[ERROR] tuplet index out of range

[Gohloum]

Hello,

I am getting this error when I try and run the node. I have installed requirements and everything seems to be installed correctly. I also performed full updates and stopped/started just to make sure. Here is the error I am getting:

tuple index out of range

ComfyUI Error Report

Error Details

• Node Type: Florence2Run
• Exception Type: IndexError
• Exception Message: tuple index out of range

Stack Trace

  File "/Volumes/OWC Envoy Pro FX/_AI Tools/ComfyUI/execution.py", line 323, 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 "/Volumes/OWC Envoy Pro FX/_AI Tools/ComfyUI/execution.py", line 198, 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 "/Volumes/OWC Envoy Pro FX/_AI Tools/ComfyUI/execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)

  File "/Volumes/OWC Envoy Pro FX/_AI Tools/ComfyUI/execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/Volumes/OWC Envoy Pro FX/_AI Tools/ComfyUI/custom_nodes/ComfyUI-Florence2/nodes.py", line 296, in encode
    generated_ids = model.generate(
                    ^^^^^^^^^^^^^^^

  File "/Users/tj/.cache/huggingface/modules/transformers_modules/Florence-2-base/modeling_florence2.py", line 2796, in generate
    return self.language_model.generate(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/Users/tj/miniconda3/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^

  File "/Users/tj/miniconda3/lib/python3.12/site-packages/transformers/generation/utils.py", line 1828, in generate
    self._prepare_special_tokens(generation_config, kwargs_has_attention_mask, device=device)

  File "/Users/tj/miniconda3/lib/python3.12/site-packages/transformers/generation/utils.py", line 1677, in _prepare_special_tokens
    and isin_mps_friendly(elements=eos_token_tensor, test_elements=pad_token_tensor).any()
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/Users/tj/miniconda3/lib/python3.12/site-packages/transformers/pytorch_utils.py", line 325, in isin_mps_friendly
    return elements.tile(test_elements.shape[0], 1).eq(test_elements.unsqueeze(1)).sum(dim=0).bool().squeeze()
                         ~~~~~~~~~~~~~~~~~~~^^^

System Information

• ComfyUI Version: v0.2.5-3-g65a8659
• Arguments: main.py
• OS: posix
• Python Version: 3.12.4 | packaged by Anaconda, Inc. | (main, Jun 18 2024, 10:07:17) [Clang 14.0.6 ]
• Embedded Python: false
• PyTorch Version: 2.3.1

Devices

• Name: mps
  • Type: mps
  • VRAM Total: 68719476736
  • VRAM Free: 37896896512
  • Torch VRAM Total: 68719476736
  • Torch VRAM Free: 37896896512

[SwordFaith]

Got same problem

[SwordFaith]

It's due to Florence2 model can't handle mps backend. Modify model device to cuda or cpu setting works for me.