V2.1: Same as V2, but trained at 768. Seems to have slightly better ear placement, but V2 is a bit more flexible with poses and full body shots.
V2: Better quality, more granular trigger word options to select anatomy. Trained with base SD1.5 at 512, should work with other models, but seems to do best with realistic ones.
V1: Trained on Hassenblend using 18 images. Should work with other models.
Description
Trained on Hassenblend
FAQ
Comments (13)
cursed
Exactly, this is what happens when you mess with bog witches.
Too preoccupied with whether he could, he didn’t stop to think if he should.
It is something tho...
your pig women are alluring and sexy. 😍
Thank you 😊
Why?
very love these realistic animal humanoid woman. Could you please teach me how to create some pictures which could be used in training? By using Ps or only prompts? :P
awwwwh disgusting
Shocked but that's alright
No
Adding keywords like morph, manip, photomorph, or photomanip to the prompt can have a positive effect (though very occasionally they can make things worse).
Thanks for training and sharing this network!
Thanks for the tip!
Just how and why...