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
Vibecoded a custom_node to blending frames when SVI combining PNG extended video. Now colorshifting is drastically reduced but i guess is still a thing, you can use color correct node to further mitigate in some way.
You will need to update my custom nodes
The PNG concatenate is now done via a K3NK node that blends 5 frames each sequence (by frame num), if you wanna create a extend without SVI you will need to use the node that says, NO SVI in the final video stage
FAQ
Comments (15)
You are awsome!!!!!!!!!!! great work ! great generosity ;)
Awesome!
great update, thank you for your time invested. quick question: have you already released wan22-gagreflex-60epoc-low-i2v-k3nk.safetensors somewhere?
Not yet, idk if I can publish that in here, even tho is trained with YouTube Emetophobia SFW videos...
@K3NK do you have a private group or channel? tg or discord? it would be great to support you, gagreflex would be incredible for the science
nice! is there a way we can use gguf with this workflow? btw what's this 'gag reflex' lora that's in the workflow? was it uploaded and censored away?
nop, is kind of comission, when i have it ready i will publish it, i dont use gguf but im pretty sure theres a gguf loader for wrapper
@K3NK ah i see, thanks for answering k3nk, you're the goat!
Just use the GGUFs and disable quantization.
@etherloth i'll try, it's just hard to see all the hidden stuff in this workflow!
@olivereads38255 you can bypass stuff to see if theres anything underneath
@K3NK understood, thank my dude!
i'm curious why t2v has 2 of those awesome lora select nodes for high noise but then i2v only has 1. does i2v have some kind of limitation there?
i'm tempted to duplicate the lora nodes for convenience, but i'm afraid i'll screw up the workflow since idk how to detangle something this complex!
just space to add the input image, feel free to duplicate and add it to the loop if needed
@K3NK ah okay thanks!