[SOLVED] ValueError: This ORT build has ['AzureExecutionProvider', 'CPUExecutionProvider'] enabled

[cguykim]

First, confirm

• I have read the instruction carefully
• I have searched the existing issues
• I have updated the extension to the latest version

What happened?

Always loops back to this 1 specific error.

Steps to reproduce the problem

1. Generate any image with reactor enabled
2. Read the Error

Sysinfo

RTX 3080 12G
automatic1111 (1.6.0)

Relevant console log

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.6.0
Commit hash: 5ef669de080814067961f28357256e8fe27544f4
current transparent-background 1.2.4
Launching Web UI with arguments: --xformers --no-half-vae --autolaunch
Stop Motion CN - Running Preload
Set Gradio Queue: True
Civitai Helper: Get Custom Model Folder
Civitai Helper: Load setting from: C:\sd.webui\webui\extensions\Stable-Diffusion-Webui-Civitai-Helper\setting.json
Civitai Helper: No setting file, use default
Tag Autocomplete: Could not locate model-keyword extension, Lora trigger word completion will be limited to those added through the extra networks menu.
[-] ADetailer initialized. version: 23.9.3, num models: 9
2023-09-21 15:29:09,191 - ControlNet - INFO - ControlNet v1.1.410
ControlNet preprocessor location: C:\sd.webui\webui\extensions\sd-webui-controlnet\annotator\downloads
2023-09-21 15:29:09,378 - ControlNet - INFO - ControlNet v1.1.410
[Vec. CC] Style Sheet Loaded...
Loading weights [327c0c5702] from C:\sd.webui\webui\models\Stable-diffusion\3d core model.safetensors
Creating model from config: C:\sd.webui\webui\configs\v1-inference.yaml
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 23.2s (prepare environment: 6.1s, import torch: 4.4s, import gradio: 1.8s, setup paths: 1.0s, initialize shared: 0.3s, other imports: 1.0s, setup codeformer: 0.3s, load scripts: 5.8s, create ui: 1.9s, gradio launch: 0.6s).
Loading VAE weights specified in settings: C:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.safetensors
Applying attention optimization: xformers... done.
Model loaded in 9.8s (load weights from disk: 1.8s, create model: 0.7s, apply weights to model: 4.2s, apply half(): 1.3s, load VAE: 0.6s, calculate empty prompt: 1.0s).
Checking ReActor requirements... Ok
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.6.0
Commit hash: 5ef669de080814067961f28357256e8fe27544f4
current transparent-background 1.2.4
Checking ReActor requirements... Ok
Launching Web UI with arguments: --xformers --no-half-vae --autolaunch
Stop Motion CN - Running Preload
Set Gradio Queue: True
Civitai Helper: Get Custom Model Folder
Civitai Helper: Load setting from: C:\sd.webui\webui\extensions\Stable-Diffusion-Webui-Civitai-Helper\setting.json
Civitai Helper: No setting file, use default
Tag Autocomplete: Could not locate model-keyword extension, Lora trigger word completion will be limited to those added through the extra networks menu.
[-] ADetailer initialized. version: 23.9.3, num models: 9
2023-09-21 15:31:36,007 - ControlNet - INFO - ControlNet v1.1.410
ControlNet preprocessor location: C:\sd.webui\webui\extensions\sd-webui-controlnet\annotator\downloads
2023-09-21 15:31:36,141 - ControlNet - INFO - ControlNet v1.1.410
15:31:36 - ReActor - STATUS - Running v0.4.2-b2
[Vec. CC] Style Sheet Loaded...
Loading weights [327c0c5702] from C:\sd.webui\webui\models\Stable-diffusion\3d core model.safetensors
Creating model from config: C:\sd.webui\webui\configs\v1-inference.yaml
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 23.2s (prepare environment: 6.4s, import torch: 4.2s, import gradio: 1.6s, setup paths: 0.9s, initialize shared: 0.2s, other imports: 0.9s, setup codeformer: 0.3s, load scripts: 6.3s, create ui: 2.0s, gradio launch: 0.4s).
Loading VAE weights specified in settings: C:\sd.webui\webui\models\VAE\vae-ft-mse-840000-ema-pruned.safetensors
Applying attention optimization: xformers... done.
Model loaded in 8.9s (load weights from disk: 1.9s, create model: 0.7s, apply weights to model: 3.7s, apply half(): 1.2s, load VAE: 0.3s, calculate empty prompt: 1.0s).
100%|██████████████████████████████████████████████████████████████████████████████████| 45/45 [00:07<00:00,  6.34it/s]
15:32:24 - ReActor - STATUS - Working: source face index [0], target face index [0]████| 45/45 [00:06<00:00,  7.04it/s]
15:32:24 - ReActor - STATUS - Detecting Source Face, Index = 0
*** Error running postprocess_image: C:\sd.webui\webui\extensions\sd-webui-reactor\scripts\reactor_faceswap.py
    Traceback (most recent call last):
      File "C:\sd.webui\webui\modules\scripts.py", line 675, in postprocess_image
        script.postprocess_image(p, pp, *script_args)
      File "C:\sd.webui\webui\extensions\sd-webui-reactor\scripts\reactor_faceswap.py", line 362, in postprocess_image
        result, output, swapped = swap_face(
      File "C:\sd.webui\webui\extensions\sd-webui-reactor\scripts\reactor_swapper.py", line 279, in swap_face
        source_face, wrong_gender, source_age, source_gender = get_face_single(source_img, face_index=source_faces_index[0], gender_source=gender_source)
      File "C:\sd.webui\webui\extensions\sd-webui-reactor\scripts\reactor_swapper.py", line 198, in get_face_single
        face_analyser = copy.deepcopy(getAnalysisModel())
      File "copy.py", line 172, in deepcopy
      File "copy.py", line 271, in _reconstruct
      File "copy.py", line 146, in deepcopy
      File "copy.py", line 231, in _deepcopy_dict
      File "copy.py", line 146, in deepcopy
      File "copy.py", line 231, in _deepcopy_dict
      File "copy.py", line 172, in deepcopy
      File "copy.py", line 271, in _reconstruct
      File "copy.py", line 146, in deepcopy
      File "copy.py", line 231, in _deepcopy_dict
      File "copy.py", line 172, in deepcopy
      File "copy.py", line 273, in _reconstruct
      File "C:\sd.webui\system\python\lib\site-packages\insightface\model_zoo\model_zoo.py", line 33, in __setstate__
        self.__init__(model_path)
      File "C:\sd.webui\system\python\lib\site-packages\insightface\model_zoo\model_zoo.py", line 25, in __init__
        super().__init__(model_path, **kwargs)
      File "C:\sd.webui\system\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 432, in __init__
        raise e
      File "C:\sd.webui\system\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 419, in __init__
        self._create_inference_session(providers, provider_options, disabled_optimizers)
      File "C:\sd.webui\system\python\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 451, in _create_inference_session
        raise ValueError(
    ValueError: This ORT build has ['AzureExecutionProvider', 'CPUExecutionProvider'] enabled. Since ORT 1.9, you are required to explicitly set the providers parameter when instantiating InferenceSession. For example, onnxruntime.InferenceSession(..., providers=['AzureExecutionProvider', 'CPUExecutionProvider'], ...)

---
Total progress: 100%|██████████████████████████████████████████████████████████████████| 45/45 [00:08<00:00,  5.18it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 45/45 [00:08<00:00,  7.04it/s]

Additional information

This error is a little bit different from below strangers Post.
(if you look closely, you will see the difference different, deepcopy, reconstruct )

[cguykim]

I follow your answer from below posts, and it works!

python -m pip install -U pip
pip uninstall -y onnx onnxruntime onnxruntime-gpu onnxruntime-silicon
pip uninstall -y onnxruntime-extensions <<<<< This i didn't have it, but i tried.
pip install onnx==1.14.0 onnxruntime==1.15.0

Thanks!

[Gourieff]

I follow your answer from below posts, and it works!

python -m pip install -U pip pip uninstall -y onnx onnxruntime onnxruntime-gpu onnxruntime-silicon pip uninstall -y onnxruntime-extensions <<<<< This i didn't have it, but i tried. pip install onnx==1.14.0 onnxruntime==1.15.0

Thanks!

You're welcome!

[Gourieff]

So, this is the source of 'AzureExecutionProvider' Issue: microsoft/onnxruntime#17631
Fixed in the last commit 41d5b1e - the ORT requirement is set to 1.15.1 strictly - until Microsoft will fix this moment with 1.16.1 patch

[alenknight]

I follow your answer from below posts, and it works!

python -m pip install -U pip pip uninstall -y onnx onnxruntime onnxruntime-gpu onnxruntime-silicon pip uninstall -y onnxruntime-extensions <<<<< This i didn't have it, but i tried. pip install onnx==1.14.0 onnxruntime==1.15.0

Thanks!

I tried this and now Comfyui won't load up.... any idea what broke?

C:\AI\ComfyUI>.\python_embeded\python.exe -s ComfyUI\main.py --listen --windows-standalone-build
** ComfyUI start up time: 2023-09-24 16:12:17.313024

Prestartup times for custom nodes:
   0.0 seconds: C:\AI\ComfyUI\ComfyUI\custom_nodes\ComfyUI-Manager

Total VRAM 24576 MB, total RAM 32704 MB
xformers version: 0.0.21
Traceback (most recent call last):
  File "C:\AI\ComfyUI\ComfyUI\comfy\model_management.py", line 211, in <module>
    import accelerate
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\accelerate\__init__.py", line 3, in <module>
    from .accelerator import Accelerator
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\accelerate\accelerator.py", line 35, in <module>
    from .checkpointing import load_accelerator_state, load_custom_state, save_accelerator_state, save_custom_state
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\accelerate\checkpointing.py", line 24, in <module>
    from .utils import (
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\accelerate\utils\__init__.py", line 142, in <module>
    from .megatron_lm import (
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\accelerate\utils\megatron_lm.py", line 32, in <module>
    from transformers.modeling_outputs import (
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\transformers\__init__.py", line 30, in <module>
    from . import dependency_versions_check
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\transformers\dependency_versions_check.py", line 17, in <module>
    from .utils.versions import require_version, require_version_core
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\transformers\utils\__init__.py", line 34, in <module>
    from .generic import (
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\transformers\utils\generic.py", line 33, in <module>
    import tensorflow as tf
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\__init__.py", line 37, in <module>
    from tensorflow.python.tools import module_util as _module_util
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\python\__init__.py", line 37, in <module>
    from tensorflow.python.eager import context
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\python\eager\context.py", line 29, in <module>
    from tensorflow.core.framework import function_pb2
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\core\framework\function_pb2.py", line 16, in <module>
    from tensorflow.core.framework import attr_value_pb2 as tensorflow_dot_core_dot_framework_dot_attr__value__pb2
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\core\framework\attr_value_pb2.py", line 16, in <module>
    from tensorflow.core.framework import tensor_pb2 as tensorflow_dot_core_dot_framework_dot_tensor__pb2
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\core\framework\tensor_pb2.py", line 16, in <module>
    from tensorflow.core.framework import resource_handle_pb2 as tensorflow_dot_core_dot_framework_dot_resource__handle__pb2
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\core\framework\resource_handle_pb2.py", line 16, in <module>
    from tensorflow.core.framework import tensor_shape_pb2 as tensorflow_dot_core_dot_framework_dot_tensor__shape__pb2
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\core\framework\tensor_shape_pb2.py", line 36, in <module>
    _descriptor.FieldDescriptor(
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\google\protobuf\descriptor.py", line 561, in __new__
    _message.Message._CheckCalledFromGeneratedFile()
TypeError: Descriptors cannot not be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:
 1. Downgrade the protobuf package to 3.20.x or lower.
 2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).

More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates

ERROR: LOW VRAM MODE NEEDS accelerate.
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync
VAE dtype: torch.bfloat16
Using xformers cross attention
Traceback (most recent call last):
  File "C:\AI\ComfyUI\ComfyUI\main.py", line 72, in <module>
    import execution
  File "C:\AI\ComfyUI\ComfyUI\execution.py", line 11, in <module>
    import nodes
  File "C:\AI\ComfyUI\ComfyUI\nodes.py", line 20, in <module>
    import comfy.diffusers_load
  File "C:\AI\ComfyUI\ComfyUI\comfy\diffusers_load.py", line 4, in <module>
    import comfy.sd
  File "C:\AI\ComfyUI\ComfyUI\comfy\sd.py", line 12, in <module>
    from . import clip_vision
  File "C:\AI\ComfyUI\ComfyUI\comfy\clip_vision.py", line 1, in <module>
    from transformers import CLIPVisionModelWithProjection, CLIPVisionConfig, CLIPImageProcessor, modeling_utils
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\transformers\__init__.py", line 30, in <module>
    from . import dependency_versions_check
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\transformers\dependency_versions_check.py", line 36, in <module>
    from .utils import is_tokenizers_available
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\transformers\utils\__init__.py", line 34, in <module>
    from .generic import (
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\transformers\utils\generic.py", line 33, in <module>
    import tensorflow as tf
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\__init__.py", line 37, in <module>
    from tensorflow.python.tools import module_util as _module_util
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\python\__init__.py", line 37, in <module>
    from tensorflow.python.eager import context
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\python\eager\context.py", line 29, in <module>
    from tensorflow.core.framework import function_pb2
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\core\framework\function_pb2.py", line 16, in <module>
    from tensorflow.core.framework import attr_value_pb2 as tensorflow_dot_core_dot_framework_dot_attr__value__pb2
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\core\framework\attr_value_pb2.py", line 16, in <module>
    from tensorflow.core.framework import tensor_pb2 as tensorflow_dot_core_dot_framework_dot_tensor__pb2
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\core\framework\tensor_pb2.py", line 16, in <module>
    from tensorflow.core.framework import resource_handle_pb2 as tensorflow_dot_core_dot_framework_dot_resource__handle__pb2
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\core\framework\resource_handle_pb2.py", line 16, in <module>
    from tensorflow.core.framework import tensor_shape_pb2 as tensorflow_dot_core_dot_framework_dot_tensor__shape__pb2
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\tensorflow\core\framework\tensor_shape_pb2.py", line 36, in <module>
    _descriptor.FieldDescriptor(
  File "C:\AI\ComfyUI\python_embeded\lib\site-packages\google\protobuf\descriptor.py", line 561, in __new__
    _message.Message._CheckCalledFromGeneratedFile()
TypeError: Descriptors cannot not be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:
 1. Downgrade the protobuf package to 3.20.x or lower.
 2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).

More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates

C:\AI\ComfyUI>pause
Press any key to continue . . .

[Gourieff]

@alenknight

1. Downgrade the protobuf package to 3.20.x or lower.

So, try it, just change its version to 3.20.3 by python_embeded\python.exe -m pip install protobuf==3.20.3 (and don't forget to close ComfyUI before that)

[ruslawik]

I have the same error, but I can't just delete onnxruntime-gpu==1.16.0, because it is being used for other custom_nodes. By the way I have
onnx=1.14.0
onnxruntime=1.15.1
protobuf==3.20.3
Please, help