I have an RTX 5080

### Expected Behavior

Basic picture creating workflow does not create an image gives this error

### Actual Behavior

I get an error even trying to create the basic image

CLIPTextEncode
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.

I also have a local version of come for UI that doesn't work with most nodes and I'm really wondering how to get round all this because I'm not very knowledgeable about the compatibility of the nodes with python and CUDA

Any help would be mostly appreciated even if you heading me in the right direction
Thanks Louis

### Steps to Reproduce

Download uninstall come for UI on your local machine and run the basic image workflow again the challenge I believe is with my new RTX 5080 graphics card compatibility

### Debug Logs

```powershell
Prompt executed in 4.56 seconds
FETCH ComfyRegistry Data: 40/79
FETCH ComfyRegistry Data: 45/79
FETCH ComfyRegistry Data: 50/79
FETCH ComfyRegistry Data: 55/79
FETCH ComfyRegistry Data: 60/79
FETCH ComfyRegistry Data: 65/79
FETCH ComfyRegistry Data: 70/79
FETCH ComfyRegistry Data: 75/79
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
nightly_channel:
https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/remote
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[ComfyUI-Manager] All startup tasks have been completed.
got prompt
!!! Exception during processing !!! 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.

Traceback (most recent call last):
File "C:\Users\louis\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\louis\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\louis\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)
File "C:\Users\louis\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\louis\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\nodes.py", line 69, in encode
return (clip.encode_from_tokens_scheduled(tokens), )
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\louis\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\louis\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\louis\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\louis\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\louis\AppData\Local\Programs\@comfyorgcomfyui-electron\resources\ComfyUI\comfy\sd1_clip.py", line 274, in encode
return self(tokens)
^^^^^^^^^^^^
File "C:\Users\louis\OneDrive\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\louis\OneDrive\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\louis\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\louis\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\louis\OneDrive\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\louis\OneDrive\Documents\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\louis\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\louis\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\louis\OneDrive\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.

Prompt executed in 0.01 seconds
```

### Other

_No response_

Start by reproducing the basic image workflow on the reported RTX 5080 and trace the failure from execution.py and nodes.py through comfy/sd1_clip.py and comfy/ops.py. Compare the installed PyTorch environment with the GPU requirements, then determine what change or supported setup would make CLIPTextEncode complete without the CUDA kernel error.

Written by the indexing model from the issue text.