21:31:24.550620 - ** User directory:2025-09-28T21:31:24.550620 - 2025-09-28T21:31:24.550620 - G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\user2025-09-28T21:31:24.550620 - 2025-09-28T21:31:24.587304 - ** ComfyUI-Manager config path:2025-09-28T21:31:24.587304 - 2025-09-28T21:31:24.587304 - G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Manager\config.ini2025-09-28T21:31:24.587304 - 2025-09-28T21:31:24.587304 - ** Log path:2025-09-28T21:31:24.587804 - 2025-09-28T21:31:24.587804 - G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\user\comfyui.log2025-09-28T21:31:24.587804 - 2025-09-28T21:31:25.841206 - Prestartup times for custom nodes: 2025-09-28T21:31:25.841206 - 0.0 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy 2025-09-28T21:31:25.841206 - 0.0 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use 2025-09-28T21:31:25.841704 - 3.1 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager 2025-09-28T21:31:25.841704 - 2025-09-28T21:31:26.349701 - G:\ComfyQwenEdit\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py:63: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you. import pynvml # type: ignore[import] 2025-09-28T21:31:27.497942 - Checkpoint files will always be loaded safely. 2025-09-28T21:31:27.613935 - Total VRAM 24576 MB, total RAM 65462 MB 2025-09-28T21:31:27.613935 - pytorch version: 2.8.0+cu128 2025-09-28T21:31:27.614447 - Set vram state to: NORMAL_VRAM 2025-09-28T21:31:27.614953 - Device: cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync 2025-09-28T21:31:28.798483 - Using pytorch attention 2025-09-28T21:31:30.669178 - Python version: 3.12.7 (tags/v3.12.7:0b05ead, Oct 1 2024, 03:06:41) [MSC v.1941 64 bit (AMD64)] 2025-09-28T21:31:30.669178 - ComfyUI version: 0.3.60 2025-09-28T21:31:30.719092 - ComfyUI frontend version: 1.26.13 2025-09-28T21:31:30.720594 - [Prompt Server] web root: G:\ComfyQwenEdit\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfyui_frontend_package\static 2025-09-28T21:31:31.718567 - [Crystools ?[0;32mINFO?[0m] Crystools version: 1.27.3 2025-09-28T21:31:31.752228 - [Crystools ?[0;32mINFO?[0m] Platform release: 11 2025-09-28T21:31:31.752739 - [Crystools ?[0;32mINFO?[0m] JETSON: Not detected. 2025-09-28T21:31:31.753252 - [Crystools ?[0;32mINFO?[0m] CPU: AMD Ryzen 7 5800X 8-Core Processor - Arch: AMD64 - OS: Windows 11 2025-09-28T21:31:31.777521 - [Crystools ?[0;32mINFO?[0m] pynvml (NVIDIA) initialized. 2025-09-28T21:31:31.778027 - [Crystools ?[0;32mINFO?[0m] GPU/s: 2025-09-28T21:31:31.784592 - [Crystools ?[0;32mINFO?[0m] 0) NVIDIA GeForce RTX 3090 2025-09-28T21:31:31.784592 - [Crystools ?[0;32mINFO?[0m] NVIDIA Driver: 581.29 2025-09-28T21:31:34.074437 - [ComfyUI-Easy-Use] server: 2025-09-28T21:31:34.074437 - v1.3.4 2025-09-28T21:31:34.074437 - Loaded2025-09-28T21:31:34.074942 - 2025-09-28T21:31:34.074942 - [ComfyUI-Easy-Use] web root: 2025-09-28T21:31:34.074942 - G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use\web_version/v2 2025-09-28T21:31:34.074942 - Loaded2025-09-28T21:31:34.074942 - 2025-09-28T21:31:34.079541 - ComfyUI-GGUF: Allowing full torch compile 2025-09-28T21:31:34.096705 - ### Loading: ComfyUI-Manager (V3.37) 2025-09-28T21:31:34.097205 - [ComfyUI-Manager] network_mode: public 2025-09-28T21:31:34.316452 - ### ComfyUI Version: v0.3.60-33-gb60dc316 | Released on '2025-09-28' 2025-09-28T21:31:34.656445 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json 2025-09-28T21:31:34.659695 - __ ______ ____ ____ ____ _ _ \ \ / / _ \ / ___| __ _ _ __ ___ ___| _ \ _____ __/ ___(_)_ __| | \ \ / /| |_) | | _ / _` | '_ ` _ \ / _ \ | | |/ _ \ \ / / | _| | '__| | \ V / | _ <| |_| | (_| | | | | | | __/ |_| | __/\ V /| |_| | | | | | \_/ |_| \_\\____|\__,_|_| |_| |_|\___|____/ \___| \_/ \____|_|_| |_| 🎮 VRGameDevGirl custom nodes loaded successfully! 🎞️ 2025-09-28T21:31:34.659695 - 2025-09-28T21:31:34.674725 - [G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts2025-09-28T21:31:34.677227 - 2025-09-28T21:31:34.677727 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json 2025-09-28T21:31:34.678228 - [G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False2025-09-28T21:31:34.678730 - 2025-09-28T21:31:34.679230 - [G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']2025-09-28T21:31:34.679730 - 2025-09-28T21:31:34.733321 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json 2025-09-28T21:31:34.753433 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json 2025-09-28T21:31:34.798021 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json 2025-09-28T21:31:35.440152 - G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py:26: UserWarning: DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly warnings.warn("DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly") 2025-09-28T21:31:35.668878 - Using pytorch attention 2025-09-28T21:31:35.679543 - (RES4LYF) Init2025-09-28T21:31:35.679543 - 2025-09-28T21:31:35.679543 - (RES4LYF) Importing beta samplers.2025-09-28T21:31:35.680056 - 2025-09-28T21:31:35.695781 - (RES4LYF) Importing legacy samplers.2025-09-28T21:31:35.695781 - 2025-09-28T21:31:35.716538 - 2025-09-28T21:31:35.716538 - [rgthree-comfy] Loaded 48 exciting nodes. 🎉2025-09-28T21:31:35.716538 - 2025-09-28T21:31:35.716538 - 2025-09-28T21:31:35.720343 - Import times for custom nodes: 2025-09-28T21:31:35.720343 - 0.0 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py 2025-09-28T21:31:35.720842 - 0.0 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\wlsh_nodes 2025-09-28T21:31:35.720842 - 0.0 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF 2025-09-28T21:31:35.720842 - 0.0 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_essentials 2025-09-28T21:31:35.720842 - 0.0 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_UltimateSDUpscale 2025-09-28T21:31:35.720842 - 0.0 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-KJNodes 2025-09-28T21:31:35.721343 - 0.0 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy 2025-09-28T21:31:35.721343 - 0.0 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-vrgamedevgirl 2025-09-28T21:31:35.721343 - 0.1 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Crystools 2025-09-28T21:31:35.721343 - 0.2 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\RES4LYF 2025-09-28T21:31:35.721343 - 0.5 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager 2025-09-28T21:31:35.721843 - 0.8 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux 2025-09-28T21:31:35.721843 - 2.3 seconds: G:\ComfyQwenEdit\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use 2025-09-28T21:31:35.721843 - 2025-09-28T21:31:35.967370 - Context impl SQLiteImpl. 2025-09-28T21:31:35.967370 - Will assume non-transactional DDL. 2025-09-28T21:31:35.968370 - No target revision found. 2025-09-28T21:31:35.985886 - Starting server 2025-09-28T21:31:35.986888 - To see the GUI go to: http://127.0.0.1:8188 2025-09-28T21:31:38.799462 - FETCH ComfyRegistry Data: 5/982025-09-28T21:31:38.799462 - 2025-09-28T21:31:42.648702 - FETCH ComfyRegistry Data: 10/982025-09-28T21:31:42.649707 - 2025-09-28T21:31:46.220897 - FETCH ComfyRegistry Data: 15/982025-09-28T21:31:46.220897 - 2025-09-28T21:31:49.941279 - FETCH ComfyRegistry Data: 20/982025-09-28T21:31:49.941786 - 2025-09-28T21:31:53.660875 - FETCH ComfyRegistry Data: 25/982025-09-28T21:31:53.661378 - 2025-09-28T21:31:58.793185 - FETCH ComfyRegistry Data: 30/982025-09-28T21:31:58.793185 - 2025-09-28T21:32:02.331854 - FETCH ComfyRegistry Data: 35/982025-09-28T21:32:02.331854 - 2025-09-28T21:32:05.979715 - FETCH ComfyRegistry Data: 40/982025-09-28T21:32:05.979715 - 2025-09-28T21:32:09.589795 - FETCH ComfyRegistry Data: 45/982025-09-28T21:32:09.590299 - 2025-09-28T21:32:13.092641 - FETCH ComfyRegistry Data: 50/982025-09-28T21:32:13.092641 - 2025-09-28T21:32:16.799013 - FETCH ComfyRegistry Data: 55/982025-09-28T21:32:16.799013 - 2025-09-28T21:32:22.016418 - FETCH ComfyRegistry Data: 60/982025-09-28T21:32:22.016418 - 2025-09-28T21:32:27.298906 - FETCH ComfyRegistry Data: 65/982025-09-28T21:32:27.299407 - 2025-09-28T21:32:31.735686 - FETCH ComfyRegistry Data: 70/982025-09-28T21:32:31.736191 - 2025-09-28T21:32:35.752787 - FETCH ComfyRegistry Data: 75/982025-09-28T21:32:35.753305 - 2025-09-28T21:32:39.692772 - FETCH ComfyRegistry Data: 80/982025-09-28T21:32:39.692772 - 2025-09-28T21:32:43.417085 - FETCH ComfyRegistry Data: 85/982025-09-28T21:32:43.417085 - 2025-09-28T21:32:47.084577 - FETCH ComfyRegistry Data: 90/982025-09-28T21:32:47.084577 - 2025-09-28T21:32:52.225495 - FETCH ComfyRegistry Data: 95/982025-09-28T21:32:52.225495 - 2025-09-28T21:32:54.844295 - FETCH ComfyRegistry Data [DONE]2025-09-28T21:32:54.844295 - 2025-09-28T21:32:54.971047 - [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes 2025-09-28T21:32:54.997062 - FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json2025-09-28T21:32:55.043114 - [DONE]2025-09-28T21:32:55.043114 - 2025-09-28T21:32:55.106362 - [ComfyUI-Manager] All startup tasks have been completed. 2025-09-28T21:33:20.305590 - got prompt 2025-09-28T21:33:20.307947 - Failed to validate prompt for output 151: 2025-09-28T21:33:20.307947 - * Switch any [Crystools] 225: 2025-09-28T21:33:20.308458 - - Required input is missing: on_false 2025-09-28T21:33:20.308458 - - Required input is missing: on_true 2025-09-28T21:33:20.308458 - Output will be ignored 2025-09-28T21:33:20.308458 - Failed to validate prompt for output 150: 2025-09-28T21:33:20.308458 - Output will be ignored 2025-09-28T21:33:20.308966 - Failed to validate prompt for output 224: 2025-09-28T21:33:20.308966 - Output will be ignored 2025-09-28T21:33:20.308966 - Failed to validate prompt for output 119: 2025-09-28T21:33:20.308966 - Output will be ignored 2025-09-28T21:33:20.308966 - Failed to validate prompt for output 60: 2025-09-28T21:33:20.308966 - Output will be ignored 2025-09-28T21:33:20.308966 - invalid prompt: {'type': 'prompt_outputs_failed_validation', 'message': 'Prompt outputs failed validation', 'details': '', 'extra_info': {}} ``` ## Attached Workflow Please make sure that workflow does not contain any sensitive information such as API keys or passwords. ``` Workflow too large. Please manually upload the workflow from local file system. ``` ## Additional Context (Please add any additional context or steps to reproduce the error here)

Mr. Friendly

I tried deleting everything that shouldn't be used when just using one image. And then it worked. So removed controlnet and image 2 and 3. Then it worked for one images and saved it as a seperet workflow for now. Now I tried asking chatgpt and it said it could fix it. Will se how it does.

Mr. Friendly

Chatgpt: Part 1 "In your JSON, that switch does have both sides wired (OpenPose → on_true via link 377, Depth → on_false via link 378) and its toggle is set to false (“use Depth”). So the file looks correct: OpenPosePreprocessor (id 152) → link 377 → Switch any on_true. QWEN-IMAGE-EDIT-PLUS_ULTRA DepthAnythingV2Preprocessor (id 155) → link 378 → Switch any on_false. QWEN-IMAGE-EDIT-PLUS_ULTRA The switch (id 225) then feeds a preview (id 224) and another node (id 111). QWEN-IMAGE-EDIT-PLUS_ULTRA Why Comfy says they’re missing anyway You have Fast Groups Bypasser (rgthree) nodes targeting the CONTROLNET group. If you toggled/bypassed that group, ComfyUI removes the OpenPose/Depth nodes from the runtime prompt, which leaves the Switch-any with no inputs, triggering the validation error you see. (You have bypassers for “CONTROLNET” visible in the file.) QWEN-IMAGE-EDIT-PLUS_ULTRA The error mentions other outputs (224 PreviewImage, 119 Image Comparer, 60 SaveImage) failing validation too — they’re downstream of that switch, so they get ignored after the switch fails. (PreviewImage 224 consumes the switch output.) QWEN-IMAGE-EDIT-PLUS_ULTRA Fix it (pick one of these options) Re-enable the CONTROLNET group In the graph, find the Fast Groups Bypasser (rgthree) labeled “CONTROLNET” and make sure it’s not bypassing the group. When the group is enabled, nodes 152 and 155 exist at runtime again and the switch has both inputs. QWEN-IMAGE-EDIT-PLUS_ULTRA If you don’t want ControlNet at all, bypass the switch too Select Switch any [Crystools] (id 225) and press Ctrl +B (or click the bypass icon) to bypass it, or delete it and wire the downstream consumers to a direct image instead (e.g., the resized/source image). That avoids a required-input node with missing inputs. (Preview 224 currently reads from the switch.) QWEN-IMAGE-EDIT-PLUS_ULTRA Feed safe defaults to both sides of the switch Connect the same image to both on_true and on_false. For example, use your “LoadImage” (id 106) or “ImageScaleToTotalPixels” (id 93) output as both inputs to node 225, so validation always succeeds even when a group is bypassed. (93 → many consumers; 225 expects “*”, so IMAGE is fine.) QWEN-IMAGE-EDIT-PLUS_ULTRA Replace with a tolerant router Swap Switch any [Crystools] for an rgthree “Router/Switch/Bypasser” node that tolerates missing branches when groups are toggled. This avoids strict required-input validation when a branch is disabled. A couple of extra checks (nice to do) The Switch latent [Crystools] (id 154) is correctly wired (on_true and on_false both present); leave it as-is. QWEN-IMAGE-EDIT-PLUS_ULTRA Make sure the OpenPose and Depth preprocessors are enabled if you intend to use them (they’re wired from LoadImage 106 → 152/155 and into the switch). QWEN-IMAGE-EDIT-PLUS_ULTRA If you want, I can also send back a patched JSON where: node 225 is bypassed (or fed from ImageScaleToTotalPixels 93 on both inputs), and Preview 224 is kept working. But the quickest path is usually: un-bypass CONTROLNET or bypass/delete the switch when you’re not using those preprocessors." part 2 "What I changed Removed the node Switch any [Crystools] (id 225) that required both on_true/on_false. Rewired its consumers: PreviewImage (id 224) now takes the image directly from ImageScaleToTotalPixels (id 93). TextEncodeQwenImageEditPlus (id 111) input image2 now also receives the same safe image from node 93. This keeps everything running even if the CONTROLNET group (with the OpenPose/Depth preprocessors) is toggled off. Download Patched workflow JSON: Download QWEN-IMAGE-EDIT-PLUS_ULTRA_patched.json How to use Import the patched JSON in ComfyUI. If you want to use OpenPose/Depth again, just re-insert a switch (or wire one branch directly) later—this version prioritizes robustness when groups are bypassed. If you’d prefer a variant where the switch stays but lives inside the CONTROLNET group (so it disappears cleanly when bypassed), say the word and I’ll send that version too."

Sean Wilton

Hey I hope someone can help me, when I try to run a script in ComfyUI I get the following error, any help would be great, Thanks! 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.

Mr. Friendly

Solved! true - openpose False - Depth Should be disabled when controlnet and image2 and 3 is off, but it is still active. So just disable it when using one image. Easy fix drag the nod in to the controlnet box, then it gets diabled as well.

Flo_Tou

how did you do it ?

Mr. Friendly

"true - openpose False - Depth" - the nod Should be disabled when controlnet is off, but it is still active. So just disable it when using one image. Easy fix drag the nod into the red controlnet box (that can be resized), then it gets disabled as well.

Tommario Minor

YOU CAN RIGHT CLICK AND SELECT BYPASS FOR THE NODE MODE

Aitrepreneur

Indeed my fault, uploaded an older version of the workflow (fairly similar) but you can just dl the new one, it's the same as in the video

Aitrepreneur

because you ran the installer as admin, you can just move the folder somewhere else since it's a portable version

Aitrepreneur

You need to use the installer and have the Qwen2.5-VL-7B-Instruct-mmproj file inside the unet folde

Aitrepreneur

read the post, you can easily solve the error, this often happens because of the custom nodes updates, I'll try to fix this next time

Aitrepreneur

I could but it wouldn't be interesting since it's the same as training the kontext model

Aitrepreneur

could be bad prompts or incorrect resolutions

Aitrepreneur

you can redl the workflow, I uploaded an older version of the workflow by mistake

Aitrepreneur

my fault, uploaded an older version of the workflow (fairly similar) but you can just dl the new one, it's the same as in the video

Aitrepreneur

read the post, it explains how to solve this

Spool

I solved the ghosting by dropping the new unet in to Aitr's old Image Edit workflow, did need to update the TextEncode to the new one.

Jeff

Hi! I'm getting the following error when trying to run Qwen plus: "UnetLoaderGGUF This model is not currently supported - (Model architecture not allowed for conversion! (i.e. reference VS diffusers format))" any help would be fantastic!! Thanks! (I'm running the nightly version, with comfyUI V3.37, and Qwen-image-Edit-2509-Q5_K_S.gguf ) should I try using Q5_k_M? or maybe go up or down to Q4 or Q6

Vincent Nestler

I have used comfyui for a while. The question i have is will the batch file work with the official version or do I have to run it from inside the portable version which I had for a while but switch. I like the interface on the official one.

Cristo

I noticed that the images that I change position or clothes, they get a lot of contrast

Robb

Where do I find the NSFW Loras for this that you were taking about?

Artari Dziar

I have the same, blurry photo, minimal shift, ghosts

Artari Dziar

I have the same, blurry photo, minimal shift, ghosts

Dennis Stolte

I did a little digging. if you are referring to the reinstallation of torch to lets say cu126 (like it showed me i had version 12.6) it was not as simple as that. i actualy had python installed on my system and the system variables were pointing to that installation not the embedded one with comfyui. i changed that and had them point to the embedded one and reinstalled torch with cu126. that worked. im able to start comfyui again. so i was thinking because i have a 5090 and it tells me this "NVIDIA GeForce RTX 5090 with CUDA capability sm_120 is not compatible with the current PyTorch installation. The current PyTorch install supports CUDA capabilities sm_61 sm_70 sm_75 sm_80 sm_86 sm_90. If you want to use the NVIDIA GeForce RTX 5090 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/" basicly telling me to update cuda. I looked and there is a version 13.0.1 out now. should i update to that? if i look at the pytorch i cannot go higher then 12.9. do you think i should try 12.9 or find 12.8?

Manic

I am using a 5080, and the fix you have posted with the post has not worked after reinstalled everything 4 times.

Slavik Riff

Similar result here. Simple tasks redraw the original image, changing the features of the chracter (even when prompting to maintain), two images tasks give blury or "ghosty" results..

Erock Vaughn

civitai dot com you can find many there.

mnkjiu

where do i add in the LORA node? i am trying to find some examples on civitai

Manic

Can you please help me. I have tried your solutions and they have not worked for me.

Foxy

I'm getting the response "No such file or directory" after I drop the two lines of code into the terminal. Any ideas?

Christian LOUIS

I tried the runpod version but i get this error • downloading Qwen-Image-Edit-2509-Q8_0.gguf ####################################################################################################################################################################################################################### 100.0%####################################################################################################################################################################################################################### 100.0% • downloading Qwen-Image-Edit-Lightning-8steps-V1.1.safetensors curl: (22) The requested URL returned error: 404

CodeCrafters Collective

you need huggingface token if downloading via cli, or download in browser and move to folder

westingtyler (edited)

Comment edits

2026-09-08 20:00 hello! I'm using the QWEN IMAGE EDIT PLUS ULTRA in comfyui, which I manually updated, got models and nodes. trying the top left section - no inpainting, no controlnet, when I get to the Switch latent, whether it's on true or false, I get this: mat1 and mat2 shapes cannot be multiplied (784x1280 and 3840x1280). I'm using a 1024 image in the top slot, and the width and heighth are their default, 1024x1024. RTX 5070ti 16gb, win 10. using Qwen Image Edit 2509 Q5 K S .guff and the other default models of the workflow.
2025-10-02 10:25

Cristo

After the updated, I can't auto install it on rundpod. It says "there is no such file"

Aitrepreneur

Yup, my bad, you can redownload the installers now, it's fixed

Aitrepreneur

have you used the installer? and do you have the Qwen2.5-VL-7B-Instruct-mmproj-BF16.gguf file in the ComfyUI_windows_portable\ComfyUI\models\text_encoders folder?

Aitrepreneur

you probably didn't open the terminal in the correct folder when putting the installer

Aitrepreneur

Yup, that's my bad, you can redownload the installers now, it's fixed

Anthony Harris

I did a clean install of this and downloaded the new workflow but I am still getting the ghosting effect in the image output of the altered image

Anthony Harris

All working fine now, just seen the comments about the files weren't updated last night due to an issue with Pateron so downloaded the new work flow and it is 79k instead of 80k and the images are generating fine now. Thanks for the reply

Anthony Sparks

OpenposePreprocessor No module named 'dateutil im getting the above error i have updated and done what was in the video is there a way i can fix this?? its only when open pose is trying to be used!

Aitrepreneur

you can try to uninstall the controlnet aux node and reinstall it

PinkE

I'm using your run pod template. I updated Comfy UI, but after refreshing the page there is no longer a Manager button anywhere. Without the Comfy UI manger and it's restart button, I don't know how to restart the server. What can I do?

BenignOne

Having the same issue

Cristo

This a great tool but unfortunatelly after the update you made, the template, workflow is waaaay slower to load and to the generate images, even if I want to mask something, it takes more than 1 minute. Hopefully you fix it. I'm using it on runpod. I've restarted the pod many times, I even deleted the storage and created a new one, I download everything again and still face this same issue

Anthonin Hauy

Hey ! everything works well but I have ghosting problems, gen are very blurry.

Lex Jong

Hey Aitrepreneur, I run a 5070ti and used your installer and ran into the AssertionError: Torch error. But everything worked after the workaround (which torch) you placed in your guide. But now I have some other issues, which I can't seem to fix (tried all weekend), can you take a look and give some advice? With Qwen-Image-Edit-2509-Q5_K_S.gguf in Unetloader and one of the following in CLIPloader: + Qwen2.5-VL-7B-instruct-UD-Q4_K_S.gguf: I get Falling back to numpy dequant for qtype: 23 (which is a fallback to CPU I understand. -> which does finish but very slowly + Qwen2.5-VL-7B-instruct-mmproj-BF.gguf: I get the error TextEncodeQwenImageEditPlus - mat1 and mat2 shapes cannot be multiplied -> which stops the proces + Qwen2.5-VL-7B-instruct-Q4_K_M.gguf: I get the error CLIPLoaderGGUF - Unexpected text model architecture type in GGUF file: 'qwen2'

Peter Noble

I installed using your batch file: QWEN-IMAGE-EDIT-PLUS-COMFYUI-MANAGER_AUTO_INSTALL.bat Then I updated comfyui to the latest version because it said some nodes needed newer version. Now I get this error message: UnetLoaderGGUF cannot reshape array of size 1618850 into shape (3072,2112)

mnkjiu

Just sharing, doing Qwen Image Edit Plus on macOS is not possible. Even with the mmproj file. Unless someone can share with me how to do it properly with the right files

Daniel Liu

hello, i ran this and the image coming out is blurry, can you advice what is wrong?

Emiliano

Hey I've installed from scratch 3 or 4 times and keep getting this error, if anyone has encountered this and can help I really appreciate it: Edit: Local install, 5070ti w/ 16gb vram. I'm selecting the 12-16gb option in the installer. TextEncodeQwenImageEditPlus 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. In the terminal: RuntimeError: 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.

Emilien-Edmond D'aramitz (LeonceTheLion)

Just want to put this here brothers and sisters. I've noticed that with this and the previous runpod installer for the non 2509, that sometimes, but not all the time it changes the port of your comfy. I highly doubt this is an issue with Aitrepreneur's code, but rather a glitch with runpod. If you notice your comfy isn't loading, or is spinning, look at your comfy log, and you may notice it is 3001. In my case, i was using the ultimate SD workflow, because it comes with automatic1111 and an uploader, so i can download civitai models, so it is 3020 for me and tonight it changed the port to 3021. The solution is very easy, edit your pod, and open up that port, add the new port to the list. You do not need to delete the other port, just open the new port. **Edit** You may have to rerun the script if for whatever reason runpod wipes your workspace afterword, as it unexpectedly did to me tonight, just go into your models and see if they are there, or if you notice your comfy reverted to a previous version.**, Sometimes it comfy manager disapears with this workflow, so its just best to use Aitrepreneur's comfy workflow.... we need a civitai downloader for comfy, the one i found i couldnt get to work because i am an novice.

Hon Jong

Wish we can do a batch output from video. Maybe we can combine with ebsynth?

MS hadmayot

Im keep getting a black picture I have 3090 Anyone dose know how to fix it?

Dante

new to this, didnt get very far. after choosing my vram autoinstall stops saying its 16 bit, git-setup is incompatible with 64 bit windows ?

Johanna

HI. Was anyone sable to fix this ? I have an 5090 nvidia gpu 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. Thanks!

Mailman

It should be possible to swap a person (image 1) with a person in image 2, shouldn't it? I can't get it to work. the overall image 2 should be the same, just with 1 person swapped in/out.

newtoai

Hello. I am running the installer QWEN-IMAGE-EDIT-PLUS-COMFYUI-MANAGER_AUTO_INSTALL.bat with my pc that has an nvidia 5090. Then I run the update file QWEN-IMAGE-EDIT-PLUS-MODELS-NODES_INSTALL.bat I receive the message below despite I have done these steps I went inside the python embedded folder, click on the folder path, type cmd press enter, and typed: python.exe -m pip uninstall torch python.exe -s -m pip install --upgrade torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu130 The error report is below Please help C:\Users\marco\Downloads\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build [START] Security scan [DONE] Security scan ## ComfyUI-Manager: installing dependencies done. ** ComfyUI startup time: 2025-10-18 12:52:52.512 ** Platform: Windows ** Python version: 3.12.7 (tags/v3.12.7:0b05ead, Oct 1 2024, 03:06:41) [MSC v.1941 64 bit (AMD64)] ** Python executable: C:\Users\marco\Downloads\ComfyUI_windows_portable\python_embeded\python.exe ** ComfyUI Path: C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI ** ComfyUI Base Folder Path: C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI ** User directory: C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI\user ** ComfyUI-Manager config path: C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Manager\config.ini ** Log path: C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI\user\comfyui.log Prestartup times for custom nodes: 0.0 seconds: C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use 0.0 seconds: C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy 1.9 seconds: C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager C:\Users\marco\Downloads\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py:63: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you. import pynvml # type: ignore[import] Checkpoint files will always be loaded safely. Traceback (most recent call last): File "C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI\main.py", line 149, in import execution File "C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI\execution.py", line 15, in import comfy.model_management File "C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 237, in total_vram = get_total_memory(get_torch_device()) / (1024 * 1024) ^^^^^^^^^^^^^^^^^^ File "C:\Users\marco\Downloads\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 187, in get_torch_device return torch.device(torch.cuda.current_device()) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\marco\Downloads\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py", line 1069, in current_device _lazy_init() File "C:\Users\marco\Downloads\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\__init__.py", line 403, in _lazy_init raise AssertionError("Torch not compiled with CUDA enabled") AssertionError: Torch not compiled with CUDA enabled

Benji

If you haven't fixed it yet, it's due to using --use-sage-attention or using --force-fp16 in your startup batch script. You have to remove --use-sageattention (and/or --force-fp16) from your startup batch file and run without sage attention. If you have other workflows that you want to use sage attention with, use the KJ node "Patch Sage Attention KJ" right after the load model node with it set to "auto" to enable it.

Matthew Butcher

Could you please post a video on setting up a fresh install. I think there are alot of assumptions as to python versions, path variables etc. It would be good to start from scratch.

David Murakami

""AssertionError: Torch not compiled with CUDA enabled" it's ok don't panic." Sorry, but I'm still panicking! Like lots of people here it seems, this is not working despite the torch reinstall suggestion. Please help, thank you!

westingtyler (edited)

Comment edits

2026-09-08 20:00 any time I do anything i get this error: mat1 and mat2 shapes cannot be multiplied (748x1280 and 3840x1280) i have an rtx 5070ti 16gb, using win 10. any idea how to fix this? I use all the same resolution of image, but I always get this.
2025-11-02 04:34

a pretty parrot

i believe fixed this by swapping the text encoder, you need one that matches the qwen model your loading.

Stefan Djokic

I'm using 1 click install freshly and it's not working. I get the error when running workflow "TextEncodeQwenImageEditPlus- "Stream" object does not support the context manager protocol" ---- No nodes to install in manager, how to fix this?

Slava Pits

please help! i can't fix this! CLIP LOADER: cannot reshape array of size 191083330 into shape (152064,2016). first of all I tried to run your workflow by intalling models with your bat on my confyui. ERROR. than I installed new confyui using your bat file for confyui, BUT STILL SAME ERROR!!!

Aitrepreneur

dm me screenshots of the parameters and the full error log

I Bea

getting this error using runpod: RuntimeError: 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. How do I pull up the cmd to run the updates you listed?

Michael Ang

Hi I keep getting the error in Comfy UI - TextEncodeQwenImageEditPlus gather(): Expected dtype int64 for index

Slava Pits

Thank you for rapid respond! Solved a problem by updating all (Confyui, Manager, nodes)

RavenWT

Got the same erreur, and you need to go inside : \ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF Then search for Int32 and the line: qs = torch.gather(kvalues, dim=-1, index=qs.to(torch.int32)).reshape((n_blocks, -1, 32)) There you need to switch the in32 for int64. Your line is supposed to look like this: qs = torch.gather(kvalues, dim=-1, index=qs.to(torch.int64)).reshape((n_blocks, -1, 32)) It fixed my issue

RavenWT

Just reinstalled the workflow, and strangely we have a lot of errors to fix, and when running it, it doesn't modify the image animore or just lightly.

LW

I opened ostris AI-toolkit but I didn't see an option for training loras for Klein. Is this something in the works? Or is a different lora trainer needed?