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 2.2 ULTRA VIDEO & IMAGE WORKFLOW! (Patreon)

Published:
2025-08-04 21:39:01
Edited:
2025-08-07 18:24:37
Imported:
2026-06
Tags:

Downloads

Content

EDIT 07 AUGUST: I UPDATED THE WORKFLOW AND INSTALLERS TO ADD THE NEW IMAGE TO VIDEO 4 STEPS LORAs AS WELL AS THE NEWLY UPDATED TEXT TO VIDEO 1.1 4 STEPS LORAs. THEY ARE FINALLY HERE AND YOU CAN USE THEM TO SPEED UP YOUR IMAGE TO VIDEO GEN IN ONLY 4 STEPS!THE NEW 1.1 TEXT TO VIDEO LORAs ARE BETTER THAN THE 1.0 ESPECIALLY FOR TEXT TO IMAGE GENERATION BUT FOR TEXT TO VIDEO I STILL RECOMMEND NOT USING LORAs FOR THE FIRST HIGH NOISE MODEL (FIRST PINK LORA NODE). FOR BETTER MOVEMENT AND QUALITY!YOU CAN WATCH THE SHORT UPDATE VIDEO HERE: https://youtu.be/aTGAiZe6SXU EDIT 05 AUGUST: I UPDATED THE WORKFLOW TO REMOVE MAGCACHE SINCE SO MANY PEOPLE HAD ISSUES WITH IT SO IF YOU HAD THE ERROR:KSamplerAdvanced 'NoneType' object has no attribute 'to' EITHER DISABLE MAGCACHE OR DOWNLOAD THIS NEW WORKFLOW. I WILL REUPDATE IT ONCE THE MAGCACHE NODES WILL SUPPORT WAN 2.2.Hey everyone! I've just released a new video on the NEW WAN 2.2 MODELS! Simply the best Text to Video, Image to Video AND Text to image models ever released to date. Better motion, better style, better quality, just better in every single way! Capable of creating lifelike videos and images with incredible motion in only a few minutes. The age of movie creation at home as started, jump on the hype train right now while you still can!There is just no competition for Wan right now....it wins on everything...

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

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/135728905

Here the link to the manual install guide: https://pastebin.com/8jNxWZBm

Down below you will also find the WAN2_2-ULTRA_WORKFLOW.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

Tyler

Can the 2.2 I2V models fit into existing wan2.1 workflows?

Steve Mills

hi great work dont see WAN2_2-ULTRA_WORKFLOW.json link

GenTsoCkn

Fresh install. getting this error on running t2i and t2v with A14B Q8 CLIPLoaderGGUF cannot reshape array of size 14110877 into shape (4096,7040)

Aitrepreneur

have you used the installer? looks like you don't have the correct text encoder loaded, in the workflow it's the umt5-xxI-encoder-Q5 K_S.gguf

MegaChill

Getting KSampler issue with: ``` KSamplerAdvanced 'NoneType' object has no attribute 'to' ``` ideas? latest comfy with nodes installed. T2I generation.

Aitrepreneur

yes don't use the magcache nodes as I explained in the video until it gets updated for wan 2.2

GenTsoCkn

I did, and it's in the folder and selected in comfyui

Aitrepreneur

Have you updated comfyui to the latest version using the update comfyui bat file inside the update folder?

kaudlol

Receiving this same error for I2V attempt. According to Grok, "That error in ComfyUI means the KSampler Advanced node is missing a required attribute called to under its NoneType object." Is this missing a node by chance? FYI, my set up wasn't done with the Auto Installer since it's used with Pinokio, so maybe the auto-installer Aitrenpreneur provided something needed that I might've missed doing a manual install. Thoughts?

kaudlol

Disregard, looks like Aitrepreneur answered as I was typing my reply lol thank you sir <3

MegaChill

had to right click fix node (recreate) and error is gone.

gregoryallen caldwell

will it run on a 40 gig vram, 32 gig ram ryzen -radeon- with no gpu? i have the specs i just dont have a dedicated gpu ! AMD

GenTsoCkn

I have. No luck. Traceback is not all that helpful !!! Exception during processing !!! cannot reshape array of size 20026845 into shape (5120,5440) Traceback (most recent call last): File "G:\projects\comfy\ComfyUI_windows_portable\ComfyUI\execution.py", line 496, in execute output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\projects\comfy\ComfyUI_windows_portable\ComfyUI\execution.py", line 315, in get_output_data return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\projects\comfy\ComfyUI_windows_portable\ComfyUI\execution.py", line 289, in _async_map_node_over_list await process_inputs(input_dict, i) File "G:\projects\comfy\ComfyUI_windows_portable\ComfyUI\execution.py", line 277, in process_inputs result = f(**inputs) ^^^^^^^^^^^ File "G:\projects\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 152, in load_unet sd = gguf_sd_loader(unet_path) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\projects\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF\loader.py", line 52, in gguf_sd_loader reader = gguf.GGUFReader(path) ^^^^^^^^^^^^^^^^^^^^^ File "G:\projects\comfy\ComfyUI_windows_portable\python_embeded\Lib\site-packages\gguf\gguf_reader.py", line 182, in __init__ self._build_tensors(offs, tensors_fields) File "G:\projects\comfy\ComfyUI_windows_portable\python_embeded\Lib\site-packages\gguf\gguf_reader.py", line 364, in _build_tensors data = self._get(data_offs, item_type, item_count).reshape(np_dims), ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ValueError: cannot reshape array of size 20026845 into shape (5120,5440)

Aitrepreneur

DM me screens of the parameters before and after generation

Ryan Prosser

This is awesome! I have one issue only with the Frame to Frame workflow, any ideas where I should look? "WanFirstLastFrameToVideo cannot access local variable 'clip_vision_output' where it is not associated with a value"

Ryan Prosser

Ah, I did set it to update but maybe it didn't successfully I will try again tks

Biogoly

You can't see it from the post in your feed. It's only visible from the post in the home account.

Dingus the Greater

all i get are blank images. i ddnt change anything except disable MAG like you instructed in your video. I dont have any problems with your 2.1 template so not suure what the issue is.

Ryan Prosser

Thanks for saving me from pulling out all my hair, it didn't update properly and after going back through everything NOW it's all good.

Aitrepreneur

Send in DM instead and give access to the link

Star Hawk

Do Wan 2.1 T2V loras work with this setup?

kristopher ulley

KSamplerAdvanced 'NoneType' object has no attribute 'to'

John Horton

disable MagCache to make it work

Serguei Nevarko

I tried running I2V A14B Q4 on both GPU and CPU and I get the same error for both: !!! Exception during processing !!! 'NoneType' object has no attribute 'to' ChatGPT thinks that the models are not loaded properly or not connected properly in the flow. But if it works for other people then it should not be a problem :/ I did a fresh install so I'm really not sure what could be wrong. Anyone else have that error? Usually I can run AI without issue on my PC, but this is the first time I'm using ComfyUI

Paweł Pawłowski

Prompt outputs failed validation: UnetLoaderGGUF: - Value not in list: unet_name: 'wan2.2_t2v_low_noise_14B_Q8_0.gguf' not in ['Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf', 'Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf', 'Wan2.2-T2V-A14B-HighNoise-Q8_0.gguf', 'Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf'] UnetLoaderGGUF: - Value not in list: unet_name: 'wan2.2_t2v_high_noise_14B_Q8_0.gguf' not in ['Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf', 'Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf', 'Wan2.2-T2V-A14B-HighNoise-Q8_0.gguf', 'Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf'] Prompt outputs failed validation: KSamplerAdvanced: - Value not in list: scheduler: 'bong_tangent' not in ['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal'] - Value not in list: sampler_name: 'res_2s' not in (list of length 40) KSamplerAdvanced: - Value not in list: scheduler: 'bong_tangent' not in ['simple', 'sgm_uniform', 'karras', 'exponential', 'ddim_uniform', 'beta', 'normal', 'linear_quadratic', 'kl_optimal'] - Value not in list: sampler_name: 'res_2s' not in (list of length 40) Did not changed anything just raw .json from you

Silent Monk

I am getting all sort of weird artifacts in the image, mainly a blue and red glow.

Pak26

I use a 3060 12gb and with i2v mode, with a 720x480 image I generate a video in around 8 min with pretty nice results. Is there a way to speed up the video generation ?

ak pak

This has to do something with a custom node RES4LYF, but I did not figured it out for myself yet. Did you use script for installement or did you install it manually?

Oli Norwell

Making the resolution smaller for the output video will help

Remowylliams .

Having a problem getting this workflow to work. i'm getting errors for the Ksampler (advanced) saying there is 'no bong_tangent' so I changed it to Euler, then it told me there is no res_2, and changing that to simple it told me 'NoneType' object has no attribute 'io' Previously this ComfyUI install was updated and created with the Wan2.1 podrun.sh I did update all comfyui from the manager. and I restarted it.

Aitrepreneur

It's because you were using the image to video model not text to video

Aitrepreneur

only for the low noise model as I explained

Aitrepreneur

Disable magcache, I think I will just remove it for now since people are confused by iut

Aitrepreneur

you are probably using the incorrect model, like text to video for image to video or something similar

Aitrepreneur

use Q4 for the model or as Oli said, decrease the video resolution or the number of frames

Nicolas Giarrusso

It seems to get stuck after the first ksampler, I see how it generates the diffusion but it doesn't move on to the second refinement ksampler. In the LORA LOW loader node, a red circle appears over the clip joint—could something be disconnected?

James Clow

Thank you so much, that workflow template is absolute gold.

PTMarks

Any reason you are using WAN_2.1_VAE instead of WAN_2.2_VAE?

PTMarks

Have you tested with wan2.2_ti2v_5B_fp16? I got better results with this model and no Lora with some I2V images. Not sure if you've had a chance to test or have an opinion. By the way thanks for all of your work on this, and the great wf. I still have to test the F2F, but really excited about it.

Maurice

I got the same issue. I used the install script.

Josh Auriemma

I get this when I load your json and run -- any ideas? Prompt outputs failed validation: UnetLoaderGGUF: - Value not in list: unet_name: 'wan2.2_t2v_low_noise_14B_Q8_0.gguf' not in ['Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf', 'Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf', 'Wan2.2-T2V-A14B-HighNoise-Q8_0.gguf', 'Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf'] UnetLoaderGGUF: - Value not in list: unet_name: 'wan2.2_t2v_high_noise_14B_Q8_0.gguf' not in ['Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf', 'Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf', 'Wan2.2-T2V-A14B-HighNoise-Q8_0.gguf', 'Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf']

Dingus the Greater

bingo, thanks. now i gotta figure out why theres artifacts

D Dunn

why am i always getting a cross fade effect on videos made with I2V?

Aitrepreneur

yes, the wan 2.2 vae is only for the special 5B model

Aitrepreneur

yes I did, it's decently "okayish" for image to video but text to video is an absolute abomination, I get better results with the 1.3B model

Aitrepreneur

yes, I updated the workflow, just did a small mistake, just select the correct model for your GPU

Aitrepreneur

I solved the issue, just updated the runpod installer, re dl it again

Josh Auriemma

Hmm, are your sure your workflow was updated? When I update them I still get the following (after downloading your current workflow) File "D:\AI\Comfy-WAN\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-MagCache\nodes.py", line 414, in magcache_wanmodel_forward x[i*b:(i+1)*b] += self.magcache_state[k]['residual_cache'].to(x.device) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ AttributeError: 'NoneType' object has no attribute 'to'

Josh Auriemma

Nevermind. I'm dumb and didn't overwrite the old json :D

Ron Harris-White II

I get the following error, any ideas? Prompt execution failed Prompt outputs failed validation: Power Lora Loader (rgthree): - Return type mismatch between linked nodes: model, received_type(WANVIDEOMODEL) mismatch input_type(MODEL) Power Lora Loader (rgthree): - Return type mismatch between linked nodes: model, received_type(WANVIDEOMODEL) mismatch input_type(MODEL)

Virtamouse

FyI getting this error on the first and last frame. WanFirstLastFrameToVideo cannot access local variable 'clip_vision_output' where it is not associated with a value

Aitrepreneur

because you haven't updated comfyui, update it using the comfyui update bat file in the update folder

Virtamouse

That was it. Thanks. Initially I got some other errors after I updated, but I then just closed and reloaded the new WF by dragging it over again and it works fine now.

Pizza

So the BOSS walked me through a fix. The 1st Unet Loader needs the T2V High Noise as well as the 2nd Unet Loader needs the T2V Low Noise versions. He uploaded a new installer and .JSON workflow. I am very new to this and this got it working. The new installer does not have the MagCache.

Silent Monk

I downloaded the models from your Huggingface folder. They seem to have the correct name, maybe you somehow named them incorrectly? Dunno. it seems to work fine when adding an extra 5th step, but I wonder if everything is working correctly for me now.

Nicolas Giarrusso

I think the LoRA Low node is disconnected from the CLIP Loader, could it be? I connected it and it worked, the workflow was exactly as I downloaded it, so you must have saved it like that, in case you want to check it, thanks for your posts, you're awesome!

jonescrusher1

I think it's because it's in a seperate post

PTMarks

Is there anyway to define the timing or degree of the blend between frames in the Frame2Frame workflow? In some instances it works well, in others the transition is almost just a cut between images. Thanks!

Al Bore

Text to Image works fine, Text to Video works fine but when I try to use Image to Image or Image to video the output doesn't match the input Image. All the settings are not changed so I don't really know what's going on. Any help would be appreciated. Love your work

PDI

The Fantastic Talking GGUF node doesn't work, it has a bug when connected to rgthree's Power Lora Loader Node. That is what is causing the WANVIDEOMODEL to MODEL error. Deleting the folder ComfyUI-GGUF-FantasyTalking inside custom_nodes fixes it.

PDI

It's because of ComfyUI-GGUF-FantasyTalking node is replacing Unet Loader (GGUF) node. You fix it by deleting ComfyUI-GGUF-FantasyTalking inside custom_nodes folder

Josh

In your video you’re generating videos 1280x720.. I can’t even get my 5090 to generate 512x512 without getting OOM errors the low pass seems to take up 100% vram and the clear vram node seems to do nothing. Any idea what I’m doing wrong here?

Aitrepreneur

Just be very precise in your prompt with lots of details (you can use chatgpt to help embelish the prompt)

Aitrepreneur

probably because you are not using the correct model, you need to select the I2V model for image to video. For image to image, it's up to the denoise value, the higher the value the more different the final image will be from the starting image

Aitrepreneur

yeah that's definitely weird, have you changed any settings that can explain that? Like the number of frames?

Aitrepreneur

I mean it works for me but you don't have to connect the low lora node to clip

Aitrepreneur

you're probably using the wrong models here, send me screenshots of the whole parameters before generation

PDI

Google says that your downloaded model was corrupted during download. You need to download it again, if your internet is slow try using a download manager like IDM or Jdownloader

Josh

Never mind I had the —highvram flag enabled

Yovan Vujacic

Cool workflow as asual. Do you have any tricks to make a Control net like you did with 2.1 ? I gave it a try but was unsuccessful.

Dawid Ogiegło

MAGCACHE just got updated to support WAN 2.2 :)

Aitrepreneur

that's because you need the Vace Wan 2.2 model, which doesn't exist. yet

Aitrepreneur

yes but not supported inside comfyui yet, it will be next week

Yovan Vujacic

thanks for the reply! and thank you for your great videos.

Al Bore

Thanks for the quick reply :D But when I select the I2V model for both high and low noise, I get the error: UnetLoaderGGUF cannot reshape array of size 3864562 into shape (5120,5440) I've run all 3 .bat files in the update folder but still no luck.

Al Bore

Ignore me, turns out one of the I2V models didn't fully download. Am manually downloading it now. Hopefully it works

Dart Photography UK

Sorry i'm running text to image and i get stuck on the first ksampler, around 33%. -- Attempting to release mmap (63) (RES4LYF) rk_type: res_2s 0%|

Aitrepreneur

If this is the first time, sometimes it takes a while to load the model, the next few times are faster but if you have low vram and low ram this could be slow

Troy Walton

Works great so long as I don’t generate too many frames at once. (I’m using a 4090 on Runpod)

TomiTom1234

I tried the img2Video, but the result is a blurry video. I didn't change anything from the values of the workflow. Is the Manual tutorial https://pastebin.com/8jNxWZBm updated also specially the Lora files? EDIT: I also tried the Text2IMG , and I get bad results, the images are blurry. I downloaded all the models and loras manually. I use the Q5 because I have 16 VRAM, 5070 Ti.

Nibmeister

This new workflow rocks! About 4x faster than WAN2.1 on my puny 3070TI with 8 GB VRAM. 480x840 81 frames I2V.

Aitrepreneur

I have updated the manual install guide, check out my update video description, send screenshots of the parameters but you are probably using the incorrect model in the first nodes

Aitrepreneur

Yup but that's the limit of the model the more frames, the more vram it uses and the less coherent the video becomes if it becomes too long

Bicklemode

this is so good, wan2.2 is faster and better. thank youuuu

Zoran Kanti-Paul

in Frame to frame with the new workflow all I get is to 73% and then comfyui sits there doing nothing more. I have waited an hour and it has not changed.

Clint

Isn't it more prone to censorship than 2.1 though?

Keyvan Riley

what loras can run along side this workflow? meaning model type. i tried one of my older loras and was told in the code that its not the proper lora model. or do we have to wait for them to be released under a model type of wan 2.2?

Eyes_Wide_Shut

What is the max number of frames everyone able to achieve? Also what about FPS?

Eden Alon

Is there any database for 2.2 lora's I can check out and download somewhere? I don't think I understand what to filter for in Civitai

Jayson King

Any advanced video to video workflows lined up? Control nets ect, image and text is great but thats all available in comfy by default. Eager to have real control like in vace 2.1

Todgins

Try and increase the # steps. Instead of 4, 0-2, 4 2-4 try 8, 0-4, 8, 4-8 or 12, 0-6, 12 6-12 like in image below. This will increase generation time but allow for more time baking. https://ibb.co/fz8NVfGP

Frlur Flute

image to video is not working at all ... I can't fix it :(

Daniele Verdi

I reveived this message. My GPU is a 4070 super. KSamplerAdvanced Given groups=1, weight of size [5120, 36, 1, 2, 2], expected input[1, 32, 21, 90, 160] to have 36 channels, but got 32 channels instead

Salamander

I keep getting this error on the latest Image to Video workflow: "UnetLoaderGGUF cannot reshape array of size 6730640 into shape (5120,3520)" I'm using the Wan2.2-I2V-A14B-HighNoise-Q5_K_S and Wan2.2-I2V-A14B-LowNoise-Q5_K_S models for my 24 VRAM 3090. Any ideas on where I start troubleshooting this?

Jason Walsh

I had this problem, too. I solved it by updating ComfyUI and all the custom nodes! Try that.

leandrasin

Given groups=1, weight of size [5120, 36, 1, 2, 2], expected input[1, 16, 21, 90, 160] to have 36 channels, but got 16 channels instead I think its a custom node thats doing this but for the life of me cant seem to find it, any help? ..................................................................................... Ok i feel pretty stupid now -.- Just updated everything, rendering a video atm Kudos for the great work!

Ez

Very cool and works great. Any chance of getting a video+image to video workflow? I could probably look one up, but your stuff is good and I'm incredibly lazy. lol

Patrick Brown

See Nils Johan Anti below. Looks like you have a corrupted file.

Salamander

That seemed to fix it. I just redownloaded the Wan models from the repo. Thanks!

Eckard Vermeulen

Please help. im new to this patreon and ai and everything What does this mean? Prompt outputs failed validation: UnetLoaderGGUF: - Value not in list: unet_name: 'Wan2.2-T2V-A14B-LowNoise-Q8_0.gguf' not in ['Wan2.2-I2V-A14B-HighNoise-Q4_K_S.gguf', 'Wan2.2-I2V-A14B-LowNoise-Q4_K_S.gguf', 'Wan2.2-T2V-A14B-HighNoise-Q4_K_S.gguf', 'Wan2.2-T2V-A14B-LowNoise-Q4_K_S.gguf'] UnetLoaderGGUF: - Value not in list: unet_name: 'Wan2.2-T2V-A14B-HighNoise-Q8_0.gguf' not in ['Wan2.2-I2V-A14B-HighNoise-Q4_K_S.gguf', 'Wan2.2-I2V-A14B-LowNoise-Q4_K_S.gguf', 'Wan2.2-T2V-A14B-HighNoise-Q4_K_S.gguf', 'Wan2.2-T2V-A14B-LowNoise-Q4_K_S.gguf'] Just note, i used the auto installer to install everything and updated it Also if i shouldn't post this here, where should I?

Bob

same... now im trying to download manually search exact file in google to hugface, they are about 15gb each

Eckard Vermeulen

Let me know if that fixes it. Also where Do you paste the files after download?

Bob

i asked chatgpt where to place, he said put all into diffusion_models

Nicolas Giarrusso

How can I apply a mask so that it only affects a portion of the image when I do img2img in Imagen with WAN 2.2?

Eckard Vermeulen

Ah I found my problem Look at the Unet Loader. Mine's defult is diffirant to the vram package i selected at the begining. just change it to the correct one and it works. Didn't download anything to make it work

Bob

Unet Loader? where is it, select?

Fox Fo

Literally.... Cant get anything to work. Nothing. Followed all the steps. Very dissatisfying.

Aitrepreneur

you just didn't select the correct downloaded model in the node

Mahmoud Alhashim

I have this idea if you can solve it One of the biggest limitations for most creators right now is the short video duration—typically capped at around 5–10 seconds. A potential solution could be to split longer prompts into connected segments. Each prompt could continue the story by using the final frame of the previous segment as a visual input for the next. This would allow creators to build seamless, longer videos that feel continuous.

Aitrepreneur

Yeah we can already do that, I'll try to make a good workflow for a future update

Giovanni Ceriani

i have a 4090 with 24gb of vram but it always goes out of memory even if i use Q4_K_S. My starting image is 768x1365 pixels and i set to create 49 frames.. any help?

LilLegyiths

Hi! I wanted to run your batch on an Amazon EC2 instance but Windows server 2025 is throwing a 16 bit compatibility error. Ive dug into the batch file with Grok and dont see any applications that would cause that. any ideas?

Chayse Sterling

For some reason in my wan 2.2 ultra workflow. under the wan 2.2 image generation, i dont have the magcache section at all. its just missing

Testtn

It was removed ... EDIT 05 AUGUST: I UPDATED THE WORKFLOW TO REMOVE MAGCACHE SINCE SO MANY PEOPLE HAD ISSUES WITH IT SO IF YOU HAD THE ERROR.

Testtn

Brilliant idea!

Testtn

+1 Would love a multiple image to video workflow as well. Pika.art does this as well as video+image to video. The quality is fantastic but not as easy to prompt as Wan... And Pika prompting is pretty easy to begin with.

Chayse Sterling

Whenever i generate a image in wan 2.2 ultra, it just produces a white image. wan2.2-i2v-a14b-highnoise-q4_k_s,wan2.2-i2v-a14b-lownoise-q4_k_s , umt5-xxl-encoder-q5_k_s, wan_2.1_vae,wan2.2-lightning_t2v-v1.1-a14b-4teps-lora_high_fp16, wan2.2-lightning_t2v-v1.1-a14b-4teps-lora_low_fp16

Aitrepreneur

because you are using the image to video model instead of the text to video

Josh inmn

the above work flow ``` Loading aborted due to error reloading workflow data TypeError: (intermediate value).removeWidget is not a function ```

sirvz

I have same error. Maybe because ComfyUI update?

Mark Schlegel

New to this but my .jason file is missing the on off option. I tried to run updates and still not resolved. little help would be great. Thank you

Florian Schulze

what is the best way to use a lora with this workflow? please for wan 2.1 and 2.2 loras

Aitrepreneur

same as with other models...put the lora in the lora folder, then load it with the node and then use the trigger word in the prompt

Florian Schulze

and where should i put the lora for wan 2.1 because these only have one file unlike the wan 2.2

Josh inmn

@sirvz What worked for me: I deleted the comfyui_magcache folder found in my custom nodes. I guess the workflow above is still trying to make a call to it? I went into my custom nodes folder and saw that the magcache custom node was in there. I recalled that it had been removed because of the issues it was causing. (From the post: "EDIT 05 AUGUST: I UPDATED THE WORKFLOW TO REMOVE MAGCACHE SINCE SO MANY PEOPLE HAD ISSUES WITH IT SO IF YOU HAD THE ERROR:") So, I deleted the folder, and that seemed to fix the workflow loading issue. I think this post mentions two different workflows, but I only saw one to download. Wouldn't it make more sense to keep the workflow and all the install .bat files together in one place? I can see how it could be frustrating to scroll around for one after you've just downloaded the installers. Anyway, maybe the workflow that was supposed to have magcache removed was the one I had. Either way, that was the only workflow available to me above, and it wouldn't load until I removed the comfyui_magcache custom node folder.

Mark Schlegel

guess you scared it so now its working. thank you.

James Inage

Tried to do image to video and image gets cropped but also whole video is just blurry and can barely see original image details in the back

mnkjiu

I have tried this workflow on both windows and mac on windows, takes about 500 to 600 sec to generate ~5 sec vid, extremely good quality been trying on mac however, can't get pass ksampler step 0 to step 2, keep getting stuck anyone using this on mac and have success?

Waifu Art Haven

Whenever I try to use the workflow, i get this error Prompt execution failed Prompt outputs failed validation: Power Lora Loader (rgthree): - Return type mismatch between linked nodes: model, received_type(WANVIDEOMODEL) mismatch input_type(MODEL) Power Lora Loader (rgthree): - Return type mismatch between linked nodes: model, received_type(WANVIDEOMODEL) mismatch input_type(MODEL) i'm new to comfyui can you help pls

Tom Budgen

Getting this error "cannot mmap an empty file" :(

Axl9

Hi, when I use txt2Img I get image but with "wave". It's especially visible with hairs. The image is not clear (and not beautifull). I don't understand why I don't have the same image than you. I use the both wan2.2-T2V... and umt5-xxl-encoder-Q5_K_S and Wan_2.1_vae. As sampler I use Euler Beta. (I have a rtx4090). What I have missed ?

daniel baychev

if i always get "pause" does that mean i ran out of memory? 100%|████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:58<00:00, 29.03s/it] gguf qtypes: F16 (694), Q4_K (356), Q5_K (44), F32 (1) model weight dtype torch.float16, manual cast: None model_type FLOW Requested to load WAN21 loaded partially 4762.706980926514 4760.3907470703125 0 Attempting to release mmap (264) (RES4LYF) rk_type: res_2s 100%|████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:56<00:00, 28.50s/it] Requested to load WanVAE D:\ComfyUI_windows_portable>pause Press any key to continue . . .

skedsu suki

having the same error as well..TT

Waifu Art Haven

Solved mine by deleting the gguf fantasytalk custom node

skedsu suki

thanks. just solved mine as well. the same fantasytalk problem which has bunch of conflict and replaced the original gguf. removing that solved it.

Stevo T

I'm getting 5 of the custom nodes IMPORT FAILED, any fix??

Axl9

My problem is near fixed after an update of Confyui. But I find the eyes of the generated character ... bad. Expecialy, for photorealistique fantasy character. Maybe I have miss a setting...

Sam

Is there a way to clear VHS_VideoCombine Preview from last generations when opening up Comfyui?

BadgerWi Johnson

When I try to create a video from image I'm getting an error shape '[1, 16, 45, 2, 80, 2]' is invalid for input of size 4838400 2025-08-28T19:56:44.226416 - Prompt executed in 23.27 seconds ``` ## 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)

Ech0_Hue

I have a problem, everything works fine ,but the image looks latent noise, like there is no good image just noise, i dont use loras and my comfy is updated, and iam sure i used the correct two models , anyone had this?

Adam Adair

Yeah, I've done everything right and every image I generate looks like absolute garbage. Weird ghosting, bad anatomy everywhere, blur, something is wrong and i cant figure it out. I'm about to go back to flux.

Ech0_Hue

If you ever find the solution, send it because i tryed everything and still cant make it work

Ashley Barrett

is there anyway to output the last frame instead of the first with the i2v? please help chat gpt lead me down a rabbithole

Dan

When using Image to Video I end up getting a loop. For example, my last attempt I had a man taking off a jacket and turning. Everything worked great and did exactly what I wanted the first 2.5 seconds, but it just reversed the final 2.5 seconds to return to the start point. Sorry if this is an obvious fix, very, very new to using AI models and workflows. What I want is a full 5 second video of the person removing the jacket and turning their head towards the camera at the final frame.

Boy Thee

it sounds to me like you had ping pong turned on in the video compiler at the end.

Dan

I'll look for that. Thanks.

Dan

So I finally got around to checking this and ping pong was set to false. Any other ideas? Had it run again with all the same prompts and same thing happened. Running this locally if that makes a difference.

Ziad Ramadan

Bro u are the goat for not gatekeeping this

Yato

i get noisy pictures when using text2img

Jeffrey

BTW, the commands to install stuff that you used in the video are not in the video description or this Patreon post. I had to type them manually. tail -f comfyui.log

Jeffrey

chmod +x WAN2_2-ULTRA-AUTO_INSTALL-RUNPOD.sh ./WAN2_2-ULTRA-AUTO_INSTALL-RUNPOD.sh

Dirk Diggler

The videos with a single character lora turn out decent, but when I add more than one the results are not great. I'm unclear on what strength I should be setting the lighting lora, and the additional single lora at for the best results. I've googled and researched for hours, and tested it and it seems like the high noise for lightning needs to be at 3 and the low noise lightning at 1.5. Then when I add the single character lora keeping both low and high at 1 produce good results. When adding a 2nd charcter lora it throws everything off and I cant seem to find the sweet spot in that situation. If you could clarify what the ideal strength for each lora in the power lora loader that would be very helpful.

AiSon

Hey guys, can you help me please, when I drag and rop the workflow to comfyui in runpod, a error message appea "Some Nodes are Missing" - Fast Group Bypasser, Label (rgthree), FastLaplacianSharpen, FastFilmGrain. Then i close the pop up, and it doesnt work at all the tool

Baz

Hey, I had the same issue and fixed it on RunPod by installing the missing nodes manually in Jupyter. Here’s what I did: - Open JupyterLab (Port 8888 in RunPod). - Go to the Terminal. - Run these commands one by one to install the missing custom nodes: cd /ComfyUI/custom_nodes git clone https://github.com/city96/ComfyUI-GGUF.git git clone https://github.com/wallish77/wlsh_nodes.git git clone https://github.com/rgthree/rgthree-comfy.git git clone https://github.com/VRMonster/ComfyUI-Video-Enhancement-Nodes.git - Once installed, go back to ComfyUI, Update all and Restart it (use the restart button in the Manager tab). - Reload your WAN2.2 workflow, it should now open fine without the FastLaplacianSharpen or FastFilmGrain errors. If you still get FastLaplacianSharpen or FastFilmGrain errors: - Go to Custom Nodes Manager → Search for “Video Enhancement Nodes” (by VRGameDevGirl). (That pack contains FastLaplacianSharpen and FastFilmGrain.) - Install it. -- Restart comfy and reload your WAN2.2 workflow, it should now open fine without the FastLaplacianSharpen or FastFilmGrain errors.

Greono Games

the quality of the videos generated from the images are very poor.

Michael Corbett

I've tried this three times and each time the manager disappears. I also get errors for Fast Groups Bypasser and Label.

scifimovie2019

took 5 minutes to render 4 second clip at 1280x544. Using RTX 6000 ADA.

Phillip Gimmi

also have "Some Nodes are Missing" - Fast Group Bypasser, Label (rgthree), FastLaplacianSharpen, FastFilmGrain.

Charles Leonhart

The image to video part of the workflow doesn't seem to be utilizing the image I uploaded. Any thoughts?

J R

a1111

Kendeclise

This workflow uses custom nodes you haven't installed yet. FastLaplacianSharpen FastFilmGrain

Cristo

I had this workflow installed before but I lost it. Now I installed everything again and when I run a IMAGE to VIDEO, the result get so blurry, I don't know what to do. This didn't used to happen

Cristo

After I pasted this code, it asks for username and password for github

floflo tutu

I have a problem with the template on runpod, after i update comfyui, if i refresh the page comfyui is not available anymore it goes error: Code d’erreur : 403 Forbidden

Aitrepreneur

Just add a / at the end of the url then press enter