This is a textual inversion trained on pictures of wrestler Stacy Keibler.
Really happy with the way it came out, hope you enjoy it, too.
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 (7)
She's got legs and she knows how to use them.
Wow another one. I might as well delete mine and download yours. Great work.
Stacy is one of my all-time favorites back then in the WWE.
Out of curiosity, I downloaded the images and checkedd their exif info, how did you resize them? It seems the exif info say hiresfix was used to resize them from their default 512x768 res to 2048x3072 (basically a 4x resize).
I can't use the upscaler in the txt2img tab. So after I created a bunch of images and selected the ones for upload I batch resize them in the extras tab.
@ElizaPottinger So what settings did you use for using batch resize then if you don't mind revealing?
just putting it on 3x or 4x, and choose a upscaler I like for the image and leave the rest on 0
@ElizaPottinger Fair enough, thanks. Guess I'll just try a few of the popular upscalers like 4x ultrasharp or R-ESRGAN 4x+ and see which looks best sometime.
Fun note, I generated a few images earlier and was puzzled at how the quality of the image turned out as I copied all the information on the exif info, then I suddenly realized the problem. I was using consistentfactor v40 vivid model 😂
Gonna have to do a new batch with the non-vivid model.