Stable Diffusion - Deforum - Openvino

[fedep]

I'm would use openvino in Stable Difusion with DEFORUM, any help?

At the moment I can't even mnake the basic, with this installation:
https://github.com/openvinotoolkit/stable-diffusion-webui/wiki/Installation-on-Intel-Silicon

for this 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 "D:\\stable-openvino2\\stable-diffusion-webui-master\\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 "D:\stable-openvino2\stable-diffusion-webui-master\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 will try in another machine.

I was able to work with https://github.com/rupeshs/fastsdcpu but i can't even install Deforum 

[Megat_Intel]

Hi Fedep,

Thank you for reaching out to us. 

For your information, I was able to install the Stable Diffusion with OpenVINO™ with the steps here:

1. Install git and Python 3.10 (The newer version of Python does not support torch), checking "Add Python to PATH".
2. Download the stable-diffusion-webui repository.

git clone https://github.com/openvinotoolkit/stable-diffusion-webui.git
cd stable-diffusion-webui
webui-user.bat

On the other hand, could you please provide us with the details below:

• OS and version
• Python version
• Full error message and which step the error occurs.

Regards,

Megat

[Megat_Intel]

Hi Fedep,

Thank you for your question. This thread will no longer be monitored since we have provided a suggestion. If you need additional information from Intel, please submit a new question.

Regards,

Megat