Installed OpenVINO™ toolkit Stable Diffusion and received the error message:
"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"
The error is due to incompatible Torch version. Install the newer Torch version 2.1.0.
cd stable-diffusion-webui
venv\Scripts\activate
pip install torch==2.1.0
To install the OpenVINO™ toolkit stable diffusion, refer to the Openvino™ Toolkit™ stable diffusion GitHub* page.