# Stable Diffusion web UI [GitHub - AUTOMATIC1111/stable-diffusion-webui: Stable Diffusion web UI](https://github.com/AUTOMATIC1111/stable-diffusion-webui) ## Installation on Apple Silicon _2023/10/10_ Python 3.11.5 [Installation on Apple Silicon · AUTOMATIC1111/stable-diffusion-webui Wiki · GitHub](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon) ```shell git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui ``` [Downloading Stable Diffusion Models](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon#downloading-stable-diffusion-models) ``` cd stable-diffusion-webui ./webui.sh ``` ```python ModuleNotFoundError: No module named '_lzma' ``` 👉 [[Use lzma module]] ## Poor Performance _2023/10/10_ Chip: Apple M1 Memory: 8GB ``` -[IOGPUMetalCommandBuffer validate]:215: failed assertion `commit an already committed command buffer' webui.sh: line 255: 51932 Abort trap: 6           "${python_cmd}" -u "${LAUNCH_SCRIPT}" "$@" ``` ```sh ./webui.sh --opt-split-attention-v1 ``` ``` modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check. ``` ```shell ./webui.sh --opt-split-attention-v1 --medvram ``` ```shell ./webui.sh --opt-split-attention-v1 --lowvram ``` ![[00000-3049311401.png|400]]