At 8/26/22 12:40 AM, Nabella wrote:
Wow, what a coincidence, I was debating about making a thread on this exact topic for the past week and a half.
Has anyone here seen some of the images generated by Stable Diffusion, the free open-source model anyone can download and modify? With enough patience and a beefy enough computer, it seems like you can create some very impressive results.
The following images were plucked while I was lurking on /sdg/ on /g/ and it's associate threads on /vg/, and /h/.
Prompt that was attached to this specific lady above me.
I suppose what’s needed is to train users to pick out tiny artifacts and stuff, because I could still tell what the giveaways were for those last two being AI, and if I were to review these on the Art Portal, I’d probably say “the crown is shaped a bit weird” or “I’d recommend you practice fingers, and I think I see a couple stray strokes next to her shoulder”. I probably wouldn’t be able to connect the dots that it is AI, but once I’ve mentioned the “things you need to practice”, then someone else who’s suspicious about you (or whoever’s posting them) probably could. I’m generally not a stickler for tiny details like that, but I’m good at pointing them out.