UltralyticsDetectorProvider - KeyError - "filename 'storages' not found"

[cushycrux]

ComfyUI Error Report

Error Details

• Node ID: 1133
• Node Type: UltralyticsDetectorProvider
• Exception Type: KeyError
• Exception Message: "filename 'storages' not found"

Stack Trace

  File "V:\ComfyUI_windows_portable_26\ComfyUI\execution.py", line 510, 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, hidden_inputs=hidden_inputs)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "V:\ComfyUI_windows_portable_26\ComfyUI\execution.py", line 324, 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, hidden_inputs=hidden_inputs)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "V:\ComfyUI_windows_portable_26\ComfyUI\execution.py", line 298, in _async_map_node_over_list
    await process_inputs(input_dict, i)

  File "V:\ComfyUI_windows_portable_26\ComfyUI\execution.py", line 286, in process_inputs
    result = f(**inputs)

  File "V:\ComfyUI_windows_portable_26\ComfyUI\custom_nodes\ComfyUI-Impact-Subpack\modules\subpack_nodes.py", line 55, in doit
    model = subcore.load_yolo(model_path)

  File "V:\ComfyUI_windows_portable_26\ComfyUI\custom_nodes\ComfyUI-Impact-Subpack\modules\subcore.py", line 317, in load_yolo
    return YOLO(model_path)

  File "V:\ComfyUI_windows_portable_26\python_embeded\Lib\site-packages\ultralytics\models\yolo\model.py", line 76, in __init__
    super().__init__(model=model, task=task, verbose=verbose)
    ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "V:\ComfyUI_windows_portable_26\python_embeded\Lib\site-packages\ultralytics\engine\model.py", line 144, in __init__
    self._load(model, task=task)
    ~~~~~~~~~~^^^^^^^^^^^^^^^^^^

  File "V:\ComfyUI_windows_portable_26\python_embeded\Lib\site-packages\ultralytics\engine\model.py", line 283, in _load
    self.model, self.ckpt = load_checkpoint(weights)
                            ~~~~~~~~~~~~~~~^^^^^^^^^

  File "V:\ComfyUI_windows_portable_26\python_embeded\Lib\site-packages\ultralytics\nn\tasks.py", line 1461, in load_checkpoint
    ckpt, weight = torch_safe_load(weight)  # load ckpt
                   ~~~~~~~~~~~~~~~^^^^^^^^

  File "V:\ComfyUI_windows_portable_26\python_embeded\Lib\site-packages\ultralytics\nn\tasks.py", line 1409, in torch_safe_load
    ckpt = torch_load(file, map_location="cpu")

  File "V:\ComfyUI_windows_portable_26\python_embeded\Lib\site-packages\ultralytics\utils\patches.py", line 116, in torch_load
    return torch.load(*args, **kwargs)
           ~~~~~~~~~~^^^^^^^^^^^^^^^^^

  File "V:\ComfyUI_windows_portable_26\ComfyUI\custom_nodes\ComfyUI-Impact-Subpack\modules\subcore.py", line 216, in torch_wrapper
    return orig_torch_load(*args, **load_kwargs)

  File "V:\ComfyUI_windows_portable_26\python_embeded\Lib\site-packages\torch\serialization.py", line 1554, in load
    return _legacy_load(
        opened_file, map_location, pickle_module, **pickle_load_args
    )

  File "V:\ComfyUI_windows_portable_26\python_embeded\Lib\site-packages\torch\serialization.py", line 1792, in _legacy_load
    return legacy_load(f)

  File "V:\ComfyUI_windows_portable_26\python_embeded\Lib\site-packages\torch\serialization.py", line 1663, in legacy_load
    tar.extract("storages", path=tmpdir)
    ~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^

  File "tarfile.py", line 2413, in extract

  File "tarfile.py", line 2427, in _get_extract_tarinfo

  File "tarfile.py", line 2061, in getmember

System Information

• ComfyUI Version: 0.3.75
• Arguments: ComfyUI\main.py --fast fp16_accumulation
• OS: nt
• Python Version: 3.13.9 (tags/v3.13.9:8183fa5, Oct 14 2025, 14:09:13) [MSC v.1944 64 bit (AMD64)]
• Embedded Python: true
• PyTorch Version: 2.9.1+cu130

Devices

• Name: cuda:0 NVIDIA GeForce RTX 5070 Ti : cudaMallocAsync
  • Type: cuda
  • VRAM Total: 17094475776
  • VRAM Free: 15645802496
  • Torch VRAM Total: 0
  • Torch VRAM Free: 0

Logs

2025-11-30T12:55:58.212805 - ComfyUI frontend version: 1.32.9
2025-11-30T12:55:58.213722 - [Prompt Server] web root: V:\ComfyUI_windows_portable_26\python_embeded\Lib\site-packages\comfyui_frontend_package\static
2025-11-30T12:55:58.645464 - Total VRAM 16303 MB, total RAM 65112 MB
2025-11-30T12:55:58.645599 - pytorch version: 2.9.1+cu130
2025-11-30T12:55:58.647051 - Enabled fp16 accumulation.
2025-11-30T12:55:58.647193 - Set vram state to: NORMAL_VRAM
2025-11-30T12:55:58.647556 - Device: cuda:0 NVIDIA GeForce RTX 5070 Ti : cudaMallocAsync
2025-11-30T12:55:58.656527 - Using async weight offloading with 2 streams
...

Help Please?

[cushycrux]

After more trying:

The BBOX detector is working.
Put all models into the whitelist. Can see they got loaded at ComfyUI boot-up. Still not working with SEGM.