OPENGIT/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2024-12-29 19:05:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

update installation for amd gpus

ClashSAN 2023-01-15 13:31:54 +00:00
parent c195474a06
commit 1602280ec5
1 changed files with 13 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
Install-and-Run-on-AMD-GPUs.md

@ -1,4 +1,15 @@
The instructions below only work on Linux! An alternative guide for Windows user can be found [here](https://rentry.org/ayymd-stable-diffustion-v1_4-guide) (untested).
# 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.)
1. Install Python 3.10.6
2. git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
3. Place stable diffusion checkpoint (model.ckpt) in the models/Stable-diffusion directory
4. For many AMD gpus you MUST Add `--precision full` `--no-half` to `COMMANDLINE_ARGS=` in **webui-user.sh** to avoid black squares or crashing.*
5. Run **webui-user.sh**
*Certain cards like the Radeon RX 6000 Series and the RX 500 Series will function normally without the option `--precision full --no-half`, saving plenty of vram. (noted [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/5468).)
# Running natively
@ -90,6 +101,6 @@ launch-command below instead:
TORCH_COMMAND='pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/rocm5.1.1' python launch.py --precision full --no-half
```
It's possible that you don't need "--precision full", dropping "--no-half" however it may not work for everyone.
Certain cards like the Radeon RX 6000 Series and the RX 500 Series have been will function normally without the option `--precision full --no-half`, saving plenty of vram. (noted [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/5468).)
Certain cards like the Radeon RX 6000 Series and the RX 500 Series will function normally without the option `--precision full --no-half`, saving plenty of vram. (noted [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/5468).)
Always use this new launch-command from now on, also when restarting the web UI in following runs.