This is my first try with Base, expect that it will need refinements.
Retrain of https://civarchive.com/models/2222911/z-image-godpussy for Zimage Base. It was trained using the AIToolkit model. It came out ok-ish, but not great. Version 2.0 might follow in the future if there is interest in it.
Captions were done with JoyCaption.
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. Description
FAQ
Comments (11)
"...if there is interest in it" Yes, yes there always is
add examples please
They are under review for some reason.
gp.safetensors, really bro? Come on. We all have thousands of loras.
Thanks very much! Of course there is forever lasting interest in this.
So far I was struggling with getting any Lora to work on ZIT :(
I am using shader's ZIT workflow that he shared on Civit along with his BigLove checkpoints.
Any recommendation regarding a better WF that works well with Loras?..
Feels like it isn't very flexible but okayish
Not supposed to be, its for one thing.
It seems to argue with the base model quite a bit. It's either deformed anatomy and prompt adherence, or no prompt adherence and great anatomy render. Overall, its a great start! thanks for sharing!


