Cuda and CPU tensor issue not fixed

[ShamimShahriyar]

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?

Ensure both tensors are on the same device

            pasting_alpha = pasting_alpha.to(device)
            mask_i = mask[i].to(device)

            paste_mask = torch.min(pasting_alpha, mask_i).unsqueeze(2).repeat(1, 1, 4)

            pasting = pasting.to(device)
            paste_mask = paste_mask.to(device)

            result[image_index] = pasting * paste_mask + result[image_index] * (1. - paste_mask)

           # paste_mask = torch.min(pasting_alpha, mask[i]).unsqueeze(2).repeat(1, 1, 4)

          #  pasting = pasting.to(device) if pasting.device != device else pasting
          #  paste_mask = paste_mask.to(device) if paste_mask.device != device else paste_mask

          #  result[image_index] = pasting * paste_mask + result[image_index] * (1. - paste_mask)

            face_segment = result

I have it fixed this way.
was able to run on pytorch version: 2.10.0.dev20251016+cu128
But Dependency Issue rising in pytorch version: 2.10.0.dev20251016+cu130

Steps to reproduce the problem

image_swap_beta1 (1).json

Sysinfo

Total VRAM 4096 MB, total RAM 24413 MB
pytorch version: 2.10.0.dev20251016+cu128
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce GTX 1650 : native
Using pytorch attention
Python version: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 14 2025, 16:10:16) [MSC v.1929 64 bit (AMD64)]
ComfyUI version: 0.3.65
ComfyUI frontend version: 1.28.7

Relevant console log

FETCH ComfyRegistry Data: 15/100
Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
  File "D:\Conda\envs\comfy\Lib\asyncio\events.py", line 88, in _run
    self._context.run(self._callback, *self._args)
  File "D:\Conda\envs\comfy\Lib\asyncio\proactor_events.py", line 165, in _call_connection_lost
    self._sock.shutdown(socket.SHUT_RDWR)
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/app.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/api.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/imagePreview.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/utils.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/widgets.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/pnginfo.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/clipspace.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/popup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
FETCH ComfyRegistry Data: 20/100
got prompt
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
W0000 00:00:1760638608.489740    8364 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
W0000 00:00:1760638609.680303   22192 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
W0000 00:00:1760638610.994371   22744 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
W0000 00:00:1760638612.039759   24812 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
FETCH ComfyRegistry Data: 25/100
[ReActor] 23:46:52 - STATUS - Checking for any unsafe content...
[ReActor] 23:46:53 - STATUS - Ensuring NSFW detection model exists...
[ReActor] 23:46:54 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 23:46:54 - STATUS - Using Loaded Source Face Model...
[ReActor] 23:46:54 - STATUS - Analyzing Target Image...
2025-10-16 23:46:54.6406229 [E:onnxruntime:Default, provider_bridge_ort.cc:2251 onnxruntime::TryGetProviderInfo_CUDA] E:\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1844 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : Error loading "D:\Conda\envs\comfy\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" which depends on "cublasLt64_12.dll" which is missing. (Error 126: "The specified module could not be found.")

2025-10-16 23:46:55.7038003 [E:onnxruntime:Default, provider_bridge_ort.cc:2251 onnxruntime::TryGetProviderInfo_CUDA] E:\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1844 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : Error loading "D:\Conda\envs\comfy\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" which depends on "cublasLt64_12.dll" which is missing. (Error 126: "The specified module could not be found.")

2025-10-16 23:46:55.8188486 [E:onnxruntime:Default, provider_bridge_ort.cc:2251 onnxruntime::TryGetProviderInfo_CUDA] E:\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1844 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : Error loading "D:\Conda\envs\comfy\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" which depends on "cublasLt64_12.dll" which is missing. (Error 126: "The specified module could not be found.")

2025-10-16 23:46:55.9127471 [E:onnxruntime:Default, provider_bridge_ort.cc:2251 onnxruntime::TryGetProviderInfo_CUDA] E:\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1844 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : Error loading "D:\Conda\envs\comfy\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" which depends on "cublasLt64_12.dll" which is missing. (Error 126: "The specified module could not be found.")

2025-10-16 23:46:56.0885148 [E:onnxruntime:Default, provider_bridge_ort.cc:2251 onnxruntime::TryGetProviderInfo_CUDA] E:\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1844 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : Error loading "D:\Conda\envs\comfy\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" which depends on "cublasLt64_12.dll" which is missing. (Error 126: "The specified module could not be found.")

2025-10-16 23:46:57.8258860 [E:onnxruntime:Default, provider_bridge_ort.cc:2251 onnxruntime::TryGetProviderInfo_CUDA] E:\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1844 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : Error loading "D:\Conda\envs\comfy\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" which depends on "cublasLt64_12.dll" which is missing. (Error 126: "The specified module could not be found.")

FETCH ComfyRegistry Data: 30/100
[ReActor] 23:47:01 - STATUS - Swapping...
[ReActor] 23:47:01 - STATUS - Face Boost is enabled (inswapper/reswapper only)
[ReActor] 23:47:02 - STATUS - Boosting the Face with GPEN-BFR-512.onnx | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
2025-10-16 23:47:03.4891304 [E:onnxruntime:Default, provider_bridge_ort.cc:2251 onnxruntime::TryGetProviderInfo_CUDA] E:\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1844 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : Error loading "D:\Conda\envs\comfy\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" which depends on "cublasLt64_12.dll" which is missing. (Error 126: "The specified module could not be found.")

FETCH ComfyRegistry Data: 35/100
[ReActor] 23:47:06 - STATUS - --Done!--
!!! Exception during processing !!! Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
Traceback (most recent call last):
  File "D:\AI\ComfyUI\execution.py", line 496, in execute
    output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\AI\ComfyUI\execution.py", line 315, in get_output_data
    return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\AI\ComfyUI\execution.py", line 289, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "D:\AI\ComfyUI\execution.py", line 277, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^
  File "D:\AI\ComfyUI\custom_nodes\comfyui-reactor\nodes.py", line 1465, in execute
    paste_mask = torch.min(pasting_alpha, mask[i]).unsqueeze(2).repeat(1, 1, 4)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

Prompt executed in 19.20 seconds
FETCH ComfyRegistry Data: 40/100
FETCH ComfyRegistry Data: 45/100
FETCH ComfyRegistry Data: 50/100
FETCH ComfyRegistry Data: 55/100
FETCH ComfyRegistry Data: 60/100
FETCH ComfyRegistry Data: 65/100
FETCH ComfyRegistry Data: 70/100
FETCH ComfyRegistry Data: 75/100
FETCH ComfyRegistry Data: 80/100
FETCH ComfyRegistry Data: 85/100
FETCH ComfyRegistry Data: 90/100
FETCH ComfyRegistry Data: 95/100
FETCH ComfyRegistry Data: 100/100
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[ComfyUI-Manager] All startup tasks have been completed.

Restarting... [Legacy Mode]


Command: ['"D:\\Conda\\envs\\comfy\\python.exe"', '"main.py"']
(comfy) PS D:\AI\ComfyUI> [START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2025-10-16 23:53:26.024
** Platform: Windows
** Python version: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 14 2025, 16:10:16) [MSC v.1929 64 bit (AMD64)]
** Python executable: D:\Conda\envs\comfy\python.exe
** ComfyUI Path: D:\AI\ComfyUI
** ComfyUI Base Folder Path: D:\AI\ComfyUI
** User directory: D:\AI\ComfyUI\user
** ComfyUI-Manager config path: D:\AI\ComfyUI\user\default\ComfyUI-Manager\config.ini
** Log path: D:\AI\ComfyUI\user\comfyui.log

Prestartup times for custom nodes:
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\rgthree-comfy
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-easy-use
   5.2 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-manager

D:\Conda\envs\comfy\Lib\site-packages\torch\cuda\__init__.py:64: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
  import pynvml  # type: ignore[import]
Checkpoint files will always be loaded safely.
Total VRAM 4096 MB, total RAM 24413 MB
pytorch version: 2.10.0.dev20251016+cu128
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce GTX 1650 : native
Using pytorch attention
Python version: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 14 2025, 16:10:16) [MSC v.1929 64 bit (AMD64)]
ComfyUI version: 0.3.65
ComfyUI frontend version: 1.28.7
[Prompt Server] web root: D:\Conda\envs\comfy\Lib\site-packages\comfyui_frontend_package\static
[Crystools INFO] Crystools version: 1.27.3
[Crystools INFO] Platform release: 11
[Crystools INFO] JETSON: Not detected.
[Crystools INFO] CPU: Intel(R) Core(TM) i5-9300H CPU @ 2.40GHz - Arch: AMD64 - OS: Windows 11
[Crystools INFO] pynvml (NVIDIA) initialized.
[Crystools INFO] GPU/s:
[Crystools INFO] 0) NVIDIA GeForce GTX 1650
[Crystools INFO] NVIDIA Driver: 581.57
Module 'diffusers' load failed. If you don't have it installed, do it:
pip install diffusers
[ComfyUI-Easy-Use] server: v1.3.3 Loaded
[ComfyUI-Easy-Use] web root: D:\AI\ComfyUI\custom_nodes\comfyui-easy-use\web_version/v2 Loaded
ComfyUI-GGUF: Allowing full torch compile
[ComfyUI-HakuImg]-|23:53:41|-INFO: Check HakuImg requirements
[ComfyUI-HakuImg]-|23:53:41|-INFO: Check HakuImg requirements done
### Loading: ComfyUI-Impact-Pack (V8.22.2)
[Impact Pack] Wildcards loading done.
### Loading: ComfyUI-Inspire-Pack (V1.13.1)
### Loading: ComfyUI-Manager (V3.36)
[ComfyUI-Manager] network_mode: public
### ComfyUI Version: v0.3.65-13-gbc0ad9bb | Released on '2025-10-16'
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json

[ReActor] - STATUS - Running v0.6.2-b1 in ComfyUI
Torch version: 2.10.0.dev20251016+cu128
[D:\AI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: D:\AI\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts
[D:\AI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False
[D:\AI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success!

[rgthree-comfy] Loaded 48 exciting nodes. 🎉

WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `D:\AI\ComfyUI\custom_nodes\was-node-suite-comfyui\was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 220 nodes successfully.

        "Your work is going to fill a large part of your life, and the only way to be truly satisfied is to do what you believe is great work." - Steve Jobs


Import times for custom nodes:
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\websocket_image_save.py
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\masquerade-nodes-comfyui
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\sd-dynamic-thresholding
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\cg-use-everywhere
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-post-processing-nodes
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-PixelResolutionCalculator
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-inpaint-nodes
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-animatediff
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-custom-scripts
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfy-image-saver
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-GGUF
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-kjnodes
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI_essentials
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet
   0.1 seconds: D:\AI\ComfyUI\custom_nodes\rgthree-comfy
   0.1 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-jdcn
   0.1 seconds: D:\AI\ComfyUI\custom_nodes\efficiency-nodes-comfyui
   0.1 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-Inspire-Pack
   0.1 seconds: D:\AI\ComfyUI\custom_nodes\comfyui_controlnet_aux
   0.2 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite
   0.3 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
   0.3 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-Crystools
   0.5 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-tensorops
   0.7 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-manager
   0.9 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-easy-use
   1.4 seconds: D:\AI\ComfyUI\custom_nodes\a-person-mask-generator
   1.8 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-reactor
   2.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-HakuImg
   2.0 seconds: D:\AI\ComfyUI\custom_nodes\was-node-suite-comfyui

Context impl SQLiteImpl.
Will assume non-transactional DDL.
No target revision found.
Starting server

To see the GUI go to: http://127.0.0.1:8188
FETCH ComfyRegistry Data: 5/100
FETCH ComfyRegistry Data: 10/100
FETCH ComfyRegistry Data: 15/100
got prompt
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
W0000 00:00:1760639045.642173   10308 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
W0000 00:00:1760639046.726350    9356 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
W0000 00:00:1760639047.743565    4620 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
FETCH ComfyRegistry Data: 20/100
W0000 00:00:1760639048.717135    3364 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
[ReActor] 23:54:09 - STATUS - Checking for any unsafe content...
[ReActor] 23:54:09 - STATUS - Ensuring NSFW detection model exists...
[ReActor] 23:54:11 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 23:54:12 - STATUS - Using Loaded Source Face Model...
[ReActor] 23:54:12 - STATUS - Analyzing Target Image...
FETCH ComfyRegistry Data: 25/100
[ReActor] 23:54:18 - STATUS - Swapping...
[ReActor] 23:54:18 - STATUS - Face Boost is enabled (inswapper/reswapper only)
FETCH ComfyRegistry Data: 30/100
[ReActor] 23:54:21 - STATUS - Boosting the Face with GPEN-BFR-512.onnx | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
[ReActor] 23:54:26 - STATUS - --Done!--
FETCH ComfyRegistry Data: 35/100
!!! Exception during processing !!! Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
Traceback (most recent call last):
  File "D:\AI\ComfyUI\execution.py", line 496, in execute
    output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\AI\ComfyUI\execution.py", line 315, in get_output_data
    return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\AI\ComfyUI\execution.py", line 289, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "D:\AI\ComfyUI\execution.py", line 277, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^
  File "D:\AI\ComfyUI\custom_nodes\comfyui-reactor\nodes.py", line 1465, in execute
    paste_mask = torch.min(pasting_alpha, mask[i]).unsqueeze(2).repeat(1, 1, 4)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

Prompt executed in 22.00 seconds
FETCH ComfyRegistry Data: 40/100
FETCH ComfyRegistry Data: 45/100
FETCH ComfyRegistry Data: 50/100
FETCH ComfyRegistry Data: 55/100
FETCH ComfyRegistry Data: 60/100
FETCH ComfyRegistry Data: 65/100
FETCH ComfyRegistry Data: 70/100
FETCH ComfyRegistry Data: 75/100
FETCH ComfyRegistry Data: 80/100
FETCH ComfyRegistry Data: 85/100
FETCH ComfyRegistry Data: 90/100
FETCH ComfyRegistry Data: 95/100
FETCH ComfyRegistry Data: 100/100
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[ComfyUI-Manager] All startup tasks have been completed.
got prompt
!!! Exception during processing !!! Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
Traceback (most recent call last):
  File "D:\AI\ComfyUI\execution.py", line 496, in execute
    output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\AI\ComfyUI\execution.py", line 315, in get_output_data
    return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\AI\ComfyUI\execution.py", line 289, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "D:\AI\ComfyUI\execution.py", line 277, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^
  File "D:\AI\ComfyUI\custom_nodes\comfyui-reactor\nodes.py", line 1465, in execute
    # Ensure both tensors are on the same device
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

Prompt executed in 0.40 seconds

Restarting... [Legacy Mode]


Command: ['"D:\\Conda\\envs\\comfy\\python.exe"', '"main.py"']
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2025-10-17 00:01:57.298
** Platform: Windows
** Python version: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 14 2025, 16:10:16) [MSC v.1929 64 bit (AMD64)]
** Python executable: D:\Conda\envs\comfy\python.exe
** ComfyUI Path: D:\AI\ComfyUI
** ComfyUI Base Folder Path: D:\AI\ComfyUI
** User directory: D:\AI\ComfyUI\user
** ComfyUI-Manager config path: D:\AI\ComfyUI\user\default\ComfyUI-Manager\config.ini
** Log path: D:\AI\ComfyUI\user\comfyui.log

Prestartup times for custom nodes:
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\rgthree-comfy
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-easy-use
   4.4 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-manager

D:\Conda\envs\comfy\Lib\site-packages\torch\cuda\__init__.py:64: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
  import pynvml  # type: ignore[import]
Checkpoint files will always be loaded safely.
Total VRAM 4096 MB, total RAM 24413 MB
pytorch version: 2.10.0.dev20251016+cu128
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce GTX 1650 : native
Using pytorch attention
Python version: 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 14 2025, 16:10:16) [MSC v.1929 64 bit (AMD64)]
ComfyUI version: 0.3.65
ComfyUI frontend version: 1.28.7
[Prompt Server] web root: D:\Conda\envs\comfy\Lib\site-packages\comfyui_frontend_package\static
[Crystools INFO] Crystools version: 1.27.3
[Crystools INFO] Platform release: 11
[Crystools INFO] JETSON: Not detected.
[Crystools INFO] CPU: Intel(R) Core(TM) i5-9300H CPU @ 2.40GHz - Arch: AMD64 - OS: Windows 11
[Crystools INFO] pynvml (NVIDIA) initialized.
[Crystools INFO] GPU/s:
[Crystools INFO] 0) NVIDIA GeForce GTX 1650
[Crystools INFO] NVIDIA Driver: 581.57
Module 'diffusers' load failed. If you don't have it installed, do it:
pip install diffusers
[ComfyUI-Easy-Use] server: v1.3.3 Loaded
[ComfyUI-Easy-Use] web root: D:\AI\ComfyUI\custom_nodes\comfyui-easy-use\web_version/v2 Loaded
ComfyUI-GGUF: Allowing full torch compile
[ComfyUI-HakuImg]-|00:02:10|-INFO: Check HakuImg requirements
[ComfyUI-HakuImg]-|00:02:10|-INFO: Check HakuImg requirements done
### Loading: ComfyUI-Impact-Pack (V8.22.2)
[Impact Pack] Wildcards loading done.
### Loading: ComfyUI-Inspire-Pack (V1.13.1)
### Loading: ComfyUI-Manager (V3.36)
[ComfyUI-Manager] network_mode: public
### ComfyUI Version: v0.3.65-13-gbc0ad9bb | Released on '2025-10-16'
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json

[ReActor] - STATUS - Running v0.6.2-b1 in ComfyUI
Torch version: 2.10.0.dev20251016+cu128
[D:\AI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: D:\AI\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts
[D:\AI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False
[D:\AI\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success!

[rgthree-comfy] Loaded 48 extraordinary nodes. 🎉

WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `D:\AI\ComfyUI\custom_nodes\was-node-suite-comfyui\was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 220 nodes successfully.

        "Art is the bridge that connects imagination to reality." - Unknown


Import times for custom nodes:
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\websocket_image_save.py
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\masquerade-nodes-comfyui
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\sd-dynamic-thresholding
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\cg-use-everywhere
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-post-processing-nodes
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-PixelResolutionCalculator
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-inpaint-nodes
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfy-image-saver
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-animatediff
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-custom-scripts
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-GGUF
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-kjnodes
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-jdcn
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\rgthree-comfy
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI_essentials
   0.0 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet
   0.1 seconds: D:\AI\ComfyUI\custom_nodes\comfyui_controlnet_aux
   0.1 seconds: D:\AI\ComfyUI\custom_nodes\efficiency-nodes-comfyui
   0.1 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-Inspire-Pack
   0.2 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite
   0.2 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
   0.3 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-Crystools
   0.3 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-tensorops
   0.7 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-manager
   1.0 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-easy-use
   1.3 seconds: D:\AI\ComfyUI\custom_nodes\a-person-mask-generator
   1.8 seconds: D:\AI\ComfyUI\custom_nodes\was-node-suite-comfyui
   1.8 seconds: D:\AI\ComfyUI\custom_nodes\comfyui-reactor
   2.4 seconds: D:\AI\ComfyUI\custom_nodes\ComfyUI-HakuImg

Context impl SQLiteImpl.
Will assume non-transactional DDL.
No target revision found.
Starting server

To see the GUI go to: http://127.0.0.1:8188
FETCH ComfyRegistry Data: 5/100
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/app.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/api.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/imagePreview.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/widgets.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/utils.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/clipspace.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/pnginfo.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/popup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
FETCH ComfyRegistry Data: 10/100
got prompt
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
W0000 00:00:1760639547.430258   16320 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
W0000 00:00:1760639548.727385   16256 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
W0000 00:00:1760639549.689233    1588 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
FETCH ComfyRegistry Data: 15/100
W0000 00:00:1760639550.706479   26596 inference_feedback_manager.cc:114] Feedback manager requires a model with a single signature inference. Disabling support for feedback tensors.
[ReActor] 00:02:31 - STATUS - Checking for any unsafe content...
[ReActor] 00:02:32 - STATUS - Ensuring NSFW detection model exists...
[ReActor] 00:02:33 - STATUS - Working: source face index [0], target face index [0]
[ReActor] 00:02:33 - STATUS - Using Loaded Source Face Model...
[ReActor] 00:02:33 - STATUS - Analyzing Target Image...
FETCH ComfyRegistry Data: 20/100
[ReActor] 00:02:39 - STATUS - Swapping...
[ReActor] 00:02:39 - STATUS - Face Boost is enabled (inswapper/reswapper only)
[ReActor] 00:02:42 - STATUS - Boosting the Face with GPEN-BFR-512.onnx | Face Size is set to 512 with Scale Factor = 4.0 and 'Bilinear' interpolation
FETCH ComfyRegistry Data: 25/100
[ReActor] 00:02:47 - STATUS - --Done!--
Prompt executed in 21.35 seconds
FETCH ComfyRegistry Data: 30/100
FETCH ComfyRegistry Data: 35/100
FETCH ComfyRegistry Data: 40/100
FETCH ComfyRegistry Data: 45/100
FETCH ComfyRegistry Data: 50/100
FETCH ComfyRegistry Data: 55/100
FETCH ComfyRegistry Data: 60/100
FETCH ComfyRegistry Data: 65/100
FETCH ComfyRegistry Data: 70/100
FETCH ComfyRegistry Data: 75/100
FETCH ComfyRegistry Data: 80/100
FETCH ComfyRegistry Data: 85/100
FETCH ComfyRegistry Data: 90/100
FETCH ComfyRegistry Data: 95/100
FETCH ComfyRegistry Data: 100/100
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[ComfyUI-Manager] All startup tasks have been completed.

Additional information

Hope you find this helpful

[baesik]

Your onnxruntime-gpu needs to be compiled with CUDA 13. Prebuilt wheels are only available for cu11 and cu12 as of today. CUDA 13 support is in nightly and you'll need to build it yourself.

Refer to [CUDA] Fix cuda 13 build #26153 for build arguments.

git clone --recursive https://github.com/microsoft/onnxruntime
cd onnxruntime
git checkout cuda130_nightly
git reset --hard

I use uv for my venvs.
A deprecated pyreadline was listed as a dependency for my wheel for whatever reason; probably add pyreadline3 before everything else in requirements.txt.

pip install onnxruntime\build\cuda13\Release\Release\dist\*.whl

CUDA 13 requires >= 580 nVidia driver.