Posted by admin

Use Stable Diffusion XL/SDXL locally with AMD ROCm on Linux. Install both AUTOMATIC1111 WebUI and ComfyUI. Information about SDXL and AMD ROCm: https://stablediffusionxl.com/ https://rocm.docs.amd.com/en/latest/deploy/linux/index.html AUTOMATIC1111-Stable-Diffusion-WebUI: https://github.com/AUTOMATIC1111/stable-diffusion-webui ComfyUI: https://github.com/comfyanonymous/ComfyUI GIT, frequently already included in Linux distributions: https://git-scm.com/ Miniconda: https://docs.conda.io/en/latest/miniconda.html Test: Does PyTorch use ROCm? python3 -c 'import torch; print(torch.cuda.is_available())' Create launch.sh (see video for bracket, not allowed in this comment): curl https://gist.githubusercontent.com/evshiron/8cf4de34aa01e217ce178b8ed54a2c43/raw/a27b9575b0eb1f688042d4acf606ebfba96f5ace/launch.sh Taken from this website: https://are-we-gfx1100-yet.github.io/post/a1111-webui/#the-easy-approach Get SDXL models here: https://huggingface.co/ Good prompt examples for SDXL: https://stable-diffusion-art.com/ Good workflow for ComfyUI: https://github.com/SytanSD/Sytan-SDXL-ComfyUI In case you want to try MS Windows DirectML version of WebUI: https://github.com/lshqqytiger/stable-diffusion-webui-directml My video on how to create a bootable USB-Stick with Ubuntu Linux for GPT/UEFI. The easiest way. https://youtu.be/CPQc0l0YrkE