[SOLVED] onnxruntime ERROR

[SimoneTruglia]

Hi guys, I'm facing this error only when I use reactor in the workflow. I've tried without reactor and it works, but when I put reactor I got this error.

I tried to unistall and reainstall reactor: same error.

I tried to unistall and reainstall comfyui and installing reactor again: same error

The erorr is this one:

[ReActor] 15:26:29 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 15:26:29 - STATUS - Analyzing Source Image...
2023-11-28 15:26:29.9026432 [E:onnxruntime:Default, provider_bridge_ort.cc:1480 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1193 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "D:\Stable Diffusion\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

EP Error D:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:743 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.
 when using ['CUDAExecutionProvider']
Falling back to ['CUDAExecutionProvider', 'CPUExecutionProvider'] and retrying.
2023-11-28 15:26:30.0196090 [E:onnxruntime:Default, provider_bridge_ort.cc:1480 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1193 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "D:\Stable Diffusion\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
  File "D:\Stable Diffusion\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 419, in __init__
    self._create_inference_session(providers, provider_options, disabled_optimizers)
  File "D:\Stable Diffusion\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 463, in _create_inference_session
    sess.initialize_session(providers, provider_options, disabled_optimizers)
RuntimeError: D:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:743 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.


The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "D:\Stable Diffusion\ComfyUI\ComfyUI\execution.py", line 153, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Stable Diffusion\ComfyUI\ComfyUI\execution.py", line 83, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Stable Diffusion\ComfyUI\ComfyUI\execution.py", line 76, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Stable Diffusion\ComfyUI\ComfyUI\custom_nodes\comfyui-reactor-node\nodes.py", line 117, in execute
    script.process(
  File "D:\Stable Diffusion\ComfyUI\ComfyUI\custom_nodes\comfyui-reactor-node\scripts\reactor_faceswap.py", line 96, in process
    result = swap_face(
             ^^^^^^^^^^
  File "D:\Stable Diffusion\ComfyUI\ComfyUI\custom_nodes\comfyui-reactor-node\scripts\reactor_swapper.py", line 195, in swap_face
    source_faces = analyze_faces(source_img)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Stable Diffusion\ComfyUI\ComfyUI\custom_nodes\comfyui-reactor-node\scripts\reactor_swapper.py", line 114, in analyze_faces
    face_analyser = copy.deepcopy(getAnalysisModel())
                                  ^^^^^^^^^^^^^^^^^^
  File "D:\Stable Diffusion\ComfyUI\ComfyUI\custom_nodes\comfyui-reactor-node\scripts\reactor_swapper.py", line 69, in getAnalysisModel
    ANALYSIS_MODEL = insightface.app.FaceAnalysis(
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Stable Diffusion\ComfyUI\ComfyUI\custom_nodes\comfyui-reactor-node\reactor_log_patch.py", line 48, in patched_faceanalysis_init
    model = model_zoo.get_model(onnx_file, **kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Stable Diffusion\ComfyUI\python_embeded\Lib\site-packages\insightface\model_zoo\model_zoo.py", line 96, in get_model
    model = router.get_model(providers=providers, provider_options=provider_options)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Stable Diffusion\ComfyUI\ComfyUI\custom_nodes\comfyui-reactor-node\reactor_log_patch.py", line 21, in patched_get_model
    session = PickableInferenceSession(self.onnx_file, **kwargs)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Stable Diffusion\ComfyUI\python_embeded\Lib\site-packages\insightface\model_zoo\model_zoo.py", line 25, in __init__
    super().__init__(model_path, **kwargs)
  File "D:\Stable Diffusion\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 430, in __init__
    raise fallback_error from e
  File "D:\Stable Diffusion\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 425, in __init__
    self._create_inference_session(self._fallback_providers, None)
  File "D:\Stable Diffusion\ComfyUI\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 463, in _create_inference_session
    sess.initialize_session(providers, provider_options, disabled_optimizers)
RuntimeError: D:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:743 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.

I'm using a 4090 laptop

CUDA is isntalled.

If I run nvidia-smi I get this:

Tue Nov 28 15:31:37 2023
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 546.17                 Driver Version: 546.17       CUDA Version: 12.3     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                     TCC/WDDM  | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA GeForce RTX 4090 ...  WDDM  | 00000000:01:00.0 Off |                  N/A |
| N/A   43C    P0              30W / 150W |      0MiB / 16376MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
|  No running processes found                                                           |
+---------------------------------------------------------------------------------------+

If I run nvcc -V I get this

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Fri_Nov__3_17:51:05_Pacific_Daylight_Time_2023
Cuda compilation tools, release 12.3, V12.3.103
Build cuda_12.3.r12.3/compiler.33492891_0

Can somebody help me and maybe explain me what is happing and how to fix, so I'll learn something new?

Thanks

[SimoneTruglia]

[SOLVED}

At the end I was able to solve it, installing CUDA Toolkit 11.8 from https://developer.nvidia.com/cuda-11-8-0-download-archive.

Now it works :)

I'll leave it here in the case someonelse will find it useful

[christianfr1025]

Just want to add, since I was experiencing the same problem and didn't fully understand the issue, although is implied from SimoneTruglia response.

The onxruntime doesn't support CUDA12.X, which I had installed causing the above error.

I just uninstalled CUDA entirely and it resolved, however noticed I use the CUDA toolkit for other things. So I installed CUDA 11.8 per SimoneTruglia's suggestion and it worked as well and probably the better solution.

[henryeke]

i use the cuda 12.1version and get the same trouble, but when i reinstall the cuda11.8, the comfyui said the cuda 11.8 is outdate and refuse to gei in, i fell the proble so funny

Prompt executed in 0.20 seconds
got prompt
Requested to load SDXLClipModel
Loading 1 new model
Requested to load SDXL
Loading 1 new model
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 31/31 [00:14<00:00, 2.21it/s]
Requested to load AutoencoderKL
Loading 1 new model
[ReActor] 22:50:28 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 22:50:28 - STATUS - Analyzing Source Image...
2023-12-30 22:50:28.3417047 [E:onnxruntime:Default, provider_bridge_ort.cc:1480 onnxruntime::TryGetProviderInfo_CUDA] D:\a_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1193 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "E:\stable\comfyui\ComfyUI_windows_portable03\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

EP Error D:\a_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:743 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.
when using ['CUDAExecutionProvider']
Falling back to ['CUDAExecutionProvider', 'CPUExecutionProvider'] and retrying.
2023-12-30 22:50:28.4056026 [E:onnxruntime:Default, provider_bridge_ort.cc:1480 onnxruntime::TryGetProviderInfo_CUDA] D:\a_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1193 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "E:\stable\comfyui\ComfyUI_windows_portable03\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "E:\stable\comfyui\ComfyUI_windows_portable03\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 419, in init
self._create_inference_session(providers, provider_options, disabled_optimizers)
File "E:\stable\comfyui\ComfyUI_windows_portable03\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 463, in _create_inference_session
sess.initialize_session(providers, provider_options, disabled_optimizers)
RuntimeError: D:\a_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:743 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "E:\stable\comfyui\ComfyUI_windows_portable03\ComfyUI\execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\stable\comfyui\ComfyUI_windows_portable03\ComfyUI\execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\stable\comfyui\ComfyUI_windows_portable03\ComfyUI\execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\stable\comfyui\ComfyUI_windows_portable03\ComfyUI\custom_nodes\comfyui-reactor-node-main\nodes.py", line 112, in execute
script.process(
File "E:\stable\comfyui\ComfyUI_windows_portable03\ComfyUI\custom_nodes\comfyui-reactor-node-main\scripts\reactor_faceswap.py", line 96, in process
result = swap_face(
^^^^^^^^^^
File "E:\stable\comfyui\ComfyUI_windows_portable03\ComfyUI\custom_nodes\comfyui-reactor-node-main\scripts\reactor_swapper.py", line 195, in swap_face
source_faces = analyze_faces(source_img)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\stable\comfyui\ComfyUI_windows_portable03\ComfyUI\custom_nodes\comfyui-reactor-node-main\scripts\reactor_swapper.py", line 114, in analyze_faces
face_analyser = copy.deepcopy(getAnalysisModel())
^^^^^^^^^^^^^^^^^^
File "E:\stable\comfyui\ComfyUI_windows_portable03\ComfyUI\custom_nodes\comfyui-reactor-node-main\scripts\reactor_swapper.py", line 69, in getAnalysisModel
ANALYSIS_MODEL = insightface.app.FaceAnalysis(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\stable\comfyui\ComfyUI_windows_portable03\ComfyUI\custom_nodes\comfyui-reactor-node-main\reactor_log_patch.py", line 48, in patched_faceanalysis_init
model = model_zoo.get_model(onnx_file, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\stable\comfyui\ComfyUI_windows_portable03\python_embeded\Lib\site-packages\insightface\model_zoo\model_zoo.py", line 96, in get_model
model = router.get_model(providers=providers, provider_options=provider_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\stable\comfyui\ComfyUI_windows_portable03\ComfyUI\custom_nodes\comfyui-reactor-node-main\reactor_log_patch.py", line 21, in patched_get_model
session = PickableInferenceSession(self.onnx_file, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\stable\comfyui\ComfyUI_windows_portable03\python_embeded\Lib\site-packages\insightface\model_zoo\model_zoo.py", line 25, in init
super().init(model_path, **kwargs)
File "E:\stable\comfyui\ComfyUI_windows_portable03\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 430, in init
raise fallback_error from e
File "E:\stable\comfyui\ComfyUI_windows_portable03\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 425, in init
self._create_inference_session(self._fallback_providers, None)
File "E:\stable\comfyui\ComfyUI_windows_portable03\python_embeded\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 463, in _create_inference_session
sess.initialize_session(providers, provider_options, disabled_optimizers)
RuntimeError: D:\a_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:743 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.

[wei0509]

remove and install 11.8

[kwas-123]

this is why i hate linux and python. it ALWAYS ends this way