Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required. - GitHub - Acly/krita-ai-diffusion: Streamlined interface for gen...

Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required. - GitHub - Acly/krita-ai-diffusion: Streamlined interface for gen…

  • FaeDrifter@midwest.socialEnglish
    15·
    1 year ago

    This is suuuper cool, but looks like having linux+amdgpu limits me to the cloud option.

    I supposed this is bc we don’t have a DirectML equivalent yet.

    • wim@lemmy.sdf.org
      13·
      1 year ago

      There have been some efforts to run pytorch and StableDiffusion on ROCm. Not sure if that could be combined with this.

      • wewbullEnglish
        5·
        1 year ago

        It works today. Only problem I have is the memory management is pretty poor, and it’s pretty easy to run out of vram.

        Rx7600 8GB + 5900X Rocm 5.7.1 Pytorch 2.1

        • wim@lemmy.sdf.org
          1·
          1 year ago

          Interesting! Got any links that explain how to set it up?

          I just got a laptop with an RX 6700M 10GB ans am eager to try it :)

          • wewbullEnglish
            4·
            1 year ago

            Not really. I’ve had to do quite a bit of experimentation.

            My setup that I’ve settled on:

            • Rocm system libraries from Arch Linux
            • PyTorch nightly for Rocm pip installed into a venv (see instructions on pytorch homepage)
            • Set HSA_OVERRIDE_GFX_VERSION to 11.0.0. This is just for the RX7600 and it tells it to use the RX7900 code as the pytorch version hasn’t been compiled with 7600 support.
            • Start software.
          • wewbullEnglish
            1·
            1 year ago

            Nope. Quite happy with non-binary drivers that I can actually debug and send fixes back to AMD with.

            • taanegl@beehaw.org
              1·
              1 year ago

              I don’t disagree, but marked presedence is market presedence ^^; thank glob the industry moves fast on that though. I am also happy that AMD is bringing ROCm to general consumers by way of the Ryzen APU’s, rather than just pandering to enterprise clients like NVIDIA does.

      • ByteSeb@beehaw.org
        2·
        1 year ago

        Hmm, that’s weird. I was able to run Stable Diffusion locally with Linux + RX6600.

        Probably because I used Easy Diffusion. At first, I couldn’t get the GPU acceleration to work, and I was constantly running out of RAM (Not using VRAM), so my system always froze and crashed.

        Turns out it was a ROCM bug, that I don’t know if it’s fixed by now, but I remember “fixing it” by setting an environment variable to a previous version.

        Then, it all worked really good. Took between 30 seconds to 2 minutes to make an image.

    • pantherfarber@lemmings.world
      4·
      1 year ago

      I got it to work yesterday. Have to go into the python venv it installs, remove torch and install it the way it describes on the comfyui GitHub.