WAN 2.2 💠 T2V / I2V🔹4-6 steps🔹Loop 🔹Video extend 🔹WanVideoWrapper Workflow🔹K3NK
1.8 uses subgraph, you need latest comfyui with the latest frontend updates.
For me was: setting nightly vers on the manager then update confy from the manager too.
Since theres still the set/get bug, i had to add this contraption to the workflow
Connect only with the same number,, was either using this, or the this is basically the link that goes to the end_image in the "WanVideo ImageToVideo Encode", since i noticed when using mute on the get node, the video will end up with the loop anyway.. idk whats going on with this.. this was the only way to being able to disable the loop function without too much hassle.
v1.9
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 im utilizing since wan2.1 using Kijai's 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 Scaled models
Lightx2v LoRa needed for lower steps (faster generations)
Wan22-Lightning Lightx2v alternative, newer and better in some scenarios
RES4LYF Nodes
