Is there any computer program with AI capabilities (the generative ones seen in ChatGPT; onlineText-to-Picture generators, etc.) that is actually standalone? i.e. able to run in a fully offline environment.

As far as I understand, the most popular AI technology rn consists of a bunch of matrix algebra, convolutions and parallel processing of many low-precision floating-point numbers, which works because statistics and absurdly huge datasets. So if any such program existed, how would it even have a reasonable storage size if it needs the dataset?

  • Ziggurat@sh.itjust.works
    link
    fedilink
    arrow-up
    56
    ·
    4 months ago

    There is tons of “standalone” software that you can run on your own PC

    • For Text generation, the easiest way is to get GPT4All package which allows you to run text generation model in CPU on your own PC

    • For image generation, you can try to get Easy difusion package which is an easy to use stable diffusion package, then if you like-it, time to try the “comfyUI”

    You can check !localllama@sh.itjust.works and !imageai@sh.itjust.works for some more information

    • deranger@sh.itjust.works
      link
      fedilink
      arrow-up
      2
      ·
      4 months ago

      I’ve wanted to try these out for shits and giggles - what would I expect with a 3090, is it going to take a long time to make some shitposts?

      • chicken@lemmy.dbzer0.com
        link
        fedilink
        arrow-up
        8
        ·
        4 months ago

        3090s are ideal because the most important factor is vram, and those are at the top of the plateau for vram until you get into absurdly expensive server hardware. Expect around 3 seconds for generating a 512x512 image or 4 words per second generating text at around GPT 3.5 quality.

      • Ziggurat@sh.itjust.works
        link
        fedilink
        arrow-up
        4
        arrow-down
        1
        ·
        4 months ago

        With SD 1.5 my old GTX 970was doing fine (30 second per image) I upgraded to a Radeon 7060 and with SDXL get like 4 images in these 30 seconds (but sometimes crash my Pac when loading a model)

      • tyler@programming.dev
        link
        fedilink
        arrow-up
        3
        ·
        4 months ago

        I did a bunch of image generation on my 3080 and it felt extremely fast. Enough that I was able to set it up as a shared node in one of those image generation nets and it outperformed most other people in the net.