WAN2.2. T2I (Low Noise) -– Polyhedron: High Fashion (Haute Couture) & Glossy Wet Skin Look

So, you crazy folks,

here’s a new LoRA for high-fashion photography, focused on a fresh glossy wet look for female skin—often seen on Asian models, but long since popular in the Western modeling world as well.

I’m slowly getting WAN 2.2 (T2V) under control. While it’s primarily designed for video rather than plain single images, one doesn’t exclude the other. That’s why the training data contains no video sequences—but that shouldn’t be an issue if you want to use this LoRA for clips as well.

First up is the LOW-Noise model. As usual, the corresponding HIGH-Noise model will initially be available on my Patreon, including additional training steps and, of course, the workflow used and all images shown —both as an incentive to support my work. Believe me, these high-quality trainings on high-end RunPod machines drain my credit card faster than I can blink, but hey… revolution or death! 😄

https://www.patreon.com/polyhedron_ai

And yes: the HIGH-Noise model will follow later as a free download on Civitai. Don’t worry—I won’t forget about you.

Have fun with it! <3
Frank

P.S.: If you only use the LOW-Noise-Model, you should still place it in the High-Noise-Path with a higher weight.