• 1 Post
  • 61 Comments
Joined 2 years ago
cake
Cake day: June 13th, 2023

help-circle




  • Mixel@feddit.deto196@lemmy.blahaj.zoneRule
    link
    fedilink
    arrow-up
    8
    ·
    6 months ago

    To train a diffusion model that only outputs one image with difference is I think not possible you could do an image to image and then fix the seed so you would get a consistent result and then picking the nearest result that is nearly an identical copy





  • They probably also do some OCR on that and then let something other run over that to see if the text makes sense (basically letting another AI grade the output, commonly done to judge what’s a good dataset and what isn’t) and then just feed the ai again. Today you have a shortage of data since the internet is too small (yes I know it sounds crazy) so I wouldn’t wonder if they actually tried to use pictures and ocr to gather a bit more usable data



  • That is true, I mean I mostly only use my homelab except some game servers that I am running. And you are totally right. Only reason why I want to run proxmox or in general why I have a homelab is to learn more about servers and self hosting. I am currently in the first year of my apprenticeship and I have learned so much since I got my server up and running 😄 and I think I can learn a lot more when I am using proxmox