Wan 2.2 - Official Release!

A special thanks to tdrussell and and diffusion-pipe! They cracked the code. This version was trained with their newest settings for Wan 2.2. You need both the HIGH and LOW models (they are different). Run both with a strength of 1.0. All sample images were generated with the lightx2v lora. 12 steps, 6 on each model... 2 minutes to generate on an RTX 5090.

Workflow is in the 'training data' download file.

Triggers: "Her hand is in her panties." "She slides her hand in her panties." "She rubs her vagina." "She rubs her vagina fast.

v4 - A new version trained with my newest training settings. Should mix very well with other LoRAs.

v0.3 is the same data set as v0.2 but I retrained on the T2V model. v0.3 works with T2V as well as I2v.

(If you have an idea or a request, send me a message. I can afford my own coffee.)