Problems installing SD on computer using AMD GPU.

[81ginner]

Hi, I'm very new, I hope this is the right place to post my questions on SD. I am not experienced with using Github to ask questions.
I have a Windows 10 computer with enough specs, but the GPU is AMD RX 6600. So I understand some workarounds were needed to install Stable Diffusion.
I followed the instructions here, https://www.stablediffusiontutorials.com/2024/03/stable-diffusion-error-amd.html, but got stuck.

I got an import error
from numpy.lib.stride_tricks import broadcast_to
ImportError: cannot import name 'broadcast_to' from 'numpy.lib.stride_tricks' (C:\Users\goh_c\sd-test\stable-diffusion-webui-directml\venv\lib\site-packages\numpy\lib\stride_tricks.py)
Press any key to continue . . .

After which I couldn't start up SD, navigate to the 'website'/ UI.

Another website suggested that I try activating venv scripts, upgrading pip, etc, which I tried but no success. All requirements satisfied.

Then I tried running webui-user.bat, and got a bunch of errors.

So now these are the last lines they produced. All the warnings. And now I'm stuck.

(venv) C:\Users\goh_c\sd-test\stable-diffusion-webui-directml>webui-user.bat
venv "C:\Users\goh_c\sd-test\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
Python 3.10.6 | packaged by conda-forge | (main, Oct 24 2022, 16:02:16) [MSC v.1916 64 bit (AMD64)]
Version: v1.10.1-amd-25-g04bf93f1
Commit hash: 04bf93f
ROCm: agents=['gfx1032']
ROCm: version=6.2, using agent gfx1032
ZLUDA support: experimental
Using ZLUDA in C:\Users\goh_c\sd-test\stable-diffusion-webui-directml.zluda
C:\Users\goh_c\sd-test\stable-diffusion-webui-directml\venv\lib\site-packages\timm\models\layers_init_.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
warnings.warn(f"Importing from {name} is deprecated, please import via timm.layers", FutureWarning)
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
C:\Users\goh_c\sd-test\stable-diffusion-webui-directml\venv\lib\site-packages\pytorch_lightning\utilities\distributed.py:258: LightningDeprecationWarning: pytorch_lightning.utilities.distributed.rank_zero_only has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from pytorch_lightning.utilities instead.
rank_zero_deprecation(
Launching Web UI with arguments:
ONNX failed to initialize: Failed to import optimum.onnxruntime.modeling_diffusion because of the following error (look up to see its traceback):
Failed to import diffusers.pipelines.auto_pipeline because of the following error (look up to see its traceback):
Failed to import diffusers.pipelines.aura_flow.pipeline_aura_flow because of the following error (look up to see its traceback):
cannot import name 'UMT5EncoderModel' from 'transformers' (C:\Users\goh_c\sd-test\stable-diffusion-webui-directml\venv\lib\site-packages\transformers_init_.py)
Compilation is in progress. Please wait...

rocBLAS error: Cannot read C:\Program Files\AMD\ROCm\6.2\bin/rocblas/library/TensileLibrary.dat: No such file or directory for GPU arch : gfx1032

rocBLAS error: Could not initialize Tensile host:
regex_error(error_backref): The expression contained an invalid back reference.
Press any key to continue . . .

(venv) C:\Users\goh_c\sd-test\stable-diffusion-webui-directml>