5080 series graphics cards are currently reporting an error

### Your question

Graphics driver: 572.24-desktop-notebook-win10-win11-64bit-international-dch.hf
cuda: cuda_12.8.0_571.96_windows

CUDA error: no kernel image is available for execution on the deviceCUDA 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=1Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions. is:issue

### 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 "D:\AI\ComfyUI-aki\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 "D:\AI\ComfyUI-aki\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 "D:\AI\ComfyUI-aki\execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)

File "D:\AI\ComfyUI-aki\execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))

File "D:\AI\ComfyUI-aki\nodes.py", line 69, in encode
return (clip.encode_from_tokens_scheduled(tokens), )

File "D:\AI\ComfyUI-aki\comfy\sd.py", line 149, in encode_from_tokens_scheduled
pooled_dict = self.encode_from_tokens(tokens, return_pooled=return_pooled, return_dict=True)

File "D:\AI\ComfyUI-aki\comfy\sd.py", line 211, in encode_from_tokens
o = self.cond_stage_model.encode_token_weights(tokens)

File "D:\AI\ComfyUI-aki\comfy\sd1_clip.py", line 640, in encode_token_weights
out = getattr(self, self.clip).encode_token_weights(token_weight_pairs)

File "D:\AI\ComfyUI-aki\comfy\sd1_clip.py", line 45, in encode_token_weights
o = self.encode(to_encode)

File "D:\AI\ComfyUI-aki\comfy\sd1_clip.py", line 252, in encode
return self(tokens)

File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)

File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)

File "D:\AI\ComfyUI-aki\comfy\sd1_clip.py", line 224, in forward
outputs = self.transformer(tokens, attention_mask_model, intermediate_output=self.layer_idx, final_layer_norm_intermediate=self.layer_norm_hidden_state, dtype=torch.float32)

File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)

File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)

File "D:\AI\ComfyUI-aki\comfy\clip_model.py", line 137, in forward
x = self.text_model(*args, **kwargs)

File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)

File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)

File "D:\AI\ComfyUI-aki\comfy\clip_model.py", line 101, in forward
x = self.embeddings(input_tokens, dtype=dtype)

File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)

File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)

File "D:\AI\ComfyUI-aki\comfy\clip_model.py", line 82, in forward
return self.token_embedding(input_tokens, out_dtype=dtype) + comfy.ops.cast_to(self.position_embedding.weight, dtype=dtype, device=input_tokens.device)

File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)

File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)

File "D:\AI\ComfyUI-aki\comfy\ops.py", line 203, in forward
return self.forward_comfy_cast_weights(*args, **kwargs)

File "D:\AI\ComfyUI-aki\comfy\ops.py", line 199, 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 "D:\AI\ComfyUI-aki\python\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:** 0.3.14
- **Arguments:** D:\AI\ComfyUI-aki\main.py --auto-launch --preview-method auto --disable-cuda-malloc --fast
- **OS:** nt
- **Python Version:** 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]
- **Embedded Python:** false
- **PyTorch Version:** 2.5.1+cu124
## Devices

- **Name:** cuda:0 NVIDIA GeForce RTX 5080 : cudaMallocAsync
- **Type:** cuda
- **VRAM Total:** 17094475776
- **VRAM Free:** 15329295868
- **Torch VRAM Total:** 268435456
- **Torch VRAM Free:** 21134844

## Logs

2025-02-07T20:50:46.273947 - [START] Security scan2025-02-07T20:50:46.273947 -
2025-02-07T20:50:48.617212 - [DONE] Security scan2025-02-07T20:50:48.617212 -
2025-02-07T20:50:48.730439 - ## ComfyUI-Manager: installing dependencies done.2025-02-07T20:50:48.730439 -
2025-02-07T20:50:48.730439 - ** ComfyUI startup time:2025-02-07T20:50:48.730439 - 2025-02-07T20:50:48.730439 - 2025-02-07 20:50:48.7302025-02-07T20:50:48.731439 -
2025-02-07T20:50:48.731439 - ** Platform:2025-02-07T20:50:48.731439 - 2025-02-07T20:50:48.731439 - Windows2025-02-07T20:50:48.731439 -
2025-02-07T20:50:48.731439 - ** Python version:2025-02-07T20:50:48.731439 - 2025-02-07T20:50:48.731439 - 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]2025-02-07T20:50:48.731439 -
2025-02-07T20:50:48.731439 - ** Python executable:2025-02-07T20:50:48.731439 - 2025-02-07T20:50:48.731439 - D:\AI\ComfyUI-aki\python\python.exe2025-02-07T20:50:48.731439 -
2025-02-07T20:50:48.731439 - ** ComfyUI Path:2025-02-07T20:50:48.731439 - 2025-02-07T20:50:48.731439 - D:\AI\ComfyUI-aki2025-02-07T20:50:48.731439 -
2025-02-07T20:50:48.731439 - ** ComfyUI Base Folder Path:2025-02-07T20:50:48.731439 - 2025-02-07T20:50:48.731439 - D:\AI\ComfyUI-aki2025-02-07T20:50:48.731439 -
2025-02-07T20:50:48.731439 - ** User directory:2025-02-07T20:50:48.731439 - 2025-02-07T20:50:48.731439 - D:\AI\ComfyUI-aki\user2025-02-07T20:50:48.731439 -
2025-02-07T20:50:48.731439 - ** ComfyUI-Manager config path:2025-02-07T20:50:48.731439 - 2025-02-07T20:50:48.731439 - D:\AI\ComfyUI-aki\user\default\ComfyUI-Manager\config.ini2025-02-07T20:50:48.731439 -
2025-02-07T20:50:48.731439 - ** Log path:2025-02-07T20:50:48.731439 - 2025-02-07T20:50:48.731439 - D:\AI\ComfyUI-aki\user\comfyui.log2025-02-07T20:50:48.731439 -
2025-02-07T20:50:56.887172 - [ComfyUI-Manager] 'opencv' dependencies were fixed: ['opencv-contrib-python', 'opencv-python', 'opencv-python-headless']
2025-02-07T20:50:56.889175 -
Prestartup times for custom nodes:
2025-02-07T20:50:56.889175 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\rgthree-comfy
2025-02-07T20:50:56.889175 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-Marigold
2025-02-07T20:50:56.889175 - 10.6 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-Manager
2025-02-07T20:50:56.889175 -
2025-02-07T20:50:58.030053 - Checkpoint files will always be loaded safely.
2025-02-07T20:50:58.086053 - D:\AI\ComfyUI-aki\python\lib\site-packages\torch\cuda\__init__.py:235: UserWarning:
NVIDIA GeForce RTX 5080 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 5080 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/

warnings.warn(
2025-02-07T20:50:58.140562 - Total VRAM 16303 MB, total RAM 63032 MB
2025-02-07T20:50:58.140562 - pytorch version: 2.5.1+cu124
2025-02-07T20:50:58.140562 - Set vram state to: NORMAL_VRAM
2025-02-07T20:50:58.140562 - Device: cuda:0 NVIDIA GeForce RTX 5080 : cudaMallocAsync
2025-02-07T20:50:58.840903 - Using pytorch attention
2025-02-07T20:50:59.466969 - ComfyUI version: 0.3.14
2025-02-07T20:50:59.508479 - [Prompt Server] web root: D:\AI\ComfyUI-aki\web
2025-02-07T20:50:59.819768 - [Crystools INFO] Crystools version: 1.22.0
2025-02-07T20:50:59.829769 - [Crystools INFO] CPU: AMD Ryzen 9 9900X 12-Core Processor - Arch: AMD64 - OS: Windows 10
2025-02-07T20:50:59.920279 - [Crystools INFO] Pynvml (Nvidia) initialized.
2025-02-07T20:50:59.920279 - [Crystools INFO] GPU/s:
2025-02-07T20:50:59.931711 - [Crystools INFO] 0) NVIDIA GeForce RTX 5080
2025-02-07T20:50:59.931711 - [Crystools INFO] NVIDIA Driver: 572.24
2025-02-07T20:50:59.943714 - ### Loading: ComfyUI-Impact-Pack (V8.8.1)2025-02-07T20:50:59.943714 -
2025-02-07T20:51:00.043224 - [Impact Pack] Wildcards loading done.2025-02-07T20:51:00.043224 -
2025-02-07T20:51:00.047225 - ### Loading: ComfyUI-Inspire-Pack (V1.13)2025-02-07T20:51:00.047225 -
2025-02-07T20:51:00.086225 - Total VRAM 16303 MB, total RAM 63032 MB
2025-02-07T20:51:00.086225 - pytorch version: 2.5.1+cu124
2025-02-07T20:51:00.086225 - Set vram state to: NORMAL_VRAM
2025-02-07T20:51:00.086225 - Device: cuda:0 NVIDIA GeForce RTX 5080 : cudaMallocAsync
2025-02-07T20:51:00.109734 - ### Loading: ComfyUI-Manager (V3.17.7)
2025-02-07T20:51:00.270243 - ### ComfyUI Version: v0.3.14 | Released on '2025-02-05'
2025-02-07T20:51:00.430168 - (pysssss:WD14Tagger) [DEBUG] Available ORT providers: TensorrtExecutionProvider, CUDAExecutionProvider, CPUExecutionProvider2025-02-07T20:51:00.430168 -
2025-02-07T20:51:00.430168 - (pysssss:WD14Tagger) [DEBUG] Using ORT providers: CUDAExecutionProvider, CPUExecutionProvider2025-02-07T20:51:00.430168 -
2025-02-07T20:51:00.529641 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
2025-02-07T20:51:00.568760 - ------------------------------------------2025-02-07T20:51:00.568760 -
2025-02-07T20:51:00.568760 - Comfyroll Studio v1.76 :  175 Nodes Loaded2025-02-07T20:51:00.569760 -
2025-02-07T20:51:00.569760 - ------------------------------------------2025-02-07T20:51:00.569760 -
2025-02-07T20:51:00.569760 - ** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md2025-02-07T20:51:00.569760 -
2025-02-07T20:51:00.569760 - ** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki2025-02-07T20:51:00.569760 -
2025-02-07T20:51:00.569760 - ------------------------------------------2025-02-07T20:51:00.569760 -
2025-02-07T20:51:00.575760 - [comfyui_controlnet_aux] | INFO -> Using ckpts path: D:\AI\ComfyUI-aki\custom_nodes\comfyui_controlnet_aux\ckpts
2025-02-07T20:51:00.575760 - [comfyui_controlnet_aux] | INFO -> Using symlinks: False
2025-02-07T20:51:00.575760 - [comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
2025-02-07T20:51:00.585770 - DWPose: Onnxruntime with acceleration providers detected2025-02-07T20:51:00.585770 -
2025-02-07T20:51:00.593276 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
2025-02-07T20:51:00.604882 - ### [START] ComfyUI AlekPet Nodes v1.0.47 ###2025-02-07T20:51:00.604882 -
2025-02-07T20:51:00.644705 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
2025-02-07T20:51:00.749090 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
2025-02-07T20:51:01.106928 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
2025-02-07T20:51:02.030827 - Node -> ChatGLMNode: ChatGLM4TranslateCLIPTextEncodeNode, ChatGLM4TranslateTextNode, ChatGLM4InstructNode, ChatGLM4InstructMediaNode [Loading] 2025-02-07T20:51:02.030827 -
2025-02-07T20:51:02.033829 - Node -> ArgosTranslateNode: ArgosTranslateCLIPTextEncodeNode, ArgosTranslateTextNode [Loading] 2025-02-07T20:51:02.033829 -
2025-02-07T20:51:02.038827 - Node -> DeepTranslatorNode: DeepTranslatorCLIPTextEncodeNode, DeepTranslatorTextNode [Loading] 2025-02-07T20:51:02.038827 -
2025-02-07T20:51:02.039827 - Node -> GoogleTranslateNode: GoogleTranslateCLIPTextEncodeNode, GoogleTranslateTextNode [Loading] 2025-02-07T20:51:02.039827 -
2025-02-07T20:51:02.042827 - Node -> PoseNode: PoseNode [Loading] 2025-02-07T20:51:02.042827 -
2025-02-07T20:51:02.044827 - Node -> ExtrasNode: PreviewTextNode, HexToHueNode, ColorsCorrectNode [Loading] 2025-02-07T20:51:02.044827 -
2025-02-07T20:51:02.081827 - Node -> IDENode: IDENode [Loading] 2025-02-07T20:51:02.081827 -
2025-02-07T20:51:02.198190 - Node -> PainterNode: PainterNode [Loading] 2025-02-07T20:51:02.198190 -
2025-02-07T20:51:02.198190 - ### [END] ComfyUI AlekPet Nodes ###2025-02-07T20:51:02.198190 -
2025-02-07T20:51:02.566433 - Note: NumExpr detected 24 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8.
2025-02-07T20:51:02.566433 - NumExpr defaulting to 8 threads.
2025-02-07T20:51:02.722453 - FizzleDorf Custom Nodes: Loaded2025-02-07T20:51:02.722453 -
2025-02-07T20:51:02.790456 -
Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success!2025-02-07T20:51:02.790456 -
2025-02-07T20:51:02.793456 - Patching UNetModel.forward2025-02-07T20:51:02.793456 -
2025-02-07T20:51:02.793456 - UNetModel.forward has been successfully patched.2025-02-07T20:51:02.793456 -
2025-02-07T20:51:02.798455 - [Power Noise Suite]: 🦚🦚🦚 Hrruuh-hhruh!!! 🦚🦚🦚2025-02-07T20:51:02.798455 -
2025-02-07T20:51:02.798455 - [Power Noise Suite]: Tamed 11 wild nodes.2025-02-07T20:51:02.798455 -
2025-02-07T20:51:02.809710 -
2025-02-07T20:51:02.809710 - [rgthree-comfy] Loaded 42 extraordinary nodes. 🎉2025-02-07T20:51:02.809710 -
2025-02-07T20:51:02.809710 -
2025-02-07T20:51:02.811709 -
Import times for custom nodes:
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\websocket_image_save.py
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\AIGODLIKE-ComfyUI-Translation
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ControlNet-LLLite-ComfyUI
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUi_NNLatentUpscale
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\FreeU_Advanced
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\stability-ComfyUI-nodes
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI_TiledKSampler
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-WD14-Tagger
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\PowerNoiseSuite
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI_experiments
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\images-grid-comfy-plugin
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-Custom-Scripts
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI_UltimateSDUpscale
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\Derfuu_ComfyUI_ModdedNodes
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-Advanced-ControlNet
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\efficiency-nodes-comfyui
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\rgthree-comfy
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI_IPAdapter_plus
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-KJNodes
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\comfyui_controlnet_aux
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI_TensorRT
2025-02-07T20:51:02.811709 - 0.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-Inspire-Pack
2025-02-07T20:51:02.811709 - 0.1 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-Impact-Pack
2025-02-07T20:51:02.811709 - 0.1 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-Crystools
2025-02-07T20:51:02.811709 - 0.1 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI_Comfyroll_CustomNodes
2025-02-07T20:51:02.811709 - 0.1 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-Marigold
2025-02-07T20:51:02.811709 - 0.2 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI_FizzNodes
2025-02-07T20:51:02.811709 - 0.2 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-Manager
2025-02-07T20:51:02.811709 - 2.0 seconds: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI_Custom_Nodes_AlekPet
2025-02-07T20:51:02.811709 -
2025-02-07T20:51:02.822709 - Starting server

2025-02-07T20:51:02.823709 - To see the GUI go to: http://127.0.0.1:8188
2025-02-07T20:51:03.803338 - FETCH DATA from: D:\AI\ComfyUI-aki\custom_nodes\ComfyUI-Manager\extension-node-map.json2025-02-07T20:51:03.803338 - 2025-02-07T20:51:03.806434 - [DONE]2025-02-07T20:51:03.806434 -
2025-02-07T20:51:09.036152 - FETCH ComfyRegistry Data: 5/322025-02-07T20:51:09.036152 -
2025-02-07T20:51:09.297973 - got prompt
2025-02-07T20:51:09.345795 - model weight dtype torch.float16, manual cast: None
2025-02-07T20:51:09.346794 - model_type EPS
2025-02-07T20:51:09.653737 - Using pytorch attention in VAE
2025-02-07T20:51:09.655737 - Using pytorch attention in VAE
2025-02-07T20:51:09.708730 - VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
2025-02-07T20:51:09.775729 - CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
2025-02-07T20:51:10.108996 - Requested to load SD1ClipModel
2025-02-07T20:51:10.242505 - loaded completely 13447.8 235.84423828125 True
2025-02-07T20:51:10.262506 - !!! 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.

2025-02-07T20:51:10.264055 - Traceback (most recent call last):
File "D:\AI\ComfyUI-aki\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 "D:\AI\ComfyUI-aki\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 "D:\AI\ComfyUI-aki\execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)
File "D:\AI\ComfyUI-aki\execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "D:\AI\ComfyUI-aki\nodes.py", line 69, in encode
return (clip.encode_from_tokens_scheduled(tokens), )
File "D:\AI\ComfyUI-aki\comfy\sd.py", line 149, in encode_from_tokens_scheduled
pooled_dict = self.encode_from_tokens(tokens, return_pooled=return_pooled, return_dict=True)
File "D:\AI\ComfyUI-aki\comfy\sd.py", line 211, in encode_from_tokens
o = self.cond_stage_model.encode_token_weights(tokens)
File "D:\AI\ComfyUI-aki\comfy\sd1_clip.py", line 640, in encode_token_weights
out = getattr(self, self.clip).encode_token_weights(token_weight_pairs)
File "D:\AI\ComfyUI-aki\comfy\sd1_clip.py", line 45, in encode_token_weights
o = self.encode(to_encode)
File "D:\AI\ComfyUI-aki\comfy\sd1_clip.py", line 252, in encode
return self(tokens)
File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "D:\AI\ComfyUI-aki\comfy\sd1_clip.py", line 224, in forward
outputs = self.transformer(tokens, attention_mask_model, intermediate_output=self.layer_idx, final_layer_norm_intermediate=self.layer_norm_hidden_state, dtype=torch.float32)
File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "D:\AI\ComfyUI-aki\comfy\clip_model.py", line 137, in forward
x = self.text_model(*args, **kwargs)
File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "D:\AI\ComfyUI-aki\comfy\clip_model.py", line 101, in forward
x = self.embeddings(input_tokens, dtype=dtype)
File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "D:\AI\ComfyUI-aki\comfy\clip_model.py", line 82, in forward
return self.token_embedding(input_tokens, out_dtype=dtype) + comfy.ops.cast_to(self.position_embedding.weight, dtype=dtype, device=input_tokens.device)
File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\AI\ComfyUI-aki\python\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "D:\AI\ComfyUI-aki\comfy\ops.py", line 203, in forward
return self.forward_comfy_cast_weights(*args, **kwargs)
File "D:\AI\ComfyUI-aki\comfy\ops.py", line 199, 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 "D:\AI\ComfyUI-aki\python\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.

2025-02-07T20:51:10.265060 - Prompt executed in 0.97 seconds

## 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":7,"type":"CLIPTextEncode","pos":[413,389],"size":[425.27801513671875,180.6060791015625],"flags":{},"order":3,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":5,"label":"CLIP"}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[6],"slot_index":0,"label":"条件"}],"properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":["text, watermark",[false,true]]},{"id":6,"type":"CLIPTextEncode","pos":[415,186],"size":[422.84503173828125,164.31304931640625],"flags":{},"order":2,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":3,"label":"CLIP"}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[4],"slot_index":0,"label":"条件"}],"properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":["beautiful scenery nature glass bottle landscape, , purple galaxy bottle,",[false,true]]},{"id":5,"type":"EmptyLatentImage","pos":[473,609],"size":[315,106],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[{"name":"LATENT","type":"LATENT","links":[2],"slot_index":0,"label":"Latent"}],"properties":{"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":[{"name":"model","type":"MODEL","link":1,"label":"模型"},{"name":"positive","type":"CONDITIONING","link":4,"label":"正面条件"},{"name":"negative","type":"CONDITIONING","link":6,"label":"负面条件"},{"name":"latent_image","type":"LATENT","link":2,"label":"Latent"}],"outputs":[{"name":"LATENT","type":"LATENT","links":[7],"slot_index":0,"label":"Latent"}],"properties":{"Node name for S&R":"KSampler"},"widgets_values":[742645724464923,"randomize",20,8,"euler","normal",1]},{"id":8,"type":"VAEDecode","pos":[1209,188],"size":[210,46],"flags":{},"order":5,"mode":0,"inputs":[{"name":"samples","type":"LATENT","link":7,"label":"Latent"},{"name":"vae","type":"VAE","link":8,"label":"VAE"}],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[9],"slot_index":0,"label":"图像"}],"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,"label":"图像"}],"outputs":[],"properties":{},"widgets_values":["ComfyUI"]},{"id":4,"type":"CheckpointLoaderSimple","pos":[26,474],"size":[315,98],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"name":"MODEL","type":"MODEL","links":[1],"slot_index":0,"label":"模型"},{"name":"CLIP","type":"CLIP","links":[3,5],"slot_index":1,"label":"CLIP"},{"name":"VAE","type":"VAE","links":[8],"slot_index":2,"label":"VAE"}],"properties":{"Node name for S&R":"CheckpointLoaderSimple"},"widgets_values":["AAM - AnyLoRA Anime Mix.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,"offset":[0,0]},"node_versions":{"comfy-core":"0.3.14"}},"version":0.4}

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

### Other

_No response_