March 2024 - Stable Diffusion with AMD on windows -- use zluda ;)

SD is so much better now using Zluda!

Here is how to run automatic1111 with zluda on windows, and get all the features you were missing before!

** Only GPU's that are fully supported or partially supported with ROCm can run this, check if yours is fully or partially supported before starting! **

check if your gpu is fully supported on windows here:
https://rocm.docs.amd.com/projects/in...

Links to files and things:

Git for windows: https://gitforwindows.org/
Python: https://www.python.org/downloads/
Zluda: https://github.com/lshqqytiger/ZLUDA/...
AMD HIP SDK: https://rocm.docs.amd.com/projects/in...

Add PATH for HIP SDK and wherever you copies Zluda files to
%HIP_PATH%bin
C:\path\to\zluda\folder


Start Automatic 1111 webui
webui.bat

copy zluda cublas and cusparse to
...\stable-diffusion-webui-directml\venv\Lib\site-packages\torch\lib

delete cublas64_11 and cusparse64_11

rename zluda files
cublas.dll to cublas64_11.dll
cusparse to cusparse64_11.dll

back in terminal run webui
webui.bat --use-zluda



If you have issues with cudnn
...\stable-diffusion-webui-directml\modules\shared_init.py

Add this after def initialize
torch.backends.cudnn.enabled = False

If you have a GPU that is not fully supported in hip SDK follow these instructions
https://github.com/vladmandic/automat...