엔비디아 그래픽 5070ti를 사용하고 있습니다.

다름이 아니라 0.2.x버전을 이용하려다 보니 강의에서 안내해 준 대로 설치하면 그래픽 카드로 인해

cuda 관련 에러가 뜹니다

----1. 설치 후 뜨는 화면 자체도 강의와 다름----

노드 안에 박스 자체가 활성화가 안되어 있음

------

---2. cuda 관련 에러---

Error occurred when executing 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.

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\execution.py", line 151, in recursive_execute

output_data, output_ui = get_output_data(obj, input_data_all)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\execution.py", line 81, in get_output_data

return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\execution.py", line 74, in map_node_over_list

results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\nodes.py", line 58, in encode

cond, pooled = clip.encode_from_tokens(tokens, return_pooled=True)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\comfy\sd.py", line 143, in encode_from_tokens

cond, pooled = self.cond_stage_model.encode_token_weights(tokens)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\comfy\sd1_clip.py", line 527, in encode_token_weights

out, pooled = getattr(self, self.clip).encode_token_weights(token_weight_pairs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\comfy\sd1_clip.py", line 41, in encode_token_weights

out, pooled = self.encode(to_encode)

^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\comfy\sd1_clip.py", line 202, in encode

return self(tokens)

^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl

return forward_call(*args, **kwargs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\comfy\sd1_clip.py", line 181, in forward

outputs = self.transformer(tokens, attention_mask, intermediate_output=self.layer_idx, final_layer_norm_intermediate=self.layer_norm_hidden_state)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl

return forward_call(*args, **kwargs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\comfy\clip_model.py", line 134, in forward

x = self.text_model(*args, **kwargs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl

return forward_call(*args, **kwargs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\comfy\clip_model.py", line 97, in forward

x = self.embeddings(input_tokens)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl

return forward_call(*args, **kwargs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\ComfyUI\comfy\clip_model.py", line 80, in forward

return self.token_embedding(input_tokens) + self.position_embedding.weight

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl

return forward_call(*args, **kwargs)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\modules\sparse.py", line 163, in forward

return F.embedding(

^^^^^^^^^^^^

File "C:\Users\Admin\Documents\Sd\fc_comfyui\ComfyUI_windows_portable_soylab\python_embeded\Lib\site-packages\torch\nn\functional.py", line 2237, in embedding

return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)

--------

그래서

드라이브 자료실에 있는 "50xx_ComfyUI_for_Part01_Part04-001" 파일을

여기 강의에서 준 0.2.x 버전의 컴파이에 덮어씌우기를 하면

컴파이가 작동이 안되는데 어떻게 해결해야 할까요

-----

덧

만약 사용하시는 GPU가 50xx GPU인 경우 강의 자료실에 있는 50xx용 ComfyUI 셋팅 파일을 받으셔서 사용하시면 조금 더 편하게 강의 실습을 진행 하실 수 있습니다. (해당 셋팅 파일 사용시 강의를 모든 파트를 생성 실습 할 수 있도록 셋팅 되어 있기 때문에 설치 부분은 실습을 하지 않으시고 이해하는 과정으로 진행 해 주셔도 무방합니다.)

이런 답변을 달아주셨던데 "50xx_ComfyUI_for_Part01_Part04-001"를 파일 내부를 보니 models 폴더 안에 checkpoints, lora 등등 필수적인 폴더들이 없던데 그거 그냥 수동으로 만들어 주면 되나요?? 그거 안하려고 0,2.x 컴파이 파일에 덮어씌우려고 했던건데 오류가 납니다.