ObjectDetectorFL2（Florence2) 'NoneType' object is not callable

[uiueux]

ComfyUI_LayerStyle_Advance and ComfyUI are currently the latest. ps: I have noticed the adaptation of ComfyUI_LayerStyle_Advance to transforms, but my report seems to show that it has not been completely solved. Plz take time to check it.
Thanks
`

ComfyUI Error Report

Error Details

• Node ID: 1
• Node Type: LayerMask: ObjectDetectorFL2
• Exception Type: TypeError
• Exception Message: 'NoneType' object is not callable

Stack Trace

  File "D:\comfyui\3\execution.py", line 516, in execute
    output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "D:\comfyui\3\execution.py", line 330, in get_output_data
    return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "D:\comfyui\3\execution.py", line 304, in _async_map_node_over_list
    await process_inputs(input_dict, i)

  File "D:\comfyui\3\execution.py", line 292, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^

  File "D:\comfyui\3\custom_nodes\ComfyUI_LayerStyle_Advance\py\object_detector.py", line 113, in object_detector_fl2
    results, _ = process_image(model, processor, img, task,
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "D:\comfyui\3\custom_nodes\ComfyUI_LayerStyle_Advance\py\florence2_ultra.py", line 280, in process_image
    results = run_example(model, processor, task_prompt, image, max_new_tokens, num_beams, do_sample, text_input)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "D:\comfyui\3\custom_nodes\ComfyUI_LayerStyle_Advance\py\florence2_ultra.py", line 214, in run_example
    inputs = processor(text=prompt, images=image, return_tensors="pt").to(device)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

System Information

• ComfyUI Version: 0.6.0
• Arguments: D:\comfyui\3\main.py --listen --auto-launch --preview-method auto --disable-cuda-malloc
• OS: win32
• Python Version: 3.11.6 | packaged by conda-forge | (main, Oct 3 2023, 10:29:11) [MSC v.1935 64 bit (AMD64)]
• Embedded Python: false
• PyTorch Version: 2.7.0+cu128

Devices

• Name: cuda:0 NVIDIA GeForce RTX 3060 : cudaMallocAsync

torch_dtype is deprecated! Use dtype instead!

😺dzNodes: LayerStyle -> Error loading model or tokenizer: 'Florence2ForConditionalGeneration' object has no attribute '_supports_sdpa'

!!! Exception during processing !!! 'NoneType' object is not callable
Traceback (most recent call last):
File "D:\comfyui\3\execution.py", line 516, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\comfyui\3\execution.py", line 330, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\comfyui\3\execution.py", line 304, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "D:\comfyui\3\execution.py", line 292, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "D:\comfyui\3\custom_nodes\ComfyUI_LayerStyle_Advance\py\object_detector.py", line 113, in object_detector_fl2
results, _ = process_image(model, processor, img, task,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\comfyui\3\custom_nodes\ComfyUI_LayerStyle_Advance\py\florence2_ultra.py", line 280, in process_image
results = run_example(model, processor, task_prompt, image, max_new_tokens, num_beams, do_sample, text_input)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\comfyui\3\custom_nodes\ComfyUI_LayerStyle_Advance\py\florence2_ultra.py", line 214, in run_example
inputs = processor(text=prompt, images=image, return_tensors="pt").to(device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: 'NoneType' object is not callable`

[gothxx]

+1, meet the same problem

[jiyilin]

将transformers 回退到 4.41.2 可以临时修复

[hben35096]

The same issue can be resolved by recloning the repository (using the model.safetensors file), which works with transformers ≤ 4.53.3. Fortunately, it can now be fixed with a patch, allowing it to work even with transformers 5.0.0.
#139