From f2dd776770c733b25d7aabe71c2b5f80669cda0e Mon Sep 17 00:00:00 2001 From: ClashSAN <98228077+ClashSAN@users.noreply.github.com> Date: Sun, 26 Feb 2023 12:52:08 +0000 Subject: [PATCH] update windows+amd install guide --- Install-and-Run-on-AMD-GPUs.md | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/Install-and-Run-on-AMD-GPUs.md b/Install-and-Run-on-AMD-GPUs.md index 92c24fc..bbda091 100644 --- a/Install-and-Run-on-AMD-GPUs.md +++ b/Install-and-Run-on-AMD-GPUs.md @@ -1,25 +1,25 @@ # Windows -(**In Testing**) -For Windows users, try this fork using **Direct-ml**. If you get this working, it would be nice to share here: [Discussion](https://github.com/lshqqytiger/stable-diffusion-webui-directml/discussions) +Windows+AMD support has **not** officially been made for webui, \ +but you can install lshqqytiger's fork of webui that uses **Direct-ml**. -* https://github.com/lshqqytiger/stable-diffusion-webui-directml +-Training currently doesn't work, yet a variety of features/extensions do, such as LoRAs and controlnet. [Discussion](https://github.com/lshqqytiger/stable-diffusion-webui-directml/discussions) -make sure you have the modified repositories in `stable-diffusion-webui-directml/repositories/`: +1. Install [Python 3.10.6](https://www.python.org/ftp/python/3.10.6/python-3.10.6-amd64.exe) (ticking **Add to PATH**), and [git](https://github.com/git-for-windows/git/releases/download/v2.39.2.windows.1/Git-2.39.2-64-bit.exe) +2. paste this line in cmd/terminal: `git clone https://github.com/lshqqytiger/stable-diffusion-webui-directml && cd stable-diffusion-webui-directml && git submodule init && git submodule update` \ +(you can move the program folder somewhere else.) +3. Double-click webui-user.bat +4. If it looks like it is stuck when installing or running, press enter in the terminal and it should continue. +
+If you have 4-6gb vram, try adding these flags to `webui-user.bat` like so: -* https://github.com/lshqqytiger/k-diffusion-directml/tree/master -* https://github.com/lshqqytiger/stablediffusion-directml/tree/main +- `COMMANDLINE_ARGS=--opt-sub-quad-attention --lowvram --disable-nan-check` -(rename them to `k-diffusion` and `stable-diffusion-stability-ai`) -Place any stable diffusion checkpoint (ckpt or safetensor) in the models/Stable-diffusion directory, and double-click `webui-user.bat`. If you have 4-6gb vram, try adding these flags to `webui-user.bat` like so: - -`COMMANDLINE_ARGS=--opt-sub-quad-attention --lowvram --disable-nan-check` - -You can add --autolaunch to auto open the url for you. - -If it looks like it is stuck when installing gfpgan or gfgan, press enter and it should continue. +- You can add --autolaunch to auto open the url for you. +
(The rest **below are installation guides for linux** with rocm.) + # Automatic Installation (As of [1/15/23](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/6709) you can just run webui-user.sh and pytorch+rocm should be automatically installed for you.)