# ComfyUI Error Report
## Error Details
- **Node ID:** 4
- **Node Type:** CheckpointLoaderSimple
- **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 "D:\ComfyUI-0.3.65\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:\ComfyUI-0.3.65\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:\ComfyUI-0.3.65\execution.py", line 289, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "D:\ComfyUI-0.3.65\execution.py", line 277, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\nodes.py", line 578, in load_checkpoint
out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd.py", line 1179, in load_checkpoint_guess_config
out = load_state_dict_guess_config(sd, output_vae, output_clip, output_clipvision, embedding_directory, output_model, model_options, te_model_options=te_model_options, metadata=metadata)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd.py", line 1238, in load_state_dict_guess_config
clip = CLIP(clip_target, embedding_directory=embedding_directory, tokenizer_data=clip_sd, parameters=parameters, model_options=te_model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd.py", line 114, in __init__
self.cond_stage_model = clip(**(params))
^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sdxl_clip.py", line 44, in __init__
self.clip_l = sd1_clip.SDClipModel(layer="hidden", layer_idx=-2, device=device, dtype=dtype, layer_norm_hidden_state=False, model_options=model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd1_clip.py", line 121, in __init__
self.transformer = model_class(config, dtype, device, self.operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\clip_model.py", line 143, in __init__
self.text_model = CLIPTextModel_(config_dict, dtype, device, operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\clip_model.py", line 106, in __init__
self.embeddings = CLIPEmbeddings(embed_dim, num_positions=num_positions, dtype=dtype, device=device, operations=operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\clip_model.py", line 88, in __init__
self.token_embedding = operations.Embedding(vocab_size, embed_dim, dtype=dtype, device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\sparse.py", line 167, in __init__
torch.empty((num_embeddings, embedding_dim), **factory_kwargs),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
```
## System Information
- **ComfyUI Version:** 0.3.65
- **Arguments:** main.py
- **OS:** nt
- **Python Version:** 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]
- **Embedded Python:** false
- **PyTorch Version:** 2.7.1+cu118
## Devices
- **Name:** cuda:0 Tesla V100-SXM2-32GB : cudaMallocAsync
- **Type:** cuda
- **VRAM Total:** 34228338688
- **VRAM Free:** 33908523008
- **Torch VRAM Total:** 0
- **Torch VRAM Free:** 0
## Logs
```
2025-11-01T21:11:18.229501 - [START] Security scan2025-11-01T21:11:18.229501 -
2025-11-01T21:11:18.925295 - [DONE] Security scan2025-11-01T21:11:18.925295 -
2025-11-01T21:11:19.008789 - ## ComfyUI-Manager: installing dependencies done.2025-11-01T21:11:19.008789 -
2025-11-01T21:11:19.008789 - ** ComfyUI startup time:2025-11-01T21:11:19.008789 - 2025-11-01T21:11:19.008789 - 2025-11-01 21:11:19.0082025-11-01T21:11:19.008789 -
2025-11-01T21:11:19.008789 - ** Platform:2025-11-01T21:11:19.008789 - 2025-11-01T21:11:19.008789 - Windows2025-11-01T21:11:19.008789 -
2025-11-01T21:11:19.008789 - ** Python version:2025-11-01T21:11:19.008789 - 2025-11-01T21:11:19.008789 - 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]2025-11-01T21:11:19.008789 -
2025-11-01T21:11:19.008789 - ** Python executable:2025-11-01T21:11:19.008789 - 2025-11-01T21:11:19.008789 - C:\Users\Administrator\AppData\Local\Programs\Python\Python312\python.exe2025-11-01T21:11:19.008789 -
2025-11-01T21:11:19.008789 - ** ComfyUI Path:2025-11-01T21:11:19.008789 - 2025-11-01T21:11:19.008789 - D:\ComfyUI-0.3.652025-11-01T21:11:19.008789 -
2025-11-01T21:11:19.008789 - ** ComfyUI Base Folder Path:2025-11-01T21:11:19.008789 - 2025-11-01T21:11:19.008789 - D:\ComfyUI-0.3.652025-11-01T21:11:19.008789 -
2025-11-01T21:11:19.008789 - ** User directory:2025-11-01T21:11:19.008789 - 2025-11-01T21:11:19.008789 - D:\ComfyUI-0.3.65\user2025-11-01T21:11:19.008789 -
2025-11-01T21:11:19.008789 - ** ComfyUI-Manager config path:2025-11-01T21:11:19.008789 - 2025-11-01T21:11:19.012639 - D:\ComfyUI-0.3.65\user\default\ComfyUI-Manager\config.ini2025-11-01T21:11:19.012639 -
2025-11-01T21:11:19.012639 - ** Log path:2025-11-01T21:11:19.012639 - 2025-11-01T21:11:19.012639 - D:\ComfyUI-0.3.65\user\comfyui.log2025-11-01T21:11:19.012639 -
2025-11-01T21:11:19.729202 -
Prestartup times for custom nodes:
2025-11-01T21:11:19.729202 - 1.7 seconds: D:\ComfyUI-0.3.65\custom_nodes\ComfyUI-Manager
2025-11-01T21:11:19.729202 -
2025-11-01T21:11:20.893467 - Checkpoint files will always be loaded safely.
2025-11-01T21:11:20.990596 - Total VRAM 32643 MB, total RAM 65228 MB
2025-11-01T21:11:20.990596 - pytorch version: 2.7.1+cu118
2025-11-01T21:11:20.990596 - Set vram state to: NORMAL_VRAM
2025-11-01T21:11:20.990596 - Device: cuda:0 Tesla V100-SXM2-32GB : cudaMallocAsync
2025-11-01T21:11:21.929278 - Using pytorch attention
2025-11-01T21:11:23.235378 - Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]
2025-11-01T21:11:23.235378 - ComfyUI version: 0.3.65
2025-11-01T21:11:23.262790 - ComfyUI frontend version: 1.27.10
2025-11-01T21:11:23.262790 - [Prompt Server] web root: C:\Users\Administrator\AppData\Local\Programs\Python\Python312\Lib\site-packages\comfyui_frontend_package\static
2025-11-01T21:11:23.958028 - ### Loading: ComfyUI-Manager (V3.37)
2025-11-01T21:11:23.960378 - [ComfyUI-Manager] network_mode: public
2025-11-01T21:11:23.960490 - ### ComfyUI Revision: UNKNOWN (The currently installed ComfyUI is not a Git repository)
2025-11-01T21:11:24.350599 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
2025-11-01T21:11:24.396496 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
2025-11-01T21:11:24.981361 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
2025-11-01T21:11:25.272319 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
2025-11-01T21:11:26.283930 - [0;33m[ReActor][0m - [38;5;173mSTATUS[0m - [0;32mRunning v0.6.1-b2 in ComfyUI[0m2025-11-01T21:11:26.283930 -
2025-11-01T21:11:26.283930 - [ReActor] 21:11:26 - [0;33mWARNING[0m - --- ReActor LOGGING FORCED TO DEBUG LEVEL ---
2025-11-01T21:11:26.283930 - [ReActor] 21:11:26 - [0;36mDEBUG[0m - --- ТЕСТОВОЕ DEBUG СООБЩЕНИЕ ---
2025-11-01T21:11:26.349421 - Torch version: 2.7.1+cu1182025-11-01T21:11:26.349421 -
2025-11-01T21:11:26.399414 - [36;20m[D:\ComfyUI-0_x_3_x_65\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: D:\ComfyUI-0.3.65\custom_nodes\comfyui_controlnet_aux\ckpts[0m
2025-11-01T21:11:26.399414 - [36;20m[D:\ComfyUI-0_x_3_x_65\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False[0m
2025-11-01T21:11:26.399414 - [36;20m[D:\ComfyUI-0_x_3_x_65\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider'][0m
2025-11-01T21:11:26.584532 - DWPose: Onnxruntime with acceleration providers detected2025-11-01T21:11:26.584532 -
2025-11-01T21:11:26.594954 -
Import times for custom nodes:
2025-11-01T21:11:26.594954 - 0.0 seconds: D:\ComfyUI-0.3.65\custom_nodes\websocket_image_save.py
2025-11-01T21:11:26.594954 - 0.0 seconds: D:\ComfyUI-0.3.65\custom_nodes\AIGODLIKE-ComfyUI-Translation
2025-11-01T21:11:26.594954 - 0.0 seconds: D:\ComfyUI-0.3.65\custom_nodes\ComfyUI-Manager
2025-11-01T21:11:26.594954 - 0.2 seconds: D:\ComfyUI-0.3.65\custom_nodes\comfyui_controlnet_aux
2025-11-01T21:11:26.594954 - 2.4 seconds: D:\ComfyUI-0.3.65\custom_nodes\comfyui-reactor-node
2025-11-01T21:11:26.594954 -
2025-11-01T21:11:26.906982 - Context impl SQLiteImpl.
2025-11-01T21:11:26.906982 - Will assume non-transactional DDL.
2025-11-01T21:11:26.911927 - No target revision found.
2025-11-01T21:11:26.921987 - Starting server
2025-11-01T21:11:26.921987 - To see the GUI go to: http://127.0.0.1:8188
2025-11-01T21:11:29.337859 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
2025-11-01T21:11:35.696151 - FETCH ComfyRegistry Data: 5/1032025-11-01T21:11:35.696151 -
2025-11-01T21:11:42.227906 - FETCH ComfyRegistry Data: 10/1032025-11-01T21:11:42.227906 -
2025-11-01T21:11:48.693513 - FETCH ComfyRegistry Data: 15/1032025-11-01T21:11:48.693513 -
2025-11-01T21:11:53.128871 - got prompt
2025-11-01T21:11:53.429941 - model weight dtype torch.float16, manual cast: None
2025-11-01T21:11:53.431933 - model_type EPS
2025-11-01T21:11:54.480381 - Using pytorch attention in VAE
2025-11-01T21:11:54.482383 - Using pytorch attention in VAE
2025-11-01T21:11:54.575104 - VAE load device: cuda:0, offload device: cpu, dtype: torch.float32
2025-11-01T21:11:54.586094 - !!! 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.
2025-11-01T21:11:54.592018 - Traceback (most recent call last):
File "D:\ComfyUI-0.3.65\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:\ComfyUI-0.3.65\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:\ComfyUI-0.3.65\execution.py", line 289, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "D:\ComfyUI-0.3.65\execution.py", line 277, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\nodes.py", line 578, in load_checkpoint
out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd.py", line 1179, in load_checkpoint_guess_config
out = load_state_dict_guess_config(sd, output_vae, output_clip, output_clipvision, embedding_directory, output_model, model_options, te_model_options=te_model_options, metadata=metadata)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd.py", line 1238, in load_state_dict_guess_config
clip = CLIP(clip_target, embedding_directory=embedding_directory, tokenizer_data=clip_sd, parameters=parameters, model_options=te_model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd.py", line 114, in __init__
self.cond_stage_model = clip(**(params))
^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sdxl_clip.py", line 44, in __init__
self.clip_l = sd1_clip.SDClipModel(layer="hidden", layer_idx=-2, device=device, dtype=dtype, layer_norm_hidden_state=False, model_options=model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd1_clip.py", line 121, in __init__
self.transformer = model_class(config, dtype, device, self.operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\clip_model.py", line 143, in __init__
self.text_model = CLIPTextModel_(config_dict, dtype, device, operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\clip_model.py", line 106, in __init__
self.embeddings = CLIPEmbeddings(embed_dim, num_positions=num_positions, dtype=dtype, device=device, operations=operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\clip_model.py", line 88, in __init__
self.token_embedding = operations.Embedding(vocab_size, embed_dim, dtype=dtype, device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\sparse.py", line 167, in __init__
torch.empty((num_embeddings, embedding_dim), **factory_kwargs),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
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.
2025-11-01T21:11:54.595017 - Prompt executed in 1.46 seconds
2025-11-01T21:11:56.911730 - FETCH ComfyRegistry Data: 20/1032025-11-01T21:11:56.912732 -
2025-11-01T21:11:57.569748 - got prompt
2025-11-01T21:11:57.870037 - model weight dtype torch.float16, manual cast: None
2025-11-01T21:11:57.871031 - model_type EPS
2025-11-01T21:11:58.888953 - Using pytorch attention in VAE
2025-11-01T21:11:58.891530 - Using pytorch attention in VAE
2025-11-01T21:11:58.970292 - VAE load device: cuda:0, offload device: cpu, dtype: torch.float32
2025-11-01T21:11:58.979750 - !!! 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.
2025-11-01T21:11:58.980743 - Traceback (most recent call last):
File "D:\ComfyUI-0.3.65\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:\ComfyUI-0.3.65\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:\ComfyUI-0.3.65\execution.py", line 289, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "D:\ComfyUI-0.3.65\execution.py", line 277, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\nodes.py", line 578, in load_checkpoint
out = comfy.sd.load_checkpoint_guess_config(ckpt_path, output_vae=True, output_clip=True, embedding_directory=folder_paths.get_folder_paths("embeddings"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd.py", line 1179, in load_checkpoint_guess_config
out = load_state_dict_guess_config(sd, output_vae, output_clip, output_clipvision, embedding_directory, output_model, model_options, te_model_options=te_model_options, metadata=metadata)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd.py", line 1238, in load_state_dict_guess_config
clip = CLIP(clip_target, embedding_directory=embedding_directory, tokenizer_data=clip_sd, parameters=parameters, model_options=te_model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd.py", line 114, in __init__
self.cond_stage_model = clip(**(params))
^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sdxl_clip.py", line 44, in __init__
self.clip_l = sd1_clip.SDClipModel(layer="hidden", layer_idx=-2, device=device, dtype=dtype, layer_norm_hidden_state=False, model_options=model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\sd1_clip.py", line 121, in __init__
self.transformer = model_class(config, dtype, device, self.operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\clip_model.py", line 143, in __init__
self.text_model = CLIPTextModel_(config_dict, dtype, device, operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\clip_model.py", line 106, in __init__
self.embeddings = CLIPEmbeddings(embed_dim, num_positions=num_positions, dtype=dtype, device=device, operations=operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-0.3.65\comfy\clip_model.py", line 88, in __init__
self.token_embedding = operations.Embedding(vocab_size, embed_dim, dtype=dtype, device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\sparse.py", line 167, in __init__
torch.empty((num_embeddings, embedding_dim), **factory_kwargs),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
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.
2025-11-01T21:11:58.983743 - Prompt executed in 1.41 seconds
```
## Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.
```
{"id":"74ccbdc4-be7b-4ff2-b981-8094cc07e6c0","revision":0,"last_node_id":9,"last_link_id":9,"nodes":[{"id":7,"type":"CLIPTextEncode","pos":[413,389],"size":[425.27801513671875,180.6060791015625],"flags":{},"order":3,"mode":0,"inputs":[{"label":"CLIP","localized_name":"clip","name":"clip","type":"CLIP","link":5},{"localized_name":"文本","name":"text","type":"STRING","widget":{"name":"text"},"link":null}],"outputs":[{"label":"条件","localized_name":"条件","name":"CONDITIONING","type":"CONDITIONING","slot_index":0,"links":[6]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.65","Node name for S&R":"CLIPTextEncode"},"widgets_values":["text, watermark"]},{"id":6,"type":"CLIPTextEncode","pos":[415,186],"size":[422.84503173828125,164.31304931640625],"flags":{},"order":2,"mode":0,"inputs":[{"label":"CLIP","localized_name":"clip","name":"clip","type":"CLIP","link":3},{"localized_name":"文本","name":"text","type":"STRING","widget":{"name":"text"},"link":null}],"outputs":[{"label":"条件","localized_name":"条件","name":"CONDITIONING","type":"CONDITIONING","slot_index":0,"links":[4]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.65","Node name for S&R":"CLIPTextEncode"},"widgets_values":["beautiful scenery nature glass bottle landscape, , purple galaxy bottle,"]},{"id":5,"type":"EmptyLatentImage","pos":[473,609],"size":[315,106],"flags":{},"order":0,"mode":0,"inputs":[{"localized_name":"宽度","name":"width","type":"INT","widget":{"name":"width"},"link":null},{"localized_name":"高度","name":"height","type":"INT","widget":{"name":"height"},"link":null},{"localized_name":"批次大小","name":"batch_size","type":"INT","widget":{"name":"batch_size"},"link":null}],"outputs":[{"label":"Latent","localized_name":"Latent","name":"LATENT","type":"LATENT","slot_index":0,"links":[2]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.65","Node name for S&R":"EmptyLatentImage"},"widgets_values":[512,512,1]},{"id":3,"type":"KSampler","pos":[863,186],"size":[315,262],"flags":{},"order":4,"mode":0,"inputs":[{"label":"模型","localized_name":"模型","name":"model","type":"MODEL","link":1},{"label":"正面条件","localized_name":"正面条件","name":"positive","type":"CONDITIONING","link":4},{"label":"负面条件","localized_name":"负面条件","name":"negative","type":"CONDITIONING","link":6},{"label":"Latent","localized_name":"Latent图像","name":"latent_image","type":"LATENT","link":2},{"localized_name":"随机种","name":"seed","type":"INT","widget":{"name":"seed"},"link":null},{"localized_name":"步数","name":"steps","type":"INT","widget":{"name":"steps"},"link":null},{"localized_name":"CFG","name":"cfg","type":"FLOAT","widget":{"name":"cfg"},"link":null},{"localized_name":"采样器","name":"sampler_name","type":"COMBO","widget":{"name":"sampler_name"},"link":null},{"localized_name":"调度器","name":"scheduler","type":"COMBO","widget":{"name":"scheduler"},"link":null},{"localized_name":"降噪","name":"denoise","type":"FLOAT","widget":{"name":"denoise"},"link":null}],"outputs":[{"label":"Latent","localized_name":"Latent","name":"LATENT","type":"LATENT","slot_index":0,"links":[7]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.65","Node name for S&R":"KSampler"},"widgets_values":[252748603843421,"randomize",20,8,"euler","normal",1]},{"id":8,"type":"VAEDecode","pos":[1209,188],"size":[210,46],"flags":{},"order":5,"mode":0,"inputs":[{"label":"Latent","localized_name":"Latent","name":"samples","type":"LATENT","link":7},{"label":"VAE","localized_name":"vae","name":"vae","type":"VAE","link":8}],"outputs":[{"label":"图像","localized_name":"图像","name":"IMAGE","type":"IMAGE","slot_index":0,"links":[9]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.65","Node name for S&R":"VAEDecode"},"widgets_values":[]},{"id":9,"type":"SaveImage","pos":[1451,189],"size":[210,58],"flags":{},"order":6,"mode":0,"inputs":[{"label":"图像","localized_name":"图片","name":"images","type":"IMAGE","link":9},{"localized_name":"文件名前缀","name":"filename_prefix","type":"STRING","widget":{"name":"filename_prefix"},"link":null}],"outputs":[],"properties":{"cnr_id":"comfy-core","ver":"0.3.65"},"widgets_values":["ComfyUI"]},{"id":4,"type":"CheckpointLoaderSimple","pos":[26,474],"size":[315,98],"flags":{},"order":1,"mode":0,"inputs":[{"localized_name":"Checkpoint名称","name":"ckpt_name","type":"COMBO","widget":{"name":"ckpt_name"},"link":null}],"outputs":[{"label":"模型","localized_name":"模型","name":"MODEL","type":"MODEL","slot_index":0,"links":[1]},{"label":"CLIP","localized_name":"CLIP","name":"CLIP","type":"CLIP","slot_index":1,"links":[3,5]},{"label":"VAE","localized_name":"VAE","name":"VAE","type":"VAE","slot_index":2,"links":[8]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.65","Node name for S&R":"CheckpointLoaderSimple","models":[{"name":"v1-5-pruned-emaonly-fp16.safetensors","url":"https://huggingface.co/Comfy-Org/stable-diffusion-v1-5-archive/resolve/main/v1-5-pruned-emaonly-fp16.safetensors?download=true","directory":"checkpoints"}]},"widgets_values":["juggernautXL_v9_V9 + RDPhoto 2.safetensors"]}],"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":0.6344410876132931,"offset":[259.83333333333326,142.1738095238095]}},"version":0.4}
```
## Additional Context
(Please add any additional context or steps to reproduce the error here)
一般是GPU卡，并不支持cuda-malloc函数或接口。如果在后续的运行中遇到了CUDA error错误，那么就在启动命令行后面，添加：--disable-cuda-malloc。或者可以看下自己的cuda版本和GPU驱动是否匹配。
© 版权声明
文章版权归作者所有，未经允许请勿转载。
THE END
暂无评论内容