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.
Trigger: she is wearing tiny panties.
Also great for T2I
v2 was trained on a revised and expanded data set with new training settings. This version should be able to be turned down a bit to make it compatible with using multiple loras.
(If you have an idea or a request, send me a message. I can afford my own coffee.)
Description
FAQ
Comments (3)
Please Hunyuan version?
Can you train a Hunyuan version, or post your training dataset?
this is THE hardest thing to gather a dataset for. I've tried before. You either get micropanties product shots or porn models what arent actually wearing it. Very difficult to find the balance. How'd you do it?? Would love to know your methods of sourcing.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.