This is a textual inversion trained on pictures of wrestler Lita, aka Amy Dumas.
I hope you enjoy this textual inversion.
Feel free to leave me a tip/buy me a coffee if you like what I am doing :) (I also do commissions)
Description
FAQ
Comments (1)
I'm not sure if it's something with your process, but with all your TIs, there's something off with the eyes.
I first noticed it with the Ana Kasparian one. Shrugged it off, figured it was just a one time thing. But I just checked out the AJ Lee one and now this one and it seems to be a recurring issue.
Hard to describe it, but it's like they always look more reflective than is natural, like every picture was taken with too strong of a flash or something with their eyes always picking up light or something always having some whiteness in some part of the eye other than the sclera part of the eye.
I don't know if there's something maybe going on with Face Restore if you're using it, and the GFPGAN or Codeformers settings might be causing it. I've seen everything else seem right about an image before but then the eyes look off due to face restore.
Previously when I saw the errors myself firsthand it was because I had the strength set to like .6 or .4 or something, rather than 1.0 or something around that level.
Maybe it's not that. Maybe it's something you're doing with either your dataset or training. I don't know. I just figured I'd weigh in, in case it might help, because I do like your choice in subjects that you choose!









