Update: WAN 2.2 Smooth Workflow v5.0 - 04/19/2026
"WAN 2.2 Smooth Workflow v5.0" update: The new version now has a First2LastFrame Workflow. Make sure to fully update your Comfyui and the extensions.
At the time of making the Showcase: Stability Matrix v2.15.7 and ComfyUI v.019.3.
Lightx2v Loras used:
HIGH with weight 1.0 -> high_noise_lora_rank64_lightx2v_4step_1022.safetensors
LOW with weight 1.5 - > lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank128_bf16.safetensors
Still uses the same extensions as v4.0 - No need to install more. Make sure ComfyUI, its dependencies and the Extensions are fully updated.
The Showcase is focused on the usage of First2LastFrame since the other workflows are pretty much the same. Added some examples of Loops you can make. I might take a few tries but its possible to make something simple - keep Loops at 5 seconds at most - Wan 2.2 doesn't work very well above that threshold.
Updated Notes: Added mode hyperlinks for some of the Resources and Models Extensions used in the Workflow.
The videos on Showcase used the SmoothMix I2V v.2.
All Extensions for WAN 2.2 Smooth Workflow v5.0:
Links for MMAudio usage:
MMAudio NSFW Model (fine-tuned off the base model)
Put the MMAudio models on ComfyUI/models/mmaudio. Create the folder if it does not exist.
Update: WAN 2.2 Smooth Workflow v4.0 - 03/14/2026
"WAN 2.2 Smooth Workflow v4.0" update: A new version with a new Ksampler method and more functions. Make sure to fully update your Comfyui and the extensions.
NAG: Now uses Normalized Attention Guidance (NAG) in Ksamplers. Check the github page more info. It makes the negative prompt be effective even at CFG 1.0 for improved quality and control.
Adaptive Prompts: You can use Adaptive Prompts when writing your Positive prompt now. Check the github page more info. To check the choices made by the Node just open the Positive Prompt Subgraph.
Updated Notes: Added hyperlinks for all Extensions used in the Workflow. Other notes have been added and updated. There are alot of little notes everywhere. Make sure to read them. ^^
The videos on Showcase used the SmoothMix I2V v.2 and SmoothMix T2v V.3.
All Extensions for WAN 2.2 Smooth Workflow v4.0:
Update: WAN 2.2 Smooth Workflow v3.0 - 19/01/26
"WAN 2.2 Smooth Workflow v3.0" update: Its a big workflow now. Make sure to fully update your Comfyui and the extensions.
All in one: Txt2vid, Img2vid and Audio Options! You can now try adding audio to your videos.
Select your workflow: I tried to make it very simple to change between the Img2vid, Txt2vid and Audio Workflows.
New fps Output: I had to change the video outputs to 25fps to make sure the audio and video are in sync.
Multiple Notes: There are alot of little notes everywhere. Make sure to read them. ^^
Added Extensions:
It uses MMAudio. So install - ComfyUI-MMAudio Nightly
And its requirements:
MMAudio NSFW Model (fine-tuned off the base model)
Puts the MMAudio models on ComfyUI/models/mmaudio. Create the folder if it does not exist.
Small Update - 10/16
Small change made to "WAN 2.2 S. Workflow v2.0" and "WAN 2.2 Txt2Video Workflow v2.0" That should allow for a faster VAE Decoding.
Update: WAN 2.2 Txt2Video Workflow v2.0 - 10/08
"WAN 2.2 Txt2Video Workflow v2.0" update: now its SUPER simple and easy to use.
I made it to use with the Smooth Mix Txt2Vid Wan 2.2 Checkpoint! Make sure to try it! ^^
Here are my recommend video setting when using the workflow with SmoothMix Txt2Vid:
Low/Mid end PCs:
Set Steps to "6" on both KSamplers;
KSampler 1 -> end_at_step = "3";
KSampler 2 -> start_at_end = "3".
High end PCs:
Set Steps to "10" on both KSamplers;
KSampler 1 -> end_at_step = "5";
KSampler 2 -> start_at_end = "5".
Update: WAN 2.2 Smooth Workflow v2.0 - 09/29
"WAN 2.2 S. Workflow v2.0" update: now its SUPER simple and easy to use.
I made it to use with the Smooth Mix Wan 2.2 Checkpoint! Make sure to try it! ^^
All the videos on the showcase for WAN 2.2 S. Workflow v2.0 used Smooth Mix Wan 2.2 Checkpoint.
It does not has Florence anymore. Make sure to install and update all necessary extensions listed below. No new extensions where used.
Update: Adv. Workflow - 08/29
"Adv. WAN 2.2 S. Workflow" update: added the Node "Color Match" before 'Video Result' and 'Last Frame' to help with color consistency.
Update: Txt2Vid Workflow
Added a txt2vid workflow. Thanks for vinque for the suggestion. =)
Update: Adv. Workflow + First2Last Frame
Made a few adjustments to the basic workflow for these new version!
Both use the same tools/weights as the basic workflow so no need to install anything new if you can already use the basic one.
Both versions have "Power Loader Node" set for the High and Low Loras.
More Loras usually means more instructions put on the Positive Prompt so Florence2 is disabled by default.
To make a looping animation on First2Last Workflow make sure to set enough time for the AI to process the loop. Try 5 or 6 seconds.
WAN 2.2 SMOOTH WORKFLOW
PLEASE make sure to read everything.
Making a simple Workflow from Wan is tricky. Wan requires are more complicated set up to work. I'm going into this assuming you have read all tutorials necessary to make Wan 2.2 work on your PC as doing that here is unresonable.
WAB 2.2 is still pretty new and there is still alot to test. All images used on the Showcase use the same set of loras, weights and configurations. The only difference was the image used and the Positive Prompt. I tried using realistic, semirealistic and anime style to show that its possible to animated any style you want by using the configuration on this workflow.
So, before we begin, this Worflow uses the following:
Use the one that fits your own specs. The one used for the showcase was the "wan2.1-i2v-14b-720p-Q8_0" version.
Out of all Loras that increases generation speed this one has given me more consistenty results.
The one used for the showcase was the "Wan21_T2V_14B_lightx2v_cfg_step_distill_lora_rank32" version.
Of course you should test other versions or Loras that speed up generation as well as well.
Showout to @CubeyAI for the Loras. Without these making NSFW results was a pain, and we can't have that can we? Make sure to use the latest version of those Loras.
Used extensions:
==========================================================
Its divided in sections to make it easy to navigate.
PROMPTS
Here is where the magic happens. So lets start here.
There are a few ways to use it:
TYPE NOTHING ON THE POSITIVE
By default Florence will create a prompt for you and a lot of times... thats enough lol. You don't need to type anything on the Positive. For examples of results that use an empty positive prompt check this and this.
I recommend you start by leaving the Positive Prompt empty at first. After you see the results you should begin working on your prompt if you did not like the results.
USE SIMPLE PROMPTS
Don't put a giant wall of text on the Positive Prompt as Florence will do that already. The showcase has Videos with very few prompts, some with just ONE.
DISABLE FLORENCE
If you really can't seem to get what you want disabling Florence might be the way to go.
FLORENCE
Choose your Florence model. Default model is "Florence-2-base-PromptGenv.2.0". Feel free to test other version or disable all of Florence nodes if you think its not helping.
CHECKPOINTS GGUF / SAFETENSOR
Very straight foward. Just choose your Checkpoint: GGUF or Safetensors. Disable the ones you are not going to use. Set to GGUF by default.
SPEEDING TOOLS AND LORAS
Here is where Sage and the Loras are set up. Feel free to change values or disable what you don't what to use.
CLIP / VAE
Still using the same as the wan 2.1
Text encoder: umt5_xxl_fp8_e4m3fn_scaled
VAE: Wan 2.1
IMAGE
Load your Image! :)
VIDEO SIZE
By default its set to 480x720 with Upscale by 2. That results in a 960x1440 video! Default upscale method is "lanczos"!
Feel free to change anything it to fit your own specs.
VIDEO LENGTH
Here you can adjust the video length.
By default is set to 81 or 5 seconds.
VIDEO SETTINGS
All settings here were set after testing. Feel free to change to your liking! :)
VIDEO PREVIEW/RESULT/LAST FRAME
You should be able to see how your video is turning out on the preview. If you don't where the results are going just cancel the run!
The video result is set to be at 30 fps. The video will be saved on Video/(Date_video_was_made).
The last frame of the video will be saved on the same folder as the video. You can use this to extent your videos! Check this post for examples.
====================================
Other recommend extensions:
Description
FAQ
Comments (61)
First one that actually works perfectly out of the box with several different loras. Very well done. thank you.
It's bizarre that SO MANY workflows don't include LORAs. Like, are people not using ANY LORAs? None at all?
@billyboy12 you can just attach your own lora loader, wheres the problem?
Works an absolute treat. Only issue I'm running into is there seems to be an issue with vaginas looking like they're hanging out and prolapsed. I'm not sure if its a lora issue or if there's a work around?
Error: KSamplerAdvanced "No module named 'sageattention'". What is the version of SageAttention?
I have never been able to get Triton to install on my machine, It keeps telling me it's for LINUX and I need a pre-set windows binaries setup, but I can never find it and get it to install
@Dredoh408 there is triton-windows on pypi
install that in your venv in which you are running comfyui:
https://pypi.org/project/triton-windows/
and that:
https://github.com/woct0rdho/SageAttention/releases
@demonkingoftyranny thank you, I'll make a fresh install and try this
How do I fix this issue?
KSamplerAdvanced
cannot import name 'sageattn_qk_int8_pv_fp16_triton' from 'sageattention' (E:\SwarmUI\dlbackend\comfy\python_embeded\Lib\site-packages\sageattention\__init__.py)
I'm using the first2last frame workflow, but I'm having an issue with the output. The video loops correctly, but the first few frames are darker then they should be. Any advice?
Thanks a lot for posting this workflow with the comments in text boxes inside. I really needed a little kickstart to figure this out. I now mostly understand the moving parts and can make my own workflow that will produce an image.
Really good workflow, i make video very fast ! but it's like a have a red filter on the video, everything is red if someone can help me ? i have disable tritton and sage attention and using WAN 2.2 a14b
Baja el peso de lora step 4, ponle 1.5 o mas bajo si lo necesitas, en este flujo viene alto al bajarlo me soluciono el problema de que se viera rojo
if on you folder video save directori the video are red i don't no but if is on the comfyui interface is probably a bug of the HDR mode of you screen.
29/08 - "Smooth Workflow adv" update: added the Node "Color Match" before 'Video Result' and 'Last Frame' to help with color consistency.
Results with this node on First2Last Frame have being a little weird for some reason when using this, so I'm going to test a little more before updating it.
Did you have any luck with this?
The regular 2.2 worked like a champ, but for the adv im getting a blurry effect no matter what i change the cfg or steps to. tried disabling the light lora too and nothing helps. Any fixes?
fixed, i wasnt going hard enough. cranked cfg to 8 and steps to 24 and the result was outstanding
Load CLIP Vision node model is missing? What to downlaod for this
Nevermind my clip_vision folder was on a different location
Thank you
ive installed triton and Sage but only works in auto mode but the mode you put fp16_triton i get a subprocess.CalledProcessError: i know its the way i probably installed it but not even youtube videos seem to really know
i don't know if you've had your issue looked at or not but i had a similar issue i changed the "Patch Sage Attention KJ"(near the top center of the workflow) to auto and it at least lets it run through an get the model working, so a bandaid fix but worth a shot.
@hypnofan i got it fixed thanks. i just used the easy install from pixorama
@Bonticarius oh cool mind posting a link for others?
@hypnofan yea use this installer instead https://github.com/Tavris1/ComfyUI-Easy-Install
I have the version that installs, not the portable version. How can I solve this problem? I've tried many things and simply don't understand what the error is. All the videos are for the portable version. I already threw my keyboard out the window.
File "C:\Users\Hiramyy\Documents\ComfyUI\custom_nodes\ComfyUI-KJNodes-main\nodes\model_optimization_nodes.py", line 87, in patchmodules
from sageattention import sageattn
ModuleNotFoundError: No module named 'sageattention'
hey bro just delete the two nodes that use sage attention, you don't need it
Can you name the two modules that are using sage attention?
Thank you for the great workflow, so much easier to get up and running compared to the mess Kijai wrapper. I appreciate you making SageAttention easy to disable since installing it is so buggy and messy. This flow is quick too.
getting some issues with the t2v everything comes out saturated or blurry with noise any suggestions?
Did you figure it out? Am getting the same issue
@OctaLoc yeah I did, try raising the cfg a good bit like 8 and the steps as well. That should clear things up a bit
@hypnofan I was thinking that higher CFG = worse results and Steps help.
Thanks for the info
@OctaLoc nice were you able to get things looking a bit better? Or were you asking for more help lol
@hypnofan asking for help mostly.
I still get garbage I2V results, in mostly zero prompt adherence.
Hello, i have the same issue, i fix the issue by up the number of step (30)
Now I have no errors, the process is going well. But! The result of the video is bad, what is the reason?
Looks like your lora strength is to high, keep the high pass lora to 0.6 and low to 1.0, also make sure that you are using itv loras if you are using itv models, and vice versa, stick with sampler euler and scheduler beta, give that a shot.
@Zeb101 It didn't help (
@AlG80 Try disabling Sageattention lora
well this was very lovely
Morning, i keep getting this error:
Given groups=1, weight of size [5120, 36, 1, 2, 2], expected input[1, 32, 25, 90, 60] to have 36 channels, but got 32 channels instead
when the flow tries to feed the sampler, any idea why? Using the Load Diffusion models not the GGUF
I had some similar problem, I changed the VAE to WAN 2.1 VAE and it works
Same here, using GGUF i2v Q4_K_M versions and WAN 2.1 VAE. Does anyone know how to fix this
@rynas Same issue error being thrown. I'm trying to figure it out, let me know if you do and I'll post if I do as well. If anyone knows or has a further idea please do post. I tried different vae files and different checkpoints (gguf and diffusion models).
@rynas update: I solved this by uninstalling a custom node called flow2-wan-video in the GUI via: ComfyUiManager>CustomNodesManager>'installed'>search 'wan'>uninstall button under 'flow2-wan-video' restart when prompted. If I have another workflow that requires it I'll re-install. I also made sure everything else was up to date, other nodes in 'used in workflow' in CustomNodesManager, as well as updating comfyui in the update folder 'updatecomfyui.bat'. Good Luck!
Do you plan to update your adv WF? Because now, it's easy to generate infinite length video with conditioning prompt etc...Only 2 scenes is way too limited.
all your videos look like 60 fps. How do you do that?
Oh I'm just using Davinci Resolve. When adding the logo on editing I also change the video to 60fps.
use the RIVE VFI before Video Combine, with the rife47.pth, it'll interpolate or something sweet
Ну ты бом бом
How to resolve problem with eyes? A lot of time i got artifatcs with eyes or face details. I'm using q8 model and tried different loras. Source picture in anime\pixar style. I'm trying to generate video 672x1024.
try to generate 720p and artifact will be gone
Increasing the resolution usually helps. Of course the further away the subject is from the viewer the lower the quality of the face and eye details will be.
Decided to try my hand on making a Wan 2.2 Checkpoint! I'm still tweaking it! See a little teaser of it on this post or check on deviantart!
I hope you guys like it! ^^
have creating 2.2.5 version
I don't really think color correct node really helps because the color shifting issue comes from video compression.
I notice the first2last frame workflow videos seem to always get brighter as it they reach the last frame, is there any way to fix this?
Mine looks like a yellow flash for like a few frame in the end