This was a first attempt and the results are not always perfect. It turns out to be a very difficult topic to train on and the idea was just make wan slightly better than what it is.
Depending on time and motivation, I might improve it in the future.
Captions were done with JoyCaption for images and by hand for videos, so that should give you a hint on how to prompt.
Two sample prompts:
The scene is a close-up featuring a woman's vulva, the subject is filmed from below. The subject is a woman with red hair, she is nude and has a ring on her finger. She is moving her fingers slowly across her wet labia. The scene shows pussy play. This close-up photograph features a woman's vulva, with her labia and clitoral hood clearly visible. The skin tone is light, with a natural, unfiltered appearance and visible pores. The lighting is soft and natural, likely from ambient indoor light, providing a gentle illumination that highlights the skin's texture without harsh shadows. The camera angle is slightly tilted, focusing directly on the genital area, with a shallow depth of field that keeps the background blurred. The background appears to be a beige carpet, adding a neutral, non-distracting element to the composition. There is no visible makeup, and the skin looks natural and unaltered. The aesthetic quality of the image is moderate, with an emphasis on clarity and detail rather than artistic composition. No trigger word.
Description
The lora was trained for 3000 steps in images from a place you might know. The prompts are just filler because of civitiai issues
FAQ
Comments (26)
Looks like you've incorrectly tagged it as Wan 2.1 Base Model
omfg civitai and its categories, who gives a shit at the end of the day tho
@generatorofthingsreal filters does xD
@K3NK yeah but i dont :P, not like it matters to me much at the end of the day
Never downloaded a Lora that fast
Post the results
Getting a lora that makes the fun box look pretty is always satisfying.
Is thi for I2V or T2V?
They tend to work for both, so just give it a shot.
whatever you feel like
Returning to report that I've tested it on both, works good on both
@brendacaro post?
for me in text to video the results looks always ugly :/ don't know why
Best pussy lora for wan. For i2v especially it's hard to "reveal" good looking vaginas but this lora handles it the best so far.
Is this intended just for Wan Image generation? or video too?
for whatever you want to use it for
it adds stabilty to video as well. For example using it at full strength with K3nk's cunnilingus lora works
Is this lora for the High or low noise wan2.2?
do you see that there is a high and a low version?
anus part is hard to train cause it's not pretrained in Wan as for pussy
hmm. its not working for me even with both high and low noise at 1.
then you are doing something wrong, no two ways about it
Didn't label anus well enough, it can't really do them correctly. Anus is part of the genital area.
Your feedback is very much valued and I take it to heart. Gods speed good sir.
Thanks for the anatomy lesson
I love that you used the actual name: "vulva" instead of "vagina" which is the internal part... I wish more people knew this.





