WAN 2.2 💠 T2V / I2V / S2V / T2I🔹4-6 steps🔹Loop 🔹SVI Video extend 🔹WanVideoWrapper Workflow🔹K3NK
NOTICE: IF YOU ARE NEW TO COMFYUI, I DONT RECOMMEND STARTING WITH THIS WORKFLOW, IS AN ALL IN ONE WORKFLOW YOU WILL GET CONFUSED.
I UPDATED v2.3, YOU CAN CHOOSE IF YOU WANT RES4LYF OR WVW SIGMA SPLITTING
Since v1.8 im using subgraphs, you need latest comfyui with the latest frontend updates, also probably you will need to update Comfyui Manager.
For me was: setting nightly vers on the manager then update confy from the manager too.
* i allways leave the image overlay enabled, it will error if you dont have an image on it, sorry :S
v2.0
You can choose whether to merge with the loras or not, change the lora connection from the model loader to the set loras node, after that uncheck merge_loras
The toggled i added for radial sage, requieres Sage Attention to be installed, if you dont have it you should unplug the conexion i made to the attention type on the model loaders..
Be sure to update WanVideoWrapper nodes ..
The workflow works just fine with Wan2.1 if you bypass first sampler and model loader
This workflow is included with all my uploads as metadata, drag and drop a vid to comfyui.
I run a 4090 locally
You can use it as other modes if you activate this option for enabling the required nodes.
Make sure you load the correct models on the model loaders
Kijai's WanVideoWrapper Node
Wan2.2 Kijai's models
Lightx2v LoRa needed for lower steps (faster generations)
Wan22-Lightning Lightx2v alternative, newer and better in some scenarios
NSFW Clip Vision (not really needed in wan2.2)
RES4LYF Nodes
MMAUDIO
https://huggingface.co/Kijai/MMAudio_safetensors/tree/main
once installed replace nodes.py file in the mmaudio node folder with this one: https://github.com/phazei/ComfyUI-MMAudio/blob/master/nodes.py
WAN 2.2 💠 T2V / I2V
MMAUDIO NSFW
https://huggingface.co/phazei/NSFW_MMaudio (download and rename it to "mmaudio_nsfw_large_44k_v2_fp16.safetensors")
BOYONODES
K3NK IMAGE GRAB
Description
Added secondary way to extend videos with latest frame using Boyo Nodes
Swapped the S2V encoder to the latest version of the WanVideoWrapper
Set default as no merge loras, you can change it if you like
FAQ
Comments (12)
Too complex, no tutorial, shame, I'll pass.
it also breaks ReActor if you already have it installed.
@poondoggle it only has one reactor node, it shudnt break the node unles you updated it and now is not compatible with your install.. you should check your end before saying my workflow breaks reactor dude.. i shared this with a lot of peeps and noone told me about breaking anything.. but anyway.. if you have portable is allwys good to backup python_standalone folder, coz for me, trying the new HunyuanFoley audio nodes, actually broke my python install, thankfully i had a bacukp..
@K3NK My ReActor was working fine. I installed the missing nodes and then it wasn't. I'm not blaming you. I'm blaming Python's horrible dependencies. I have 4 separate ComfyUI installs to protect against this very problem.
Any chances you add T2V support for long videos, not only I2V? I mean a use of i2v sequence at the bottom of WF after T2v.
you can do that with context windows, i just dont like it coz the settings are quite confusing, i guess there is a math to calculate the perfect params, but i wasnt successfull
@K3NK Context window doesnt work correctly - quality suffers, hard do follow the prompt, also prompt+loras affect rest of the scene - the same reason why it's hard to have some split scene with completely different actors/actions. The idea is to have an ability to change loras and prompts as it is in I2V. There is another WF T2v+ multiple I2V. But the resulting quality there is bad.
@abudfv20232323 yeah i mainly wanted to do looping as t2v, and when i managed to do it quality was bad and brightness changed at the start.. S2V works great with context windows tho..
Interesting, I wish there was a tutorial.
Just wanted to say this is a super nice workflow!
Yeah it might be complex, but honestly anyone with half a brain can operate it :D
thans for the positive comment <3
i wanted to not need to swap models everytime or having to open multiple workflows, i like to have all-in-one so you setup once , then you can swap between modes easily.
The only thing i might be changing is the speed loras loaders... i still need to change it everytime.. but that might be unavoidable, since depending the lora, you might wanna change speed lora weight.. but still easier to mute and change weights, than having to look up for lighting I2v then seach for lightx2v T2v, later go back and this time search lightx2v i2v.. xDD
Boy, Im gunna need a fuggin 8k monitor to look at this workflow WHAT THE HELL.
Love your work, keep it up tho