For WAN 2.2 inference.
If you enjoy this pack and want to support my work, you can buy me a coffee here:
👉 buymeacoffee.com/designedbycrt
This is my RUNPOD referal link to earn 5$, wich is about 6h of free RTX 5090 usage : https://runpod.io?ref=u7b2habt
It also helps me to train new models, thanks.
Description
Dataset is 4 hours of diversified and trimmed (5s) videos and 5000+ images
Recommend using 8 / 12 steps, with a Lightning LoRA ( I made some comparisons for these lightning models here )
shift 8
All previews videos was generated on the full fp16 models, with the same RTX PRO 6000.
This is my RUNPOD referal link to earn 5$, wich is about 6h of free RTX 5090 usage : https://runpod.io?ref=u7b2habt
It also helps me to train new models, thanks.
FAQ
Comments (11)
is the single train model just all of the separate LORAs mixed together?
No all lora models are trained on their own, only the two large models (SSH / SSL) from the packed version are full models with a merge of few "ingredients" loras,
beware, the lora will make your character "jiggle" a lot. like, bouncing their boobs and stuff, even if prompted that the character is standing "motionless" and "not moving".
is this a warning or an endorsement? because it sounds like an endorsement...
is it possible to get the workflow please?
thank you for the insane lora pack, wish there would be a little more info about each
Hello, I'm new to AI Video creating and am using ComfyUI. I've been trying for hours to research and understand how to use these files but I've had no success. Every time I try to use them in ComfyUI nothing happens, like it doesn't recognize them.
Can someone please tell me what I need to do?
Thank you!
These files are LORA's. They're like Add-ons for Wan 2.2. You have to load the LORA with a LORA loader. Try this Workflow. There is a Power LORA loader for loading multiple LORA's. If you have no clue may concider to ask Grok or ChatGPT or else.
I wish I knew what half these files do.
Every time I try this, I get an error saying the image dimensions are only 64x64, but I cannot find the node where this is occuring. Unable to run it at the moment, despite having all the nodes
What is the main model you use in T2 and I2?