Comfy-Org / Comfy-Org/ComfyUI

Clip Text Encode Error

Open
#7,568 6 comments 0 reactions 0 assignees View on GitHub
Potential Bug
Dominant language
Python
Stars
133k
Forks
15.7k
Avg merge
1d 6h
Merged PRs (30d)
155

Description

### Expected Behavior

I am trying to run Comfy UI on a new machine which has an NVIDIA 5090 graphics car running CUDA version 12,8. I am getting the below error message which seems to indicate a conflict between versions of python and CUDA, I have upgraded to python 3.13.3 but it still does not work. Has anyone found a method to deal with this?

### Actual Behavior

# ComfyUI Error Report
## Error Details
- **Node ID:** 7
- **Node Type:** CLIPTextEncode
- **Exception Type:** RuntimeError
- **Exception Message:** CUDA error: no kernel image is available for execution on the device
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.

### Steps to Reproduce

Use basic text to image workflow template that came with COMFYUI. getting same error regardless of workflow used.

### Debug Logs

```powershell
# ComfyUI Error Report
## Error Details
- **Node ID:** 7
- **Node Type:** CLIPTextEncode
- **Exception Type:** RuntimeError
- **Exception Message:** CUDA error: no kernel image is available for execution on the device
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\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 327, 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\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 202, 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\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)

File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\nodes.py", line 69, in encode
return (clip.encode_from_tokens_scheduled(tokens), )
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd.py", line 153, in encode_from_tokens_scheduled
pooled_dict = self.encode_from_tokens(tokens, return_pooled=return_pooled, return_dict=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd.py", line 215, in encode_from_tokens
o = self.cond_stage_model.encode_token_weights(tokens)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd1_clip.py", line 662, in encode_token_weights
out = getattr(self, self.clip).encode_token_weights(token_weight_pairs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd1_clip.py", line 45, in encode_token_weights
o = self.encode(to_encode)
^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd1_clip.py", line 274, in encode
return self(tokens)
^^^^^^^^^^^^

File "C:\Users\markb\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd1_clip.py", line 241, in forward
embeds, attention_mask, num_tokens = self.process_tokens(tokens, device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd1_clip.py", line 195, in process_tokens
tokens_embed = self.transformer.get_input_embeddings()(tokens_embed, out_dtype=torch.float32)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\ops.py", line 205, in forward
return self.forward_comfy_cast_weights(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\ops.py", line 201, in forward_comfy_cast_weights
return torch.nn.functional.embedding(input, weight, self.padding_idx, self.max_norm, self.norm_type, self.scale_grad_by_freq, self.sparse).to(dtype=output_dtype)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\markb\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\functional.py", line 2551, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

## System Information
- **ComfyUI Version:** 0.3.27
- **Arguments:** C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\main.py --user-directory C:\Users\markb\Documents\ComfyUI\user --input-directory C:\Users\markb\Documents\ComfyUI\input --output-directory C:\Users\markb\Documents\ComfyUI\output --front-end-root C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\web_custom_versions\desktop_app --base-directory C:\Users\markb\Documents\ComfyUI --extra-model-paths-config C:\Users\markb\AppData\Roaming\ComfyUI\extra_models_config.yaml --log-stdout --listen 127.0.0.1 --port 8000
- **OS:** nt
- **Python Version:** 3.12.9 (main, Feb 12 2025, 14:52:31) [MSC v.1942 64 bit (AMD64)]
- **Embedded Python:** false
- **PyTorch Version:** 2.6.0+cu126
## Devices

- **Name:** cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
- **Type:** cuda
- **VRAM Total:** 34190458880
- **VRAM Free:** 32081346044
- **Torch VRAM Total:** 268435456
- **Torch VRAM Free:** 21134844

## Logs

2025-04-10T23:30:33.216731 - Adding extra search path custom_nodes C:\Users\markb\Documents\ComfyUI\custom_nodes
2025-04-10T23:30:33.216731 - Adding extra search path download_model_base C:\Users\markb\Documents\ComfyUI\models
2025-04-10T23:30:33.216731 - Adding extra search path custom_nodes C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\custom_nodes
2025-04-10T23:30:33.216731 - Setting output directory to: C:\Users\markb\Documents\ComfyUI\output
2025-04-10T23:30:33.216731 - Setting input directory to: C:\Users\markb\Documents\ComfyUI\input
2025-04-10T23:30:33.216731 - Setting user directory to: C:\Users\markb\Documents\ComfyUI\user
2025-04-10T23:30:35.204041 - [START] Security scan2025-04-10T23:30:35.204041 -
2025-04-10T23:30:36.807936 - [DONE] Security scan2025-04-10T23:30:36.807936 -
2025-04-10T23:30:37.234880 - ## ComfyUI-Manager: installing dependencies done.2025-04-10T23:30:37.234880 -
2025-04-10T23:30:37.234880 - ** ComfyUI startup time:2025-04-10T23:30:37.234880 - 2025-04-10T23:30:37.234880 - 2025-04-10 23:30:37.2342025-04-10T23:30:37.234880 -
2025-04-10T23:30:37.234880 - ** Platform:2025-04-10T23:30:37.234880 - 2025-04-10T23:30:37.234880 - Windows2025-04-10T23:30:37.234880 -
2025-04-10T23:30:37.234880 - ** Python version:2025-04-10T23:30:37.234880 - 2025-04-10T23:30:37.234880 - 3.12.9 (main, Feb 12 2025, 14:52:31) [MSC v.1942 64 bit (AMD64)]2025-04-10T23:30:37.234880 -
2025-04-10T23:30:37.234880 - ** Python executable:2025-04-10T23:30:37.234880 - 2025-04-10T23:30:37.234880 - C:\Users\markb\Documents\ComfyUI\.venv\Scripts\python.exe2025-04-10T23:30:37.234880 -
2025-04-10T23:30:37.234880 - ** ComfyUI Path:2025-04-10T23:30:37.234880 - 2025-04-10T23:30:37.234880 - C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI2025-04-10T23:30:37.234880 -
2025-04-10T23:30:37.234880 - ** ComfyUI Base Folder Path:2025-04-10T23:30:37.234880 - 2025-04-10T23:30:37.235380 - C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI2025-04-10T23:30:37.235380 -
2025-04-10T23:30:37.235380 - ** User directory:2025-04-10T23:30:37.235380 - 2025-04-10T23:30:37.235380 - C:\Users\markb\Documents\ComfyUI\user2025-04-10T23:30:37.235380 -
2025-04-10T23:30:37.235380 - ** ComfyUI-Manager config path:2025-04-10T23:30:37.235380 - 2025-04-10T23:30:37.235380 - C:\Users\markb\Documents\ComfyUI\user\default\ComfyUI-Manager\config.ini2025-04-10T23:30:37.235380 -
2025-04-10T23:30:37.235380 - ** Log path:2025-04-10T23:30:37.235380 - 2025-04-10T23:30:37.235380 - C:\Users\markb\Documents\ComfyUI\user\comfyui.log2025-04-10T23:30:37.235380 -
2025-04-10T23:30:37.760160 - [ComfyUI-Manager] Failed to restore comfyui-frontend-package
2025-04-10T23:30:37.760160 - expected str, bytes or os.PathLike object, not NoneType
2025-04-10T23:30:37.762660 -
Prestartup times for custom nodes:
2025-04-10T23:30:37.762660 - 4.5 seconds: C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\custom_nodes\ComfyUI-Manager
2025-04-10T23:30:37.762660 -
2025-04-10T23:30:52.350824 - Checkpoint files will always be loaded safely.
2025-04-10T23:30:52.543431 - C:\Users\markb\Documents\ComfyUI\.venv\Lib\site-packages\torch\cuda\__init__.py:235: UserWarning:
NVIDIA GeForce RTX 5090 with CUDA capability sm_120 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_50 sm_60 sm_61 sm_70 sm_75 sm_80 sm_86 sm_90.
If you want to use the NVIDIA GeForce RTX 5090 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/

warnings.warn(
2025-04-10T23:30:52.739715 - Total VRAM 32607 MB, total RAM 64873 MB
2025-04-10T23:30:52.739715 - pytorch version: 2.6.0+cu126
2025-04-10T23:30:52.740214 - Set vram state to: NORMAL_VRAM
2025-04-10T23:30:52.740214 - Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
2025-04-10T23:30:59.010597 - Using pytorch attention
2025-04-10T23:31:16.159835 - ComfyUI version: 0.3.27
2025-04-10T23:31:16.173842 - [Prompt Server] web root: C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\web_custom_versions\desktop_app
2025-04-10T23:31:18.066616 - ### Loading: ComfyUI-Manager (V3.30.4)
2025-04-10T23:31:18.067114 - [ComfyUI-Manager] network_mode: public
2025-04-10T23:31:18.067114 - ### ComfyUI Revision: UNKNOWN (The currently installed ComfyUI is not a Git repository)
2025-04-10T23:31:18.081106 -
Import times for custom nodes:
2025-04-10T23:31:18.081106 - 0.0 seconds: C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\custom_nodes\websocket_image_save.py
2025-04-10T23:31:18.081106 - 0.0 seconds: C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\custom_nodes\ComfyUI-Manager
2025-04-10T23:31:18.081106 -
2025-04-10T23:31:18.085106 - Starting server

2025-04-10T23:31:18.085106 - To see the GUI go to: http://127.0.0.1:8000
2025-04-10T23:31:18.288854 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
2025-04-10T23:31:18.315387 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
2025-04-10T23:31:18.332019 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
2025-04-10T23:31:18.409487 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
2025-04-10T23:31:18.437501 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
2025-04-10T23:31:21.142461 - FETCH ComfyRegistry Data: 5/812025-04-10T23:31:21.142461 -
2025-04-10T23:31:24.260234 - FETCH ComfyRegistry Data: 10/812025-04-10T23:31:24.260234 -
2025-04-10T23:31:27.421588 - FETCH ComfyRegistry Data: 15/812025-04-10T23:31:27.421588 -
2025-04-10T23:31:30.586020 - FETCH ComfyRegistry Data: 20/812025-04-10T23:31:30.586519 -
2025-04-10T23:31:33.759578 - FETCH ComfyRegistry Data: 25/812025-04-10T23:31:33.759578 -
2025-04-10T23:31:37.005225 - FETCH ComfyRegistry Data: 30/812025-04-10T23:31:37.005225 -
2025-04-10T23:31:40.195519 - FETCH ComfyRegistry Data: 35/812025-04-10T23:31:40.195519 -
2025-04-10T23:31:42.184752 - got prompt
2025-04-10T23:31:43.016956 - model weight dtype torch.float16, manual cast: None
2025-04-10T23:31:43.031456 - model_type EPS
2025-04-10T23:31:43.365122 - FETCH ComfyRegistry Data: 40/812025-04-10T23:31:43.365122 -
2025-04-10T23:31:46.276233 - Using pytorch attention in VAE
2025-04-10T23:31:46.277233 - Using pytorch attention in VAE
2025-04-10T23:31:46.654786 - FETCH ComfyRegistry Data: 45/812025-04-10T23:31:46.654786 -
2025-04-10T23:31:48.116026 - VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
2025-04-10T23:31:48.202422 - CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
2025-04-10T23:31:49.542402 - Requested to load SD1ClipModel
2025-04-10T23:31:49.628980 - loaded completely 29423.8 235.84423828125 True
2025-04-10T23:31:50.053295 - !!! Exception during processing !!! CUDA error: no kernel image is available for execution on the device
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.

2025-04-10T23:31:50.074795 - Traceback (most recent call last):
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 327, 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\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 202, 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\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\nodes.py", line 69, in encode
return (clip.encode_from_tokens_scheduled(tokens), )
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd.py", line 153, in encode_from_tokens_scheduled
pooled_dict = self.encode_from_tokens(tokens, return_pooled=return_pooled, return_dict=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd.py", line 215, in encode_from_tokens
o = self.cond_stage_model.encode_token_weights(tokens)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd1_clip.py", line 662, in encode_token_weights
out = getattr(self, self.clip).encode_token_weights(token_weight_pairs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd1_clip.py", line 45, in encode_token_weights
o = self.encode(to_encode)
^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd1_clip.py", line 274, in encode
return self(tokens)
^^^^^^^^^^^^
File "C:\Users\markb\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd1_clip.py", line 241, in forward
embeds, attention_mask, num_tokens = self.process_tokens(tokens, device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd1_clip.py", line 195, in process_tokens
tokens_embed = self.transformer.get_input_embeddings()(tokens_embed, out_dtype=torch.float32)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\ops.py", line 205, in forward
return self.forward_comfy_cast_weights(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\ops.py", line 201, in forward_comfy_cast_weights
return torch.nn.functional.embedding(input, weight, self.padding_idx, self.max_norm, self.norm_type, self.scale_grad_by_freq, self.sparse).to(dtype=output_dtype)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\markb\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\functional.py", line 2551, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: CUDA error: no kernel image is available for execution on the device
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.

2025-04-10T23:31:50.075791 - Prompt executed in 7.89 seconds

## Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.

{"id":"2b8a69fc-505c-4719-9e4a-0c593b57d410","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":[{"localized_name":"clip","name":"clip","type":"CLIP","link":5}],"outputs":[{"localized_name":"CONDITIONING","name":"CONDITIONING","type":"CONDITIONING","slot_index":0,"links":[6]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.27","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":[{"localized_name":"clip","name":"clip","type":"CLIP","link":3}],"outputs":[{"localized_name":"CONDITIONING","name":"CONDITIONING","type":"CONDITIONING","slot_index":0,"links":[4]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.27","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":[],"outputs":[{"localized_name":"LATENT","name":"LATENT","type":"LATENT","slot_index":0,"links":[2]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.27","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":[{"localized_name":"model","name":"model","type":"MODEL","link":1},{"localized_name":"positive","name":"positive","type":"CONDITIONING","link":4},{"localized_name":"negative","name":"negative","type":"CONDITIONING","link":6},{"localized_name":"latent_image","name":"latent_image","type":"LATENT","link":2}],"outputs":[{"localized_name":"LATENT","name":"LATENT","type":"LATENT","slot_index":0,"links":[7]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.27","Node name for S&R":"KSampler"},"widgets_values":[323517548819534,"randomize",20,8,"euler","normal",1]},{"id":8,"type":"VAEDecode","pos":[1209,188],"size":[210,46],"flags":{},"order":5,"mode":0,"inputs":[{"localized_name":"samples","name":"samples","type":"LATENT","link":7},{"localized_name":"vae","name":"vae","type":"VAE","link":8}],"outputs":[{"localized_name":"IMAGE","name":"IMAGE","type":"IMAGE","slot_index":0,"links":[9]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.27","Node name for S&R":"VAEDecode"},"widgets_values":[]},{"id":9,"type":"SaveImage","pos":[1451,189],"size":[210,58],"flags":{},"order":6,"mode":0,"inputs":[{"localized_name":"images","name":"images","type":"IMAGE","link":9}],"outputs":[],"properties":{"cnr_id":"comfy-core","ver":"0.3.27"},"widgets_values":["ComfyUI"]},{"id":4,"type":"CheckpointLoaderSimple","pos":[26,474],"size":[315,98],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"localized_name":"MODEL","name":"MODEL","type":"MODEL","slot_index":0,"links":[1]},{"localized_name":"CLIP","name":"CLIP","type":"CLIP","slot_index":1,"links":[3,5]},{"localized_name":"VAE","name":"VAE","type":"VAE","slot_index":2,"links":[8]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.27","Node name for S&R":"CheckpointLoaderSimple"},"widgets_values":["v1-5-pruned-emaonly-fp16.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":1.3310000000000004,"offset":[243.69797145003722,46.11269722013501]}},"version":0.4}

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

### Other

_No response_

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.