The model I think is fairly self explanatory.

Can't really figure out how to prompt this one 'properly' or what checkpoint to use. My ace in the hole trick of using illustrious 2.0 base model didn't entirely work, but made some very funny stuff. I guess hi-res fix just ruins anything you generate with the illustrious 2.0 model? Or at least it does when I try to make it upscale a lora image.

Odd, not sure what's up with that.

I'm a bit tired of attempting prompts so I'll share what I got out of it.

Also, my auto-tagger also seems to have gone hay-wire? I've noticed ever since the x-com ones I did early in the day that it's tagging a lot of colors wrong, and it's not even close, on the x-com first one it suggested that the grey jumpsuits were orange. But like, then the two anime models worked -better- than they should have, and the 40k x-com one worked well, it's all kind of a mystery. I'm going to have to figure out what's going wrong with these 'western/retro/comical' models.

https://vocaroo.com/1dCKgpymuk1M

Back to my devilish tricks.

Works well at a strength of 1

Previews made with Nova FurryV110