telling stable diffusion to render photos of liminal spaces with different sampling methods, first try for each.
stable diffusion seems to like black and white quite a lot. perhaps the model i'm using, since it's trained from danbooru, has a lot of line drawings or sketches that are black and white it was trained on.
it does seem to know generally what a liminal space is, which is kind of cool considering these ones don't exist.
@matana wow that last one is super nice to look at
@matana like i've said, AI is a great artistic tool for gaining inspiration :3
moar stable diffusion: probably the most beautiful results I've gotten and I am so very stealing it
this is my SO's OC and I couldn't quite put a finger on finalizing her look, but machine just put huge hairbuns on her and I just went "that's it!!1"
@matana @LukeAlmighty very pretty
playing with stable diffusion, tried to create Raven as "drawn" by Alphonse Mucha
This picture got me banned from Mastodon.social instance.
Just pointing at the color scheme and the obvious lies of the media
#mediaManipulation
@Fiddle nowhere near as large as MS is, perhaps not as refined either.
@Fiddle 1) lots of people working on it and getting paid for their work.
2) only 1 team is making it. no such thing as windows mint, windows manjaro, windows ubuntu, arch windows, pop windows, etc.
こんにちは、私はひげさん。はじめまして!