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 (63)
The node called 'ComfyUI-NAG' won't install, neither via git nor manually, unfortunately.
In the file "custom_nodes\ComfyUI-NAG\chroma\layers.py", change line 5 to:
"from comfy.ldm.flux.layers import DoubleStreamBlock, SingleStreamBlock" and it works
@zzz3331 i changed it but nothing it doesn't seem to do anything
@zzz3331 That helped, thank you. It's just that for some reason, the results are turning out very 'blurry' — strange.
@zzz3331 thanks
@incubusinmyhead Genau das gleiche Problem :(
@zzz3331 that saved me too, wtf is wrong with the node lol
ComfyUI-NAG wont install, changed "layers.py" line 5, still get an error:
"
File "C:\comfyUI_wan\ComfyUI\custom_nodes\ComfyUI-Manager\glob\manager_server.py", line 455, in do_install
res = await core.unified_manager.install_by_id(node_name, version_spec, channel, mode, return_postinstall=skip_post_install)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\comfyUI_wan\ComfyUI\custom_nodes\ComfyUI-Manager\glob\manager_core.py", line 1502, in install_by_id
repo_url = the_node['files'][0]
~~~~~~~~^^^^^^^^^
KeyError: 'files'
[ComfyUI-Manager] Queued works are completed.
{'install': 1}
"
anyone?
@rsamd123923
do this in your custom nodes folder
git clone https://github.com/scottmudge/ComfyUI-NAG
scott's version worked for me.
I couldn't install it with the manager, was getting an error, but just copying the files from the git into the ComfyUI-NAG folder in custom_nodes seemed to work
this is only 5s is pointless if you going to make a workflow make it 15s or more we innovating to make more longer videos we cant be stuck on 5s videos forever
I don't get how to use the "Unet Loader (GGUF)" in img2video. To which node do I link these ? I'm fairely new to this.
It's just an alternative for model, it's not necessary.
Double left click in an empty space and search typing "unet".
Choose Unet Loader (GGUF) and drag the connection to were the safetensor loader is connected to replace that connection.
Hello Digital Pastel, Great. thanks ! I buzzed you for the news t2v v3.
With the default settings, my videos from img2video are coming out super blurry. Any idea what it could be? I can send the workflow
Genau das gleiche Problem :(
@sbdztek1394 Someone commented on this. After using Loras, my videos are no longer blurry
@art12345master306 I'm having same issues working with 2/3 loras. What weight do you use for those ?
@Zuboi "lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16" with the weights set to 3.0 on High and 1.50 on Low.
Workflow works, but i cant find a way to make the Smooth models to work, its always blurry or outright weird textures, never a video or usable assets. I also dont understand why isnt the video sized to the image, why must it be set up by hand? Am i missing something?
Genau das gleiche Problem :(
To those having issues with blurry videos using this workflow, make sure you are using the lora "lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16" with the weights set to 3.0 on High and 1.50 on Low.
Which workflow specifically are you referring to, there are quite a few here.
@essence25 Smooth workflow 4.0 AIO
lol, I've been racking my brain and spent all day trying to understand why some images were perfectly fine and others weren't, and then I see this post -.-
why is there a need for a lora? that just seems ridicules
@seaker lightx have not been merged in, in this version of smoothmix
@DigitalPastel First of all, thanks for all your great work!! Enough *asskissing ;)
I'm mostly wondering about your latest workflow and why you chose the KSampler Adv instead of WanMOEKSampler?
Great work and i enjoy all your work!
I ran the workflow, but I only got a PNG file. There is no video in the file
Thanks for your work just wondering if you were going to do anything for LTX 2.3 at all?
Going to update the SVI Pro Workflow and move on to LTX 2.3. Already tested I few things and liked the results. I'm already preparing a dataset for it to begin some training. Hopefully will have something next month. ^^
Im sorry bothering you, but it is unclear to me (im super new) how one should generate a video based on image, i put my image in and it generated completely another scene with another characters, video turned out great but i don't really know what im missing :C
I have the same doubt, I'm having the same problem
1. Are you sure you're using I2V model and not T2V?
2. You may have a wrong text-encoder.
Thank you very much for your work. I was wondering if the FLF2V feature has been removed from the V4.0 AIO version, as I can only find it in the older versions... I’d like to know if you plan to bring this feature back in a future update.
The workflow stopped at the "KSampler" node. When I double-clicked to open the "KSampler" node, I found that the border of the "VAE Decoding" node had turned red, clearly indicating an error in this node.I have 96 GB of RAM, and I've set the virtual memory to 64–128 GB. My GPU is 4090.How can I resolve this?
I keep getting the error, it says my VASE is not correctly hooked up: TypeError: 'GGUFModelPatcher' object is not subscriptable
me too
I've found the problem. It can be fixed simply by disabling Nodes 2.0.
@345493665438 I tried that but it didn't do anything for me
I would celebrate an update to the F2LF workflow.
I'll updated it! ^^
Happy Easter everyone! Finally managed to finishing testing the LTX 2.3 workflow. Will have I2V and T2V with the same layout of v4.0 AIO. LTX workflows have a lot going on but I think I managed to find a good default setup for both generations. Did not have time to prepare the post and instructions due to the holiday. Still made a fun and sexy post . ^^ Should be up tomorrow.
I liked FLORENCE why did you get rid of it in version 4?
Thanks for the awesome workflow. Probably one of the better ones out there, without having to build everything out from scratch, which that is an interesting experience lol. But one thing I see is that under the "choose your workflow" section, all the workflows say "Enable TEXT2VIDEO" and only turn that t2v option on and off while the others are not enabling. Presuming that a node might be missing despite Comfy noting that everything is good and not missing any nodes. Anyone else run into this?
Hi,
I’m using this workflow exactly as uploaded, with smoothMix_I2V_v2_High + SmoothMix_I2V_v2_Low, no LoRAs, no GGUF, no changes.
The problem is that my I2V output looks too “smooth” — blurry motion, smeared details, and a kind of long-exposure / ghosting effect instead of clean sharp movement.
Is this a known issue with these models or this workflow?
Any recommended settings or fixes?
Same here - using WAN 2.2 S. Workflow v2.0 works but not the new v4 workflow for me.
Ah. a previous comment called this out:
"To those having issues with blurry videos using this workflow, make sure you are using the lora "lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16" with the weights set to 3.0 on High and 1.50 on Low."
Did that and it works now.
Excelente Workflow, tuve problemas en algunos nodos al inicio por el node manager que no los encontraba , así que toco buscarlos manualmente. Luego de eso fue sencillo hasta que tuve otro problema con el I2V, salían borrosos y gracias a unos comentarios previos sobre el Lora lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16 mencionaban que era necesario, pues luego de descárgalo quedo cañón.
Hi, I don't know what I'm doing wrong, but when I try to run the text to video, it seems to say I'm missing a negative and positive inpurt in the wanimage to video node. I see connections there, and I filled the prompt, but I must be missing something. Any help would be greatly appreciated!
Or if anyone has a link to a tutorial. I'm a bit new at this so sorry if it's a bad question!
Hi, is there a F2LF feature in version 4.0? I can't seem to find it. thanks
The new node pack wont install for me. is there any other way to get it
After the latest update, the nodes aren't working properly, and the node on/off button isn't working. We're hoping for an update as soon as possible, please.
ComfUI latest update, 0.19.0 has broken this workflow and many of your others, nodes are installed, as are models but none of them are found, just the generic "node packages not installed" and it refuses to work, hopefully we can get an update that fixes them, your older workflows, v2.0 work fine BTW!
Hey, I updated ComfyUI and now the Smooth Wan 2.2 I2V workflow isn’t working properly. Will this be fixed in a new workflow update? If yes, any idea when? If not, which ComfyUI version should I use to make it work again?
Which workflow exactly, give me the link from above to test it.
@essence25 v4.0 AIO