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
Automatic splitting steps using RES4LYF nodes
Added batch loader for I2V
Removed Context nodes (you can add them if you want, im just not using them..)
Brought back vrgamedevgirl Fast Film Grain node
Fixed incorrect NAG and positive text_embeds conexions
Swapped switch nodes for rhthree-confy ones
FAQ
Comments (8)
Can't get some of the nodes to install, and can't find a node repository to download straight from GIt or huggingface or modelscope.
please tell me which ones
K3NK Um, its a couple... r3l4sic or something like that, and another one, I can't get them to install. I will confirm the names when I reboot a machine and get back to you with the deets. the workflow itself LOOKS COOL though. I ASSUME it'll be a beast. I'm currently using the official comfui workflow with some tweaks, namely the 2.2 lightning lora instead of the lora that the workflow came with, but my issue is that the movement is not nearly as much as when I use the workflow without lightning with the same seed.
BreezyHeezy i was about to add the RES4LYF nodes git link but then i saw it inside the manager, maybe you need to update comfy in order to see those in the manager..?
@K3NK I did, I have the latest comfy, its ok though, I ended up just building a workflow from scratch.
what's new in 1.4 vs 1.2 > 1.3. Still on 1.2 and it works just fine, 1.3 broke reactorface for me and I could not get it fixed. Either way great workflows so far. Getting 5 sec clips at default settings within 240sec on a 5090.
Have you tried to run the install.bat in the reactor folder?
reactor nodes were not changed since 1.0, it only has the restore face one.. that node works on its own and niever give me a problem, not like the sfw version , or the mask helper.. damn reactor... xD