V2 update: this version of lora was trained with text encoder and should have even more prompt comprehension and be more close to the artist style. All training tags can be found here
This one is best to use with some shibari/bondage/ball-gag/blindfold/pantyhose prompting. Recommended using it with autismmixes with short negatives.
I recommend to use it with vectorscope extension with setting from example images if your gens becomes too bright or unsaturated.
Description
Old version trained without TEnc.
Some of the examples images was generated with image filters extension with color 2, contrast 1 settings, if you see your gens becomes too white, I can recommend to use it too