• morrowind@lemm.ee
        link
        fedilink
        English
        arrow-up
        6
        ·
        10 months ago

        good luck trying to run a video model locally

        Unless you have top tier hardware

        • brucethemoose@lemmy.world
          link
          fedilink
          English
          arrow-up
          10
          ·
          10 months ago

          1.4B should be surprisingly doable, especially once quantization/optimized kernels are figured out.

          HunyuanVideo can already run on a 12GB desktop 3060.

    • brb@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      4
      ·
      10 months ago

      How would one go about installing this? Asking because I don’t want to accidentally install it on my system

      • Sturgist@lemmy.ca
        link
        fedilink
        English
        arrow-up
        2
        ·
        10 months ago

        So, I definitely didn’t click! But having clicked on GitHub links in the past I can surmise that there’s a step by step install guide and also one for model acquisition. Just be sure not to click the link, and definitely do not follow what I assume is a very well written and easily understood step by step install guide.