Inpaint error [ONNXRuntimeError]

[WalterShomer]

using inpaint gives the error below, since the logs creation i've installed the pip accelerate ( which wanted tensorboard to be installed which i did) but the error hasn't changed. tried DMPS and PNDM with and without legacy, tried to run cmd as admin aswell as different browsers
would appreciate any help as this is out my understanding

*rx 5700 tx (8gb)
the current versions
python 3.1
git 2.38.1.windows.1
pip 22.3.1
onnx 1.12.0
onnxruntime 1.13.1
the D:\a\ at the Status Message isn't a path that i have ,so just assuming its some temp thing

*edit this happens after i click generate ( there is an uploaded image with a mask painted in the inpaint )
*using stable diffusion 1.5 which was manually converted ( converter wanted pytorch-lightning to be installed to work, which i did )

`Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
D:\ai\onnxdiffusersui\virtualenv\lib\site-packages\diffusers\utils\deprecation_utils.py:35: FutureWarning: It is deprecated to pass a pretrained model name or path to `from_config`.If you were trying to load a scheduler, please use <class 'diffusers.schedulers.scheduling_pndm.PNDMScheduler'>.from_pretrained(...) instead. Otherwise, please make sure to pass a configuration dictionary instead. This functionality will be removed in v1.0.0.
  warnings.warn(warning + message, FutureWarning)
Cannot initialize model with low cpu memory usage because `accelerate` was not found in the environment. Defaulting to `low_cpu_mem_usage=False`. It is strongly recommended to install `accelerate` for faster and less memory-intense model loading. You can do so with:
`
pip install accelerate
`
.
2022-11-28 13:17:27.9992643 [W:onnxruntime:, inference_session.cc:491 onnxruntime::InferenceSession::RegisterExecutionProvider] Having memory pattern enabled is not supported while using the DML Execution Provider. So disabling it for this session since it uses the DML Execution Provider.
2022-11-28 13:17:28.2592230 [W:onnxruntime:, session_state.cc:1030 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2022-11-28 13:17:28.2662583 [W:onnxruntime:, session_state.cc:1032 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
2022-11-28 13:17:30.8191094 [W:onnxruntime:, inference_session.cc:491 onnxruntime::InferenceSession::RegisterExecutionProvider] Having memory pattern enabled is not supported while using the DML Execution Provider. So disabling it for this session since it uses the DML Execution Provider.
2022-11-28 13:17:30.8938241 [W:onnxruntime:, session_state.cc:1030 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2022-11-28 13:17:30.9008354 [W:onnxruntime:, session_state.cc:1032 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
2022-11-28 13:17:32.9267102 [W:onnxruntime:, inference_session.cc:491 onnxruntime::InferenceSession::RegisterExecutionProvider] Having memory pattern enabled is not supported while using the DML Execution Provider. So disabling it for this session since it uses the DML Execution Provider.
2022-11-28 13:17:33.0036971 [W:onnxruntime:, session_state.cc:1030 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2022-11-28 13:17:33.0132865 [W:onnxruntime:, session_state.cc:1032 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
2022-11-28 13:17:44.8864234 [W:onnxruntime:, inference_session.cc:491 onnxruntime::InferenceSession::RegisterExecutionProvider] Having memory pattern enabled is not supported while using the DML Execution Provider. So disabling it for this session since it uses the DML Execution Provider.
2022-11-28 13:17:45.4037002 [W:onnxruntime:, session_state.cc:1030 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2022-11-28 13:17:45.4121412 [W:onnxruntime:, session_state.cc:1032 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
2022-11-28 13:17:47.5898731 [W:onnxruntime:, inference_session.cc:491 onnxruntime::InferenceSession::RegisterExecutionProvider] Having memory pattern enabled is not supported while using the DML Execution Provider. So disabling it for this session since it uses the DML Execution Provider.
2022-11-28 13:17:49.4486480 [W:onnxruntime:, session_state.cc:1030 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2022-11-28 13:17:49.4580168 [W:onnxruntime:, session_state.cc:1032 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
iteration 1/1
  0%|                                                                                           | 0/17 [00:00<?, ?it/s]2022-11-28 13:17:58.3517847 [E:onnxruntime:, sequential_executor.cc:369 onnxruntime::SequentialExecutor::Execute] Non-zero status code returned while running Conv node. Name:'/conv_in/Conv' Status Message: D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\MLOperatorAuthorImpl.cpp(1866)\onnxruntime_pybind11_state.pyd!00007FFCC647D0CA: (caller: 00007FFCC647E6CF) Exception(3) tid(207c) 80070057 The parameter is incorrect.

  0%|                                                                                           | 0/17 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "D:\ai\onnxdiffusersui\virtualenv\lib\site-packages\gradio\routes.py", line 292, in run_predict
    output = await app.blocks.process_api(
  File "D:\ai\onnxdiffusersui\virtualenv\lib\site-packages\gradio\blocks.py", line 1007, in process_api
    result = await self.call_function(fn_index, inputs, iterator, request)
  File "D:\ai\onnxdiffusersui\virtualenv\lib\site-packages\gradio\blocks.py", line 848, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "D:\ai\onnxdiffusersui\virtualenv\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "D:\ai\onnxdiffusersui\virtualenv\lib\site-packages\anyio\_backends\_asyncio.py", line 937, in run_sync_in_worker_thread
    return await future
  File "D:\ai\onnxdiffusersui\virtualenv\lib\site-packages\anyio\_backends\_asyncio.py", line 867, in run
    result = context.run(func, *args)
  File "D:\ai\onnxdiffusersui\onnxUI.py", line 282, in generate_click
    return run_diffusers(
  File "D:\ai\onnxdiffusersui\onnxUI.py", line 113, in run_diffusers
    batch_images = pipe(
  File "D:\ai\onnxdiffusersui\virtualenv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "D:\ai\onnxdiffusersui\virtualenv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_inpaint.py", line 428, in __call__
    noise_pred = self.unet(
  File "D:\ai\onnxdiffusersui\virtualenv\lib\site-packages\diffusers\onnx_utils.py", line 61, in __call__
    return self.model.run(None, inputs)
  File "D:\ai\onnxdiffusersui\virtualenv\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 200, in run
    return self._sess.run(output_names, input_feed, run_options)
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Conv node. Name:'/conv_in/Conv' Status Message: D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\MLOperatorAuthorImpl.cpp(1866)\onnxruntime_pybind11_state.pyd!00007FFCC647D0CA: (caller: 00007FFCC647E6CF) Exception(3) tid(207c) 80070057 The parameter is incorrect.

`

[WalterShomer]

my bad, when gpu ram touches 100% it crashes

[azuritecoin]

For inpainting, you need to use the specific model for it. https://huggingface.co/runwayml/stable-diffusion-inpainting

Legacy inpainting is if you want to use normal models.