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

WAN IMAGE AI KING WORKFLOW! (Patreon)

Published:
2025-07-13 19:02:53
Edited:
2025-07-21 02:52:44
Imported:
2026-06
Tags:

Downloads

Content

EDIT 21 july: I ADDED THE INPAINT WORKFLOW. It works pretty well and it works with loras as well, soo...try it out...Hey everyone! I've just released a new video on the TRUE IMAGE AI KING that was hiding in plain sight! A model originally built for video… that turns out to be the BEST FREE IMAGE GENERATOR I’ve ever seen! It beats Flux, HiDream and everything else with insane quality, perfect prompt following, massive LoRA support and controlnet inside ComfyUI!

You can check out the video right here: https://youtu.be/oOGiYy7cTFw

I also created a 1-click installer for the Webui for my Patreon supporters for Local AND Runpod, that you can find right here: https://www.patreon.com/posts/134046848

Here the link to the manual install guide: https://pastebin.com/h8aV1n84

Down below you will also find the WAN_IMAGE_GENERATION.json for free for you to use!

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

glendaion

I don't see where is the workflow

Alessandro Blue

stock workflow with q5 models you get this error if you do not disable magcache: KSampler Given normalized_shape=[5120], expected input with shape [*, 5120], but got input of size[1, 16, 1, 90, 160]

E Farts

Hey, I've had this with the last workflow involving depth detection, among the others. I always get an error when trying to enable and run a prompt. DepthAnythingV2Preprocessor [Errno 2] No such file or directory: 'E:\\AI\\ComfyUI Workflow\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\ckpts\\depth-anything\\Depth-Anything-V2-Large\\.cache\\huggingface\\download\\EheDQYkKfRTio82VDltlF5Af82M=.a7ea19fa0ed99244e67b624c72b8580b7e9553043245905be58796a608eb9345.incomplete' I'm still a noob with this stuff, so sorry in advance. I'm sure something just didn't download properly. I also get this one: DWPreprocessor [Errno 2] No such file or directory: 'E:\\AI\\ComfyUI Workflow\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\ckpts\\hr16\\DWPose-TorchScript-BatchSize5\\.cache\\huggingface\\download\\XpuFPiTnQg6On60IeT6uJ5VKfTw=.d86a0b2b59fddc0901a7076e9f59c9f8602602133ed72511c693fd11eea23d91.incomplete' GPU: Geforce 5070 TI (16gb VRAM) CPU: AMD Ryzen 7 9800X3D

E Farts

I managed to get Pose working by switching to "dw-ll_ucoco_384.onnx", but none of the ckpts for depth anything work. I thought my VPN was causing issues with downloading, so I turned it off, but maybe I need to turn it off an run the install again? I dunno.

Juan Forero

I don´t see it also, it´s not there.

Aitrepreneur

definitely turn off the vpn, the first time you use this node, it will download the depth model automatically, might take some time depending on your connection

Aitrepreneur

I wouldn't say that, it's not the first time that people said that they can't find it and then refreshing the page it appeared so maybe it's on the patreon's side the issue who knows

Bobby Boe

This is because of a strange behavour of the patreon page. When someone arrives... the page looks like this: https://www.patreon.com/posts/1-click-install-134046848 Only when clicking on the title "WAN IMAGE AI KING WORKFLOW!", the visitor arrives at https://www.patreon.com/posts/wan-image-ai-134046660 (where the link to the json-workflow is visible. But not knowing that the title is clickable, there is no reason that makes someone click that title and arrive at "this page". (Because comments and content are readable allready on the arrival-page.) I hope, this in valuable as feedback!? (I searched for some time to find that "this page" with the downloadlink) greets BB

Aitrepreneur

I mean...not really, is this a mobile issue? I'm on pc so it looks the same to me

glendaion

first it was not published or did not appear. Well, I looked at the end of the message where the attachments always appear. Then when I came back it did appear. Sometimes it can be an error of the page.

EX01

Then I stand corrected and removed it thanks :-)

EX01

WAN 720p long video workflow when?

Urge Leo's

Hi there! We’ve been trying to reach out regarding a potential paid collaboration opportunity. I’ve sent messages to the email you listed on YouTube and also tried DMing you on Discord (from Clio). If there’s a preferred way to contact you, we’re happy to reach out there instead. Just hoping to connect — thanks and hope to hear from you!

Alson

i was trying to run with the default settings with nothing changed, i tried the text to image workflow and now half of my screen turned black. What should i do? What am i doing wrong? I have RTX 4060 8gb, CPU is Ryzen 5 3600.

Aitrepreneur

Half of your screen?? That's sounds like an hardware issue, restart the pc maybe and try again

EX01

Just the tip mam? :-) Good to know you are thinking about it, thanks for the reply.

Alson

After I restarted, it was ok. However I got a issue where I cannot create image to image generation. It kept getting stick at k sampler 20% for around 40 mins. I I used all default settings

phail216

When using the Image to Image I am getting the following error: WanVaceToVideo shape '[1, 104, 8, 71, 8]' is invalid for input of size 478400 All parameters are at default, but I've also tried to set the resize to no, bit it always jumps back on

Lockelamora

Great workflow! how can i use other models (.checkpoint?)

Timothy Musson

Yeah, it's just Patreon's web UI being a bit crap. I dunno about Patreon's phone app, but on the actual website, a truncated view of the article is visible on the user's "home feed", along with the words "Show more...". And when you click "Show more...", you then see the entire text of the post, _minus attachments_ (and with no indication that anything's been left out). To see the attachments, one has to click the _title_ of the post, which takes you from your "home feed" page, to the full article _including_ attachments. So, yeah, it's pretty unintuitive that Patreon just quietly omits attachments when people click "Show more...", thinking they're going to see the complete post incl attachments.

Aitrepreneur

This is for wan, other models need other workflows (most are on patreon here)

Lockelamora

there are some other models for wan in civit, but are .checkpoint and cant use them in this workflow

Aitrepreneur

Which model is that? .checkpoint is not a format that exist for a model

Kamila Szkolnik

everything works great, beautiful, realistic hands and texture! i've tried to activate in power lora my own trained character, but it seems that this model doesn't activate it. Maybe I should add something more to the workflow but if you know that this model won't work with trained loras pls give me an answer in other way I will try and try and try :D

Aitrepreneur

It does work with loras but it's Wan so you need to use a lora trained on the Wan model, each loras correspond to the model they were trained on

Neil Rhodes

how to change the install path? to another drive?

Aitrepreneur

The installer installs comfyui where you have placed the installer, also it's a portable version so you can take that folder and move it anywhere you want

Aitrepreneur

this is a simple image to video model, it doesn't generate images, what you see is just images that were converted into videos, you can have the same results with the normal image to video wan model

Ansel

So that's why I was getting bad results in the generation. I thought the workflows used the base model into the model that generate the image or something like that

Nicolas Giarrusso

Thanks for sharing, I don’t know why the mask isn’t working; I draw it in the mask editor, but it doesn’t integrate the shape or the scene lighting.

Aitrepreneur

Yup just read the model name next time (t2v text to video, i2v image to video)

Ansel

Thanks for the info bro, I am learning everything about comfyui. I started 4 days ago so I am not familiarized with the this stuff

Hung Do

Work great yesterday now getting error. I redownload a fresh workflow and still got error SyntaxError: Unexpected non-whitespace character after JSON at position 4 (line 1 column 5) https://imgur.com/xdJqI63

Aitrepreneur

dm me screens of the parameters before the generation

Yovan Vujacic

Hi, I have tested your workflows and Im having an issue with the control net one. It completely ingores the control net image. could you help me find out why?

Hung Do

It's not your json... it's my comfy install. Update, the problem went away, update today and the problem is back. lol must be one of the custom node. BTW can you update this json for wan 2.2?

Alri

Hi, thanks for the awesome content! I am having issues with the control nets, they are being ignored. Any hint on how to solve the problem would be great. Thanks!

Ilir

I am basically using the vanilla worklflow that was distributed yesterday. I just change the models in the model selector to the Q5_K_S ones accordingly (top high noise, following the low noise). However when i generate an image with "text to image" i get only noise in the output. Anyone has the same behaviour?

Hog Hot

Failed to get input node 0 for group node child 433:1 with slot 1 whenever i try to generate anything

Alex

... same as well

Наташа Мальцева

and I, after the update, had the same problem Error Failed to get input node 0 for group node child 433:1 with slot 1 where to look for this 433?

Morpheus

the problematic group is the WAN IMAGE UPSCALER, after i deleted this group from the workflow it works u can debug and check which certain node is doing that , but i have a different issue seems like i cant get some missing nodes installed : "Upscale Factor With Model (WLSH)", "MagCache", "FastFilmGrain"

Morpheus

i was able to install all of them manually, running on 3080 10gb vram this is great!, it works alot better than flux and much faster, only thing about image to image i tried to put a pic of my kid and make himn a fortnite character for example and it changed him completely, i also tried to change some generated pics i made of a realistic portrait to change some facial expression but still here it also changed it to a different person, what am i missing? denoise is set to 75 all the rest is default WF settings

Morpheus

i was able to fix this issue, in the upscaler flow, rightclick on the UPSCALERS group, "convert to nodes" this worked for me

Paco

I'm trying to test the upscaler, but I get this error: Prompt outputs failed validation: SamplerCustomAdvanced: - Required input is missing: noise - Required input is missing: sampler - Required input is missing: sigmas All nodes appear to be connected

james beal

llama-anon/not-flux-kontext-dev-clothes-remover has been censored by hugging face and removed from civitai. Any suggesting on where it can be downloaded?

José Masis Valverde

This fix it "Try this and replace line 13 only with "from comfy.ldm.lightricks.model import LTXBaseModel" For both nodes.py and nodes_calibration.py in MagCache folder"