Comfy-Org / Comfy-Org/ComfyUI

The error message when running ComfyUI on Windows Server 2019 installed via KVM is as follows (translated into English):

Open
#5,834 4 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
133k
Forks
15.7k
Avg merge
1d 6h
Merged PRs (30d)
155

Description

# ComfyUI Error Report
## Error Details
- **Node ID:** 7
- **Node Type:** CLIPTextEncode
- **Exception Type:** RuntimeError
- **Exception Message:** CUDA error: operation not supported
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

## Stack Trace
```
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 198, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\nodes.py", line 65, in encode
output = clip.encode_from_tokens(tokens, return_pooled=True, return_dict=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd.py", line 132, in encode_from_tokens
self.load_model()

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd.py", line 164, in load_model
model_management.load_model_gpu(self.patcher)

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_management.py", line 559, in load_model_gpu
return load_models_gpu([model])
^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_management.py", line 545, in load_models_gpu
cur_loaded_model = loaded_model.model_load(lowvram_model_memory, force_patch_weights=force_patch_weights)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_management.py", line 327, in model_load
raise e

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_management.py", line 323, in model_load
self.real_model = self.model.patch_model(device_to=patch_model_to, lowvram_model_memory=lowvram_model_memory, load_weights=load_weights, force_patch_weights=force_patch_weights)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_patcher.py", line 470, in patch_model
self.load(device_to, lowvram_model_memory=lowvram_model_memory, force_patch_weights=force_patch_weights, full_load=full_load)

File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_patcher.py", line 442, in load
x[2].to(device_to)

File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1340, in to
return self._apply(convert)
^^^^^^^^^^^^^^^^^^^^

File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 900, in _apply
module._apply(fn)

File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 900, in _apply
module._apply(fn)

File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 900, in _apply
module._apply(fn)

[Previous line repeated 1 more time]

File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 927, in _apply
param_applied = fn(param)
^^^^^^^^^

File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1326, in convert
return t.to(
^^^^^

```
## System Information
- **ComfyUI Version:** unknown
- **Arguments:** C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\main.py --user-directory E:\comfyui\ComfyUI\user --input-directory E:\comfyui\ComfyUI\input --output-directory E:\comfyui\ComfyUI\output --front-end-root C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\web_custom_versions\desktop_app --extra-model-paths-config C:\Users\Administrator\AppData\Roaming\ComfyUI\extra_models_config.yaml --port 8000
- **OS:** nt
- **Python Version:** 3.12.4 (main, Jul 25 2024, 21:57:00) [MSC v.1929 64 bit (AMD64)]
- **Embedded Python:** false
- **PyTorch Version:** 2.5.1+cu121
## Devices

- **Name:** cuda:0 NVIDIA H800 : cudaMallocAsync
- **Type:** cuda
- **VRAM Total:** 85418967040
- **VRAM Free:** 84875411456
- **Torch VRAM Total:** 0
- **Torch VRAM Free:** 0

## Logs
```
2024-11-28T23:30:32.365425 - [START] Security scan2024-11-28T23:30:32.365425 -
2024-11-28T23:30:42.691217 - [DONE] Security scan2024-11-28T23:30:42.691217 -
2024-11-28T23:30:42.909846 - Failed to execute startup-script: C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\custom_nodes\ComfyUI-Manager\prestartup_script.py / Failed to initialize: Bad git executable.
The git executable must be specified in one of the following ways:
- be included in your $PATH
- be set via $GIT_PYTHON_GIT_EXECUTABLE
- explicitly set via git.refresh()

All git commands will error until this is rectified.

This initial message can be silenced or aggravated in the future by setting the
$GIT_PYTHON_REFRESH environment variable. Use one of the following values:
- quiet|q|silence|s|silent|none|n|0: for no message or exception
- warn|w|warning|log|l|1: for a warning message (logging level CRITICAL, displayed by default)
- error|e|exception|raise|r|2: for a raised exception

Example:
export GIT_PYTHON_REFRESH=quiet
2024-11-28T23:30:42.925592 -
2024-11-28T23:30:42.925592 -
Prestartup times for custom nodes:2024-11-28T23:30:42.925592 -
2024-11-28T23:30:42.925592 - 10.7 seconds (PRESTARTUP FAILED):2024-11-28T23:30:42.925592 - 2024-11-28T23:30:42.925592 - C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\custom_nodes\ComfyUI-Manager2024-11-28T23:30:42.925592 -
2024-11-28T23:30:42.925592 -
2024-11-28T23:31:07.862653 - Total VRAM 81462 MB, total RAM 127999 MB
2024-11-28T23:31:07.862653 - pytorch version: 2.5.1+cu121
2024-11-28T23:31:07.862653 - Set vram state to: NORMAL_VRAM
2024-11-28T23:31:07.862653 - Device: cuda:0 NVIDIA H800 : cudaMallocAsync
2024-11-28T23:31:11.343111 - Using pytorch cross attention
2024-11-28T23:31:21.213445 - [Prompt Server] web root: C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\web_custom_versions\desktop_app
2024-11-28T23:31:21.229812 - Adding extra search path checkpoints E:\comfyui\ComfyUI\models\checkpoints\
2024-11-28T23:31:21.229812 - Adding extra search path classifiers E:\comfyui\ComfyUI\models\classifiers\
2024-11-28T23:31:21.229812 - Adding extra search path clip E:\comfyui\ComfyUI\models\clip\
2024-11-28T23:31:21.229812 - Adding extra search path clip_vision E:\comfyui\ComfyUI\models\clip_vision\
2024-11-28T23:31:21.229812 - Adding extra search path configs E:\comfyui\ComfyUI\models\configs\
2024-11-28T23:31:21.229812 - Adding extra search path controlnet E:\comfyui\ComfyUI\models\controlnet\
2024-11-28T23:31:21.230909 - Adding extra search path diffusers E:\comfyui\ComfyUI\models\diffusers\
2024-11-28T23:31:21.230909 - Adding extra search path diffusion_models E:\comfyui\ComfyUI\models\diffusion_models\
2024-11-28T23:31:21.230909 - Adding extra search path embeddings E:\comfyui\ComfyUI\models\embeddings\
2024-11-28T23:31:21.230909 - Adding extra search path gligen E:\comfyui\ComfyUI\models\gligen\
2024-11-28T23:31:21.230909 - Adding extra search path hypernetworks E:\comfyui\ComfyUI\models\hypernetworks\
2024-11-28T23:31:21.231537 - Adding extra search path loras E:\comfyui\ComfyUI\models\loras\
2024-11-28T23:31:21.231537 - Adding extra search path photomaker E:\comfyui\ComfyUI\models\photomaker\
2024-11-28T23:31:21.231537 - Adding extra search path style_models E:\comfyui\ComfyUI\models\style_models\
2024-11-28T23:31:21.231537 - Adding extra search path unet E:\comfyui\ComfyUI\models\unet\
2024-11-28T23:31:21.231537 - Adding extra search path upscale_models E:\comfyui\ComfyUI\models\upscale_models\
2024-11-28T23:31:21.231537 - Adding extra search path vae E:\comfyui\ComfyUI\models\vae\
2024-11-28T23:31:21.231537 - Adding extra search path vae_approx E:\comfyui\ComfyUI\models\vae_approx\
2024-11-28T23:31:21.231537 - Adding extra search path animatediff_models E:\comfyui\ComfyUI\models\animatediff_models\
2024-11-28T23:31:21.231537 - Adding extra search path animatediff_motion_lora E:\comfyui\ComfyUI\models\animatediff_motion_lora\
2024-11-28T23:31:21.231537 - Adding extra search path animatediff_video_formats E:\comfyui\ComfyUI\models\animatediff_video_formats\
2024-11-28T23:31:21.232619 - Adding extra search path ipadapter E:\comfyui\ComfyUI\models\ipadapter\
2024-11-28T23:31:21.232619 - Adding extra search path liveportrait E:\comfyui\ComfyUI\models\liveportrait\
2024-11-28T23:31:21.232619 - Adding extra search path insightface E:\comfyui\ComfyUI\models\insightface\
2024-11-28T23:31:21.232619 - Adding extra search path layerstyle E:\comfyui\ComfyUI\models\layerstyle\
2024-11-28T23:31:21.232619 - Adding extra search path LLM E:\comfyui\ComfyUI\models\LLM\
2024-11-28T23:31:21.232619 - Adding extra search path Joy_caption E:\comfyui\ComfyUI\models\Joy_caption\
2024-11-28T23:31:21.232619 - Adding extra search path sams E:\comfyui\ComfyUI\models\sams\
2024-11-28T23:31:21.232619 - Adding extra search path blip E:\comfyui\ComfyUI\models\blip\
2024-11-28T23:31:21.232619 - Adding extra search path CogVideo E:\comfyui\ComfyUI\models\CogVideo\
2024-11-28T23:31:21.233725 - Adding extra search path xlabs E:\comfyui\ComfyUI\models\xlabs\
2024-11-28T23:31:21.233725 - Adding extra search path instantid E:\comfyui\ComfyUI\models\instantid\
2024-11-28T23:31:21.233725 - Adding extra search path custom_nodes E:\comfyui\ComfyUI\custom_nodes/
2024-11-28T23:31:23.544452 - Traceback (most recent call last):
File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\git\__init__.py", line 296, in
refresh()
File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\git\__init__.py", line 287, in refresh
if not Git.refresh(path=path):
^^^^^^^^^^^^^^^^^^^^^^
File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\git\cmd.py", line 631, in refresh
raise ImportError(err)
ImportError: Bad git executable.
The git executable must be specified in one of the following ways:
- be included in your $PATH
- be set via $GIT_PYTHON_GIT_EXECUTABLE
- explicitly set via git.refresh()

All git commands will error until this is rectified.

This initial message can be silenced or aggravated in the future by setting the
$GIT_PYTHON_REFRESH environment variable. Use one of the following values:
- quiet|q|silence|s|silent|none|n|0: for no message or exception
- warn|w|warning|log|l|1: for a warning message (logging level CRITICAL, displayed by default)
- error|e|exception|raise|r|2: for a raised exception

Example:
export GIT_PYTHON_REFRESH=quiet

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

Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\nodes.py", line 2026, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 995, in exec_module
File "", line 488, in _call_with_frames_removed
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\custom_nodes\ComfyUI-Manager\__init__.py", line 6, in
from .glob import manager_server
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\custom_nodes\ComfyUI-Manager\glob\manager_server.py", line 13, in
import git
File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\git\__init__.py", line 298, in
raise ImportError("Failed to initialize: {0}".format(_exc)) from _exc
ImportError: Failed to initialize: Bad git executable.
The git executable must be specified in one of the following ways:
- be included in your $PATH
- be set via $GIT_PYTHON_GIT_EXECUTABLE
- explicitly set via git.refresh()

All git commands will error until this is rectified.

This initial message can be silenced or aggravated in the future by setting the
$GIT_PYTHON_REFRESH environment variable. Use one of the following values:
- quiet|q|silence|s|silent|none|n|0: for no message or exception
- warn|w|warning|log|l|1: for a warning message (logging level CRITICAL, displayed by default)
- error|e|exception|raise|r|2: for a raised exception

Example:
export GIT_PYTHON_REFRESH=quiet

2024-11-28T23:31:23.544452 - Cannot import C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\custom_nodes\ComfyUI-Manager module for custom nodes: Failed to initialize: Bad git executable.
The git executable must be specified in one of the following ways:
- be included in your $PATH
- be set via $GIT_PYTHON_GIT_EXECUTABLE
- explicitly set via git.refresh()

All git commands will error until this is rectified.

This initial message can be silenced or aggravated in the future by setting the
$GIT_PYTHON_REFRESH environment variable. Use one of the following values:
- quiet|q|silence|s|silent|none|n|0: for no message or exception
- warn|w|warning|log|l|1: for a warning message (logging level CRITICAL, displayed by default)
- error|e|exception|raise|r|2: for a raised exception

Example:
export GIT_PYTHON_REFRESH=quiet

2024-11-28T23:31:23.544452 -
Import times for custom nodes:
2024-11-28T23:31:23.544452 - 0.0 seconds: C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\custom_nodes\websocket_image_save.py
2024-11-28T23:31:23.544452 - 0.2 seconds (IMPORT FAILED): C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\custom_nodes\ComfyUI-Manager
2024-11-28T23:31:23.544452 -
2024-11-28T23:31:23.567125 - Setting output directory to: E:\comfyui\ComfyUI\output
2024-11-28T23:31:23.567741 - Setting input directory to: E:\comfyui\ComfyUI\input
2024-11-28T23:31:23.567741 - Setting user directory to: E:\comfyui\ComfyUI\user
2024-11-28T23:31:23.571686 - Starting server

2024-11-28T23:31:23.572775 - To see the GUI go to: http://127.0.0.1:8000
2024-11-28T23:32:18.516615 - Failed to get ComfyUI version: [WinError 2] The system cannot find the file specified
2024-11-28T23:33:50.940124 - got prompt
2024-11-28T23:33:51.370432 - model weight dtype torch.float16, manual cast: None
2024-11-28T23:33:51.404333 - model_type EPS
2024-11-28T23:33:54.314565 - Using pytorch attention in VAE
2024-11-28T23:33:54.317633 - Using pytorch attention in VAE
2024-11-28T23:33:55.646876 - Requested to load SD1ClipModel
2024-11-28T23:33:55.646876 - Loading 1 new model
2024-11-28T23:33:55.692539 - !!! Exception during processing !!! CUDA error: operation not supported
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

2024-11-28T23:33:55.855981 - Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 198, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\nodes.py", line 65, in encode
output = clip.encode_from_tokens(tokens, return_pooled=True, return_dict=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd.py", line 132, in encode_from_tokens
self.load_model()
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd.py", line 164, in load_model
model_management.load_model_gpu(self.patcher)
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_management.py", line 559, in load_model_gpu
return load_models_gpu([model])
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_management.py", line 545, in load_models_gpu
cur_loaded_model = loaded_model.model_load(lowvram_model_memory, force_patch_weights=force_patch_weights)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_management.py", line 327, in model_load
raise e
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_management.py", line 323, in model_load
self.real_model = self.model.patch_model(device_to=patch_model_to, lowvram_model_memory=lowvram_model_memory, load_weights=load_weights, force_patch_weights=force_patch_weights)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_patcher.py", line 470, in patch_model
self.load(device_to, lowvram_model_memory=lowvram_model_memory, force_patch_weights=force_patch_weights, full_load=full_load)
File "C:\Users\Administrator\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\model_patcher.py", line 442, in load
x[2].to(device_to)
File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1340, in to
return self._apply(convert)
^^^^^^^^^^^^^^^^^^^^
File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 900, in _apply
module._apply(fn)
File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 900, in _apply
module._apply(fn)
File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 900, in _apply
module._apply(fn)
[Previous line repeated 1 more time]
File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 927, in _apply
param_applied = fn(param)
^^^^^^^^^
File "E:\comfyui\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1326, in convert
return t.to(
^^^^^
RuntimeError: CUDA error: operation not supported
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

2024-11-28T23:33:55.861968 - Prompt executed in 4.92 seconds
2024-11-28T23:33:56.145045 - Failed to get ComfyUI version: [WinError 2] The system cannot find the file specified

```
## Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.
```
{"last_node_id":9,"last_link_id":9,"nodes":[{"id":8,"type":"VAEDecode","pos":[1209,188],"size":[210,46],"flags":{},"order":5,"mode":0,"inputs":[{"name":"samples","type":"LATENT","link":7},{"name":"vae","type":"VAE","link":8}],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[9],"slot_index":0}],"properties":{"Node name for S&R":"VAEDecode"},"widgets_values":[]},{"id":9,"type":"SaveImage","pos":[1451,189],"size":[210,58],"flags":{},"order":6,"mode":0,"inputs":[{"name":"images","type":"IMAGE","link":9}],"outputs":[],"properties":{},"widgets_values":["ComfyUI"]},{"id":4,"type":"CheckpointLoaderSimple","pos":[-455.6889343261719,405.187255859375],"size":[315,98],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[{"name":"MODEL","type":"MODEL","links":[1],"slot_index":0},{"name":"CLIP","type":"CLIP","links":[3,5],"slot_index":1},{"name":"VAE","type":"VAE","links":[8],"slot_index":2}],"properties":{"Node name for S&R":"CheckpointLoaderSimple"},"widgets_values":["majicMIX realistic 麦橘写实_v7.safetensors"]},{"id":6,"type":"CLIPTextEncode","pos":[473.5639343261719,48.374603271484375],"size":[422.84503173828125,164.31304931640625],"flags":{},"order":2,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":3}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[4],"slot_index":0}],"properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":["beautiful scenery nature glass bottle landscape, , purple galaxy bottle,"]},{"id":3,"type":"KSampler","pos":[851.2872924804688,348.51507568359375],"size":[315,262],"flags":{},"order":4,"mode":0,"inputs":[{"name":"model","type":"MODEL","link":1},{"name":"positive","type":"CONDITIONING","link":4},{"name":"negative","type":"CONDITIONING","link":6},{"name":"latent_image","type":"LATENT","link":2}],"outputs":[{"name":"LATENT","type":"LATENT","links":[7],"slot_index":0}],"properties":{"Node name for S&R":"KSampler"},"widgets_values":[876012582798970,"randomize",20,8,"euler","normal",1]},{"id":7,"type":"CLIPTextEncode","pos":[396.8948974609375,331.900146484375],"size":[425.27801513671875,180.6060791015625],"flags":{},"order":3,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":5}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[6],"slot_index":0}],"properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":["text, watermark"]},{"id":5,"type":"EmptyLatentImage","pos":[281.2029113769531,682.205078125],"size":[315,106],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"name":"LATENT","type":"LATENT","links":[2],"slot_index":0}],"properties":{"Node name for S&R":"EmptyLatentImage"},"widgets_values":[512,512,1]}],"links":[[1,4,0,3,0,"MODEL"],[2,5,0,3,3,"LATENT"],[3,4,1,6,0,"CLIP"],[4,6,0,3,1,"CONDITIONING"],[5,4,1,7,0,"CLIP"],[6,7,0,3,2,"CONDITIONING"],[7,3,0,8,0,"LATENT"],[8,4,2,8,1,"VAE"],[9,8,0,9,0,"IMAGE"]],"groups":[],"config":{},"extra":{"ds":{"scale":0.6830134553650726,"offset":[940.2843069445624,361.22956643896987]}},"version":0.4}
```

## Additional Context
(Please add any additional context or steps to reproduce the error here)

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.