Giters

yolanother / DTAIImageToTextNode

A ComfyUI node for describing an image

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

TypeError: Cannot handle this data type: (1,1,512,3), |u1

altruios opened this issue · comments

commented

I receive the error when trying to ingest any image with this node. I do not know what might be the matter.

Error occurred when executing DTAIImageToTextNode:

Cannot handle this data type: (1, 1, 512, 3), |u1

  File "${base_dir}/ComfyUI/execution.py", line 155, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/execution.py", line 85, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/execution.py", line 78, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/custom_nodes/DTAIImageToTextNode/__init__.py", line 61, in imagetotext
    caption = image_to_text(image)
              ^^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/custom_nodes/DTAIImageToTextNode/imagetotext.py", line 14, in image_to_text
    inputs = processor(raw_image, return_tensors="pt").to("cuda")
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/lib/python3.11/site-packages/transformers/models/blip/processing_blip.py", line 102, in __call__
    encoding_image_processor = self.image_processor(images, return_tensors=return_tensors)
                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/lib/python3.11/site-packages/transformers/image_processing_utils.py", line 446, in __call__
    return self.preprocess(images, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/lib/python3.11/site-packages/transformers/models/blip/image_processing_blip.py", line 276, in preprocess
    images = [self.resize(image=image, size=size, resample=resample) for image in images]
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/lib/python3.11/site-packages/transformers/models/blip/image_processing_blip.py", line 276, in 
    images = [self.resize(image=image, size=size, resample=resample) for image in images]
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/lib/python3.11/site-packages/transformers/models/blip/image_processing_blip.py", line 138, in resize
    return resize(image, size=output_size, resample=resample, data_format=data_format, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/lib/python3.11/site-packages/transformers/image_transforms.py", line 275, in resize
    image = to_pil_image(image)
            ^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/lib/python3.11/site-packages/transformers/image_transforms.py", line 163, in to_pil_image
    return PIL.Image.fromarray(image)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "${base_dir}/ComfyUI/lib/python3.11/site-packages/PIL/Image.py", line 3092, in fromarray
    raise TypeError(msg) from e
    TypeError: Cannot handle this data type: (1, 1, 512, 3), |u1
commented

the imageURL to string works, it's just the image2text node causing me problems