Reported an error

[maiqunshan]

ComfyUI Error Report

Error Details

• Node ID: 63
• Node Type: JoyCaption2_simple
• Exception Type: TypeError
• Exception Message: object of type 'NoneType' has no len()

Stack Trace

  File "C:\ComfyUI_MAI\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 "C:\ComfyUI_MAI\ComfyUI\execution.py", line 228, in get_output_data
    output = merge_result_data(results, obj)

  File "C:\ComfyUI_MAI\ComfyUI\execution.py", line 175, in merge_result_data
    output_is_list = [False] * len(results[0])

System Information

• ComfyUI Version: v0.3.5-8-gbf2650a
• Arguments: ComfyUI\main.py --windows-standalone-build
• OS: nt
• Python Version: 3.10.9 (tags/v3.10.9:1dd9be6, Dec 6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
• Embedded Python: true
• PyTorch Version: 2.4.0+cu118

Devices

I have re-downloaded the model, but the error still occurs

[maiqunshan]

After updating comfyui, an error was reported.

[maiqunshan]

got prompt
comfy_model_dir: C:\ComfyUI_MAI\ComfyUI\models\LLM
Start to load existing model on cuda:0
Free VRAM: 14.74 GB
Free VRAM is less than 20GB when loading 'bf16' model. Performing VRAM cleanup.
Start to load existing VLM
Loading in bfloat16
Loading CLIP
Error loading models: Descriptors cannot be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:

1. Downgrade the protobuf package to 3.20.x or lower.
2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).

More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates
Error loading model: local variable 'clip_processor' referenced before assignment
!!! Exception during processing !!! object of type 'NoneType' has no len()
Traceback (most recent call last):
File "C:\ComfyUI_MAI\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 "C:\ComfyUI_MAI\ComfyUI\execution.py", line 228, in get_output_data
output = merge_result_data(results, obj)
File "C:\ComfyUI_MAI\ComfyUI\execution.py", line 175, in merge_result_data
output_is_list = [False] * len(results[0])
TypeError: object of type 'NoneType' has no len()

Prompt executed in 0.48 seconds

[maiqunshan]

got prompt
comfy_model_dir: C:\ComfyUI_MAI\ComfyUI\models\LLM
Start to load existing model on cuda:0
Free VRAM: 14.74 GB
Start to load existing VLM
Loading in NF4
Loading CLIP
Error loading models: Couldn't build proto file into descriptor pool: duplicate file name sentencepiece_model.proto
Error loading model: local variable 'clip_processor' referenced before assignment
!!! Exception during processing !!! object of type 'NoneType' has no len()
Traceback (most recent call last):
File "C:\ComfyUI_MAI\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 "C:\ComfyUI_MAI\ComfyUI\execution.py", line 228, in get_output_data
output = merge_result_data(results, obj)
File "C:\ComfyUI_MAI\ComfyUI\execution.py", line 175, in merge_result_data
output_is_list = [False] * len(results[0])
TypeError: object of type 'NoneType' has no len()

Prompt executed in 0.06 seconds

[smuelpeng]

same error on ComfyUI V0.20.0 and V0.36.0

[Kallamamran]

Same error :(

ComfyUI (Embedded): v0.3.7
ComfyUI_frontend: v1.4.13
Python Version: 3.11.9
Pytorch Version: 2.5.1+cu124

Prompt executed in 1.32 seconds
got prompt
comfy_model_dir: C:\ComfyUI_windows_portable\ComfyUI\models\LLM
Start to load existing model on cuda:0
Free VRAM: 14.62 GB
Free VRAM is less than 20GB when loading 'bf16' model. Performing VRAM cleanup.
Start to load existing VLM
Loading in bfloat16
Loading CLIP
Loading tokenizer
Error loading models: Incorrect path_or_model_id: 'C:\ComfyUI_windows_portable\ComfyUI\models\Joy_caption\cgrkzexw-599808\text_model'. Please provide either the path to a local folder or the repo_id of a model on the Hub.
Error loading model: cannot access local variable 'tokenizer' where it is not associated with a value
!!! Exception during processing !!! object of type 'NoneType' has no len()
Traceback (most recent call last):
  File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 324, 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 "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 229, in get_output_data
    output = merge_result_data(results, obj)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 176, in merge_result_data
    output_is_list = [False] * len(results[0])
                               ^^^^^^^^^^^^^^^
TypeError: object of type 'NoneType' has no len()

[EricRollei]

I have the same error. I think it's related to the version of transformers. Requirements specify a range transformers>=4.43.2,<=4.45.1 but of course many other custom nodes may need a newer version like 4.47