Problem:
When trying to generate image using laptop python tries to use integrated GPU and fails to load the model.
Found solution:
To fix it by yourself you need to go windows settings (win+I), go to graphics and add python.exe file from Data/py to list and say that it should use discrete GPU by default.
Used device:

Windows 10
Laptop MSI Alpha 15
Processor: AMD Ryzen™ 5 5600H
Integrated GPU: AMD Radeon Graphics 512mb vram
Discrete GPU: AMD RX 6600m with 8gb vram.

Exception from sd.txt log:

[00000077] [12-29-2022 11:06:25] Traceback (most recent call last):
[00000078] [12-29-2022 11:06:25] File "C:\SD-GUI-1.8.1\Data\repo\sd_onnx\sd_onnx.py", line 64, in
[00000079] [12-29-2022 11:06:25] pipe = OnnxStableDiffusionPipeline.from_pretrained(opt.mdlpath, provider=prov, safety_checker=None)
[00000080] [12-29-2022 11:06:25] File "C:\SD-GUI-1.8.1\Data\venv\lib\site-packages\diffusers\pipeline_utils.py", line 709, in from_pretrained
[00000081] [12-29-2022 11:06:25] loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
[00000082] [12-29-2022 11:06:25] File "C:\SD-GUI-1.8.1\Data\venv\lib\site-packages\diffusers\onnx_utils.py", line 206, in from_pretrained
[00000083] [12-29-2022 11:06:25] return cls._from_pretrained(
[00000084] [12-29-2022 11:06:25] File "C:\SD-GUI-1.8.1\Data\venv\lib\site-packages\diffusers\onnx_utils.py", line 173, in _from_pretrained
[00000085] [12-29-2022 11:06:25] model = OnnxRuntimeModel.load_model(
[00000086] [12-29-2022 11:06:25] File "C:\SD-GUI-1.8.1\Data\venv\lib\site-packages\diffusers\onnx_utils.py", line 78, in load_model
[00000087] [12-29-2022 11:06:25] return ort.InferenceSession(path, providers=[provider], sess_options=sess_options)
[00000088] [12-29-2022 11:06:25] File "C:\SD-GUI-1.8.1\Data\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 347, in init
[00000089] [12-29-2022 11:06:25] self._create_inference_session(providers, provider_options, disabled_optimizers)
[00000090] [12-29-2022 11:06:25] File "C:\SD-GUI-1.8.1\Data\venv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 395, in _create_inference_session
[00000091] [12-29-2022 11:06:25] sess.initialize_session(providers, provider_options, disabled_optimizers)
[00000092] [12-29-2022 11:06:25] onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException