SDXL
v2 is an adjuster/slider model that comes in a SDXL and SD 1.5 model variant. It's trained on front, below and from behind images. It was trained before pony and illustrious models existed but seems to work on many mixes if the weight is set high enough (more than 2 on some models)
Flux.2 Klein 9B
v7a is trained on Flux2-Klein-9B. It was trained as an image-to-image model but also seems to work for text-to-image. The main keyword used for training is "fix her crotch" but it is not required for it to work. To simplify training, unlike v6, this model was just trained with the slit pussy type. I may release other variants in the future.
v7b is a Flux2-Klein-9B img2img model similar to v7a, but trained on an innie pussy with a protruding clitoral hood.
Z-Image
v6 is trained on zimage (and also works with turbo). It's a multi-concept lora. Using "pussy slit" or "slit" will create an innie. Other concepts that seem to work at least some of the time in testing include "clitoral hood", "spreading own vagina with fingers, one hand", "spreading own pussy with both hands", "penis", and "vaginal sex"
v3 is trained for z-image turbo. It's an adjuster/slider model with no keyword needed.
Qwen
v4 is trained for qwen-image-edit-2511. It should handle input images in most styles including anime or furry content. it should also do a better job of drawing buttholes than previous models and also supports images with anal penetration (vaginal penetration not trained). The main activation keywords to use are either "adjust her pussy", "adjust her pussy and anus", or "adjust her pussy, anal"
Chroma
v5 is trained for Chroma. It works best when the keyword "cleft of venus" is used.
Stable Diffusion 1.5
v1 is an SD 1.5 adjuster/slider model. It's trained only on low angle images from the front.
v2 is trained on images from more angles (note there are 2 different v2 models. An SD 1.5 version and a SDXL version)
Description
This is a Chroma model. It works best when the keyword "cleft of venus" is used.
FAQ
Comments (10)
I love this but dude couldn't you just like change the name to p*ssyfix or innie or something. Also it works great on some, but other times the p is too extruded still would be great to have it totally inni. Anyways you're awesome if you want to do another one for SDXL, don't hesitate. (Yeah a lot of us still use that locally.)
Is it possible to have a Z image Base version too? i tried the turbo one with some base checkpoints without success. Thank you.
Edit: seems to only be for certain inputs. Works great.
For anyone wondering, applying negative weights does not add more labia, it just washes out the area.
During v4 training and testing I just used the Qwen Image Edit 2511 model. I Just tested the qwen version on Qwen-Rapid-AIO-NSFW-v23.safetensors and can confirm it works at a weight of 1. None of the labiaplasty models have been trained with the intention of supporting negative weights.
Do you have the dataset to share? Could be interesting to systematically flip the order of specific image pairs with different prompt/keywords to allow editing between different «archetypes» of pussies.
Plans for a Klein9b version?
I'm currently planning to train a Klein9b version after zimage-base
nice!
@m99 waiting
would love to see an illustrious Version, i use the SDXL Version on illsutrious but it has just a low chance of 33% to give acceptable images. If you dont have the time you could share a dataset so myself and others could add this feature to models .