Error trying to run A1111

[Krebzonide]

I was trying to follow along with a video from Intel (https://www.youtube.com/watch?v=5X0RmlH6JI4) to use A1111. I am unable to generate an image with the gpu. If I do not select any script, it does generate very slowly with my cpu. If I select the 'Accelerate with OpenVINO' script, then choose gpu, then generate I get an error:

BackendCompilerFailed: openvino_fx raised RuntimeError: ShapeProp error for: node=%self_norm1 : [#users=1] = call_module[target=self_norm1](args = (%input_tensor,), kwargs = {}) with meta={'nn_module_stack': {'self_norm1': <class 'torch.nn.modules.normalization.GroupNorm'>}, 'stack_trace': ' File "C:\\Users\\Admin\\AppData\\Local\\Programs\\Python\\Python310\\stable-diffusion-webui\\venv\\lib\\site-packages\\diffusers\\models\\resnet.py", line 691, in forward\n hidden_states = self.norm1(hidden_states)\n'} While executing %self_norm1 : [#users=1] = call_module[target=self_norm1](args = (%input_tensor,), kwargs = {}) Original traceback: File "C:\Users\Admin\AppData\Local\Programs\Python\Python310\stable-diffusion-webui\venv\lib\site-packages\diffusers\models\resnet.py", line 691, in forward hidden_states = self.norm1(hidden_states) Set torch._dynamo.config.verbose=True for more information You can suppress this exception and fall back to eager by setting: torch._dynamo.config.suppress_errors = True

I looked up this error and saw another person saying something about using their igpu, and they said it worked on the dgpu without the script selected. Also in the youtube video he explained the difference. I have a 12600KF so I don't have an igpu.

I am not very familiar with python to begin with. It took me an hour just to get the webui to start because I kept getting different errors and I had to use random scripts from the internet to fix it. I got stuck here and none of the answers I found helped me.

[Megat_Intel · Accepted solution]

Hi Krebzonide,

Thank you for reaching out to us.

The error might be due to the incompatible Torch version. Could you please confirm with us your Torch version?

cd stable-diffusion-webui
venv\Scripts\activate
pip show torch

 

Please try to install Torch version 2.1.0 and see if this fixes your issue.

pip install torch==2.1.0

If you are still facing any issues, please provide us with screenshots and details of the error messages from the WebUI and the command prompt, Thank you.

Regards,

Megat

[Krebzonide]

Yes using Torch 2.1.0 solved my issue. I only tried 2.0.1+cu118 and 2.0.1+cpu because those were the versions listed in the other forum post. Thank you.

[Megat_Intel]

Hi Krebzonide,

Thank you for your question. This thread will no longer be monitored since this issue has been resolved. If you need any additional information from Intel, please submit a new question.

Regards,

Megat