• 0 Posts
  • 129 Comments
Joined 4 years ago
cake
Cake day: June 15th, 2021

help-circle











  • Ryzen 8700F (6-core, auto-overclocks to 4.76 Ghz, 65W), Radeon 6400 (the weakest gpu I found, 55W), 64GB ram, 1TB m.2 SSD, 500W power supply (I think I just needed 200W but this one was cheaper), some gigabyte wlan mainboard (my room’s lan connection doesn’t work), ATX housing (I accidentally bought the wrong size at first), a cheap cpu cooler (65W doesn’t need much cooling)

    My usecases are modded minecraft, dolphin-emu, IntelliJ, Qwen-Image (had to stock up on ram for this), BTD6, modded Balatro, VLC.



  • No. Its just the usual prejudice. You preemptively decided that those pictures are “soulless” things who want to kill you, you will see them that way.

    Its like with liberals when they see anything chinese.

    A while ago, I also thought diffusion-generated pictures would corrupt my mind, but, turns out they don’t. There is also no scientific explanation for why they would.

    Who made me think this? Who stands to gain from calling diffusion “soulless”? Artists who are mad their monopoly broke.







  • I think its that comics/cartoons don’t really have a “world model” for the machine to build. Like, with photos, the lighting and physics and stuff all follow some rules and one could build a 3d model from a photo. But with comics/cartoons, everything is exaggerated, 3d models don’t exist, lighting is vibes-based, every character is only drawn from certain angles. Let’s say the machine determines it needs to draw the cartoon character in a 45 degree angle, but all the training data only had 0 and 60 degree angles. So it would try to base it on the 3d model it should have, but trying to make a 3d model of a cartoon character just results in contradictions. So it probably displays the contradictory result, which is then of course completely wrong.