Error occurred when executing Image2Text: PytorchStreamReader failed reading zip archive: moondream1

[dxdpxl]

It loads the model by "Loader Image to text Model node" but when loading "Image to Text node" this error occurs.

Error occurred when executing Image2Text:

PytorchStreamReader failed reading zip archive: failed finding central directory

File "E:\comfyui\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\comfyui\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 "E:\comfyui\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\comfyui\comfyui\custom_nodes\Comfyui_image2prompt\src\image2text.py", line 107, in get_value
result = model.answer_question(img, query)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\comfyui\comfyui\custom_nodes\Comfyui_image2prompt\src\moondream_model.py", line 1225, in answer_question
output = self.text_model.answer_question(self.cached_vision_encoder( image), question)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\comfyui\comfyui\custom_nodes\Comfyui_image2prompt\src\moondream_model.py", line 1212, in cached_vision_encoder
return torch.load(cache_path).to(device=self.device, dtype=self.dtype)
^^^^^^^^^^^^^^^^^^^^^^
File "E:\comfyui\python_embeded\Lib\site-packages\torch\serialization.py", line 1007, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\comfyui\python_embeded\Lib\site-packages\torch\serialization.py", line 459, in init
super().init(torch._C.PyTorchFileReader(name_or_buffer))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Any idea why this happens? Already deleted the custom node folder of img2prompt and re-downloaded the files both by comfyui manager, manually with git clone and also manually by zip file from github. Same with the moondream1 model, re-downloaded multiple times but nothing helps. Moondream2 model works without issues.