Everything shoved into single node.
Pros:
Independent of any workflow, can be used anywhere.
Versatile. Can be chained for whatever effect: T2V+I2V extensions (unlimited)+FLF2V loop+V2V Upscale+Face Inpaint, whatever else, in a single workflow.
Cons:
Newbie unfriendly - you have to know what and how Wan does to better understand how to use it.
Lora selection - have to be performed inside the subgraph. Easy to forget and miss when they were used, but also easy to copy to the next part.
Easy to mess up inputs and parameters
RAM bloat - using multiple features with different checkpoint means comfyUI will not unload them from RAM, eventually spilling to swap file. For me, even 128GB is not enough sometimes.
Workflow json file bloat - inner wflow is massive with all the branching.
To start using, select your models (ckpts and lightning loras) inside subgraph (relevant nodes highlighted by red in top left corner), install triton and sageattention, or bypass/remove torch.compile and sageattention nodes (be a quitter and lose ~40% speed boost). Publish subgraphs (book icon) to use anywhere.
When using merges with lightning loras included, bypass or remove lightning lora loaders inside subgraph.
There's a pdf manual in the archive to help navigate subgraph's parameters. Also contains short instruction about triton and sageattention installation.
Changelog
v4 2.11.2025
Combined all Wan 2.2 and 2.1 basic features into single subgaphs.
Gathered most of VACE features into sigle subgraphs.
v3.1 17.08.2025
Added:
FunControl 2.2 - inner wflow and subgraph
Changed:
How loras added; initially i opted to using lora stacks, as only 2.1 loras were availible, to select lora once and apply to both ckpts, but now it's no longer relevant, so back to PowerLoraLoader
FunInpaint was very disappointing, so i won't be adding it. I2V is same in function and has no risk of conflicts with loras.
v3.0 01.08.2025
Added:
Wan2.2 model profiles and new nodes utilizing it's MoE capabilities
Changed:
Group nodes replaced with subgraphs
Removed:
1.3b control loras
v2.8 14.07.2025
Added:
VACE seamless extension - wflow and group node
VACE seamless loop - wflow and node
Removed:
HunYuan
LTX
v2.7 17.05.2025
WanWrapper workflow updated
VACE 14b and 1.3b
Phantom
FantasyTalking
CausVid (3step) lora
Spline dot control example
v2.6 24.04.2025
Wrapper IV2V node - crank up blocks to swap and upscale to XL resolution
FLF2V - official start-to-end frame model that rocks
Skyreels V2 DF - video extention model that takes last frames of provided video and seamlessly extends it - pretty much FramePack, but Wan
v2.5 7.04.2025
Wan wrapper consolidated - separate workflows are likely better, keeping it as proof of concept
v2.1. 4.04.2025
InterpV2V nodes added.
v2. 3.04.2025
HunYuan - standard tools: T2V, V2V, I2V (including LeapFusion), IV2V (performs poorly)
introduction of Group Nodes
v1. 31.03.2025
initial release
Description
Wrapper IV2V node
FLF2V
Skyreels V2 DF
FAQ
Comments (20)
true, "comfy is a lie."🤦♂️
Needs a tutorial breaking down the workflow and how to use it effectively.
reuploaded with advanced examples, should be enough with provided notes?
unless you mean video guide? i'm too lazy for that)
and it's efficiency lies in voiding the micro-management part of using multiple workflows. you can just chain nodes instead, in any way you see fit
So I have a unique situation. I have everything installed and I mean everything, the latest pytorch, cuda 12.8, ive got 24gb of vram, I have all the models.
I put my image in, but it just doesnt run?
There is such a large knowledge gap that I dont even know how to efficiently ask for help.
How would I start to use this for image to video?
I have every single node installed no issues. I have verified that wan video runs with triton and sage and fp16 fast
Like is there a VHS node somewhere that is the designated output? Where would I look for the output so I can reverse engineer how the node map works?
you need to provide all inputs and drag video output to VideoCombine node you added yourself. I reauploaded wflow with basic examples
File is corrupted, re-upload.
reuploaded. some of SetNodes 'forgot' the type assigned to them after nodepack update
At first, I really didn’t know where to start. But thanks to the latest examples, I can somewhat understand the design principles of workflows. I think for those who understand the process, this workflow is very helpful, and everyone should give it a try.
ty
What does this mean?
RuntimeError: Given groups=1, weight of size [1536, 16, 1, 2, 2], expected input[1, 36, 13, 56, 56] to have 16 channels, but got 36 channels instead
i ran into that error plenty of times. most often it is caused by incorrect latent length or size. size should be divisible by 16 for HY, length should abide to formula a*4+1, and some of Wan ckpts don't like it too short - lower thant 2 seconds (less then 33 frames)
resolved it every time by adjusting settings
there are more causes, it's impossible to pinpoint without looking at your wflow
@cgibson Right thanks a lot. I think I need to sit down and understand how the get and set node functions work, as well as those remote node things the 'everywhere/anywhere nodes'? I have neglected to learn those functions and they are obviously important for efficiency purposes.
What is this all about?
AttributeError: 'WanModel' object has no attribute 'vace_patch_embedding'. Did you mean: 'patch_embedding'?
I'm doing my best to not spam you with questions. I'm flipping switches on and off like a chimp in a spaceship here.
never ecountered this error
if you're using wrapper, try updating nodepack first
it could also mean you're trying to use vace nodes on regular wan model
Also in the AIO workflow, where do I input frames?
blue goes in blue
re-download archive, i added usage examples for
Extremely complex. Can you try to release something simpler for skyreels df?
No.
example workflows exist https://github.com/kijai/ComfyUI-WanVideoWrapper/tree/main/example_workflows