No requirements.txt file

[quixot1c]

There is no requirements.txt file and therefore required dependencies are not installed and I get the error:

Error occurred when executing LoadElla:

T5Tokenizer requires the SentencePiece library but it was not found in your environment. Checkout the instructions on the
installation page of its repo: https://github.com/google/sentencepiece#installation and follow the ones
that match your environment. Please note that you may need to restart your runtime after installation.

Please add a requirements.txt file so that requirements are installed automatically into the venv. Thank you.

[Astropulse]

+1

Interestingly sentencepiece seems to be installed in my comfyui venv, but theres clearly something wrong with transformers or this node.

[mrkennypowers]

I'm having the same issue. How do i install sentencepiece on comfy portable?

[quixot1c]

Create a requirements.txt file in the root of the ComfyUI_ELLA folder with the contents

sentencepiece

Then run ../../../python_embeded/python.exe -s -m pip install -r requirements.txt.

Maybe you need more or less ../ depending on how deeply nested your custom_nodes folder is, but this is what worked on my system.

[mrkennypowers]

Create a requirements.txt file in the root of the ComfyUI_ELLA folder with the contents

sentencepiece

Then run ../../../python_embeded/python.exe -s -m pip install -r requirements.txt.

Maybe you need more or less ../ depending on how deeply nested your custom_nodes folder is, but this is what worked on my system.

Thank you. That did it.

[BuckRogers01]

I am also having the same problem, I uninstalled it using pip, reinstalled it by the suggested method by quixot1c and just got this as a result, "Error occurred when executing LoadElla:

T5Tokenizer requires the SentencePiece library but it was not found in your environment. Checkout the instructions on the
installation page of its repo: https://github.com/google/sentencepiece#installation and follow the ones
that match your environment. Please note that you may need to restart your runtime after installation.

File "C:\Users\steve\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\steve\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\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\steve\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\steve\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\custom_nodes\ComfyUI_ELLA\ella.py", line 68, in load_ella
t5_model = T5TextEmbedder(t5_path).to(self.device, self.dtype)
^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\steve\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI\custom_nodes\ComfyUI_ELLA\ella_model\model.py", line 241, in init
self.tokenizer = T5Tokenizer.from_pretrained(pretrained_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\steve\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\python_embeded\Lib\site-packages\transformers\utils\import_utils.py", line 1050, in getattribute
requires_backends(cls, cls._backends)
File "C:\Users\steve\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\python_embeded\Lib\site-packages\transformers\utils\import_utils.py", line 1038, in requires_backends
raise ImportError("".join(failed))"