WAN 2.2
You should use the high and low models in your workflows. I have used the low model with WAN 2.1 successfully as well.
Trained on the same dataset as versions 1 of my Z-Image Turbo and LTX-2 LoRA, but for WAN 2.2
I replaced the 10k step low-noise model originally posted with the 9750-step model since I was getting some double headed penises there.
Description
Trained on same dataset as LTX-2 and ZIT version 1 of my other Penis LoRAs.
Trained with ~150 images using AI Toolkit
Trigger: bwc