Maybe it's a sort of recency bias but I feel like the old CNN/GAN image generators produced far more visually interesting "art" than the hyper-realistic unnerving shit that today's generative models put out.
this post was submitted on 13 Apr 2024
33 points (100.0% liked)
NotAwfulTech
357 readers
1 users here now
a community for posting cool tech news you don’t want to sneer at
non-awfulness of tech is not required or else we wouldn’t have any posts
founded 1 year ago
MODERATORS
Reject modernity (wrong number of fingers), embrace tradition (SPIRAL EYE-HOLES ARE WATCHING YOU)
DOGS, ALL DOGS
"And every one had four faces, and every one had four wings, and every one was a good dog before the Lord, Bront"
long live the trypophobia & ommetaphobia automation tool
RIP digital drug trip, you were actually pretty cool