1038lab/ComfyUI-QwenTTS
1
0
Fork 0
mirror of https://github.com/1038lab/ComfyUI-QwenTTS.git synced 2026-11-04 23:37:45 +00:00
Code Issues 21 Projects Packages Wiki Activity

[GH-ISSUE #3] KeyError: default on a clean install (Mac OS) #2

New issue
Closed
opened 2026-10-30 21:03:18 +00:00 by bsakaguchi · 1 comment
bsakaguchi commented 2026-10-30 21:03:18 +00:00
Owner
Copy link

Originally created by @jimdogx on GitHub (Jan 24, 2026).
Original GitHub issue: https://github.com/1038lab/ComfyUI-QwenTTS/issues/3

I installed ComfyUI-QwenTTS by cloning the git repo in to the custom nodes directory. I then did a pip install -r requirements.txt (all dependencies were satisfied). However, trying any of the three node groups gives me an error:

ComfyUI Error Report

Error Details

  • Node ID: 46
  • Node Type: AILab_Qwen3TTSVoiceClone
  • Exception Type: KeyError
  • Exception Message: 'default'

Stack Trace

  File "/Volumes/External/ComfyUI/execution.py", line 518, 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 "/Volumes/External/ComfyUI/execution.py", line 329, 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 "/Volumes/External/ComfyUI/execution.py", line 303, in _async_map_node_over_list
    await process_inputs(input_dict, i)

  File "/Volumes/External/ComfyUI/execution.py", line 291, in process_inputs
    result = f(**inputs)

  File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/AILab_QwenTTS.py", line 733, in generate
    return _voice_clone_generate(

  File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/AILab_QwenTTS.py", line 508, in _voice_clone_generate
    model = _load_model("Base", model_size, device, precision)

  File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/AILab_QwenTTS.py", line 319, in _load_model
    raise e

  File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/AILab_QwenTTS.py", line 311, in _load_model
    model = Qwen3TTSModel.from_pretrained(source, **kwargs)

  File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/inference/qwen3_tts_model.py", line 112, in from_pretrained
    model = AutoModel.from_pretrained(pretrained_model_name_or_path, **kwargs)

  File "/Volumes/External/ComfyUI/venv/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 372, in from_pretrained
    return model_class.from_pretrained(

  File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/core/models/modeling_qwen3_tts.py", line 1872, in from_pretrained
    model = super().from_pretrained(

  File "/Volumes/External/ComfyUI/venv/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4032, in from_pretrained
    model = cls(config, *model_args, **model_kwargs)

  File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/core/models/modeling_qwen3_tts.py", line 1821, in __init__
    self.talker = Qwen3TTSTalkerForConditionalGeneration(self.config.talker_config)

  File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/core/models/modeling_qwen3_tts.py", line 1574, in __init__
    self.model = Qwen3TTSTalkerModel(config)

  File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/core/models/modeling_qwen3_tts.py", line 1440, in __init__
    self.rotary_emb = Qwen3TTSTalkerRotaryEmbedding(config)

  File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/core/models/modeling_qwen3_tts.py", line 539, in __init__
    self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]

System Information

  • ComfyUI Version: 0.10.0
  • Arguments: main.py
  • OS: darwin
  • Python Version: 3.10.18 (main, Jun 3 2025, 18:23:41) [Clang 17.0.0 (clang-1700.0.13.3)]
  • Embedded Python: false
  • PyTorch Version: 2.10.0

Devices

  • Name: mps
    • Type: mps
    • VRAM Total: 25769803776
    • VRAM Free: 10485432320
    • Torch VRAM Total: 25769803776
    • Torch VRAM Free: 10485432320
Originally created by @jimdogx on GitHub (Jan 24, 2026). Original GitHub issue: https://github.com/1038lab/ComfyUI-QwenTTS/issues/3 I installed ComfyUI-QwenTTS by cloning the git repo in to the custom nodes directory. I then did a pip install -r requirements.txt (all dependencies were satisfied). However, trying any of the three node groups gives me an error: # ComfyUI Error Report ## Error Details - **Node ID:** 46 - **Node Type:** AILab_Qwen3TTSVoiceClone - **Exception Type:** KeyError - **Exception Message:** 'default' ## Stack Trace ``` File "/Volumes/External/ComfyUI/execution.py", line 518, 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 "/Volumes/External/ComfyUI/execution.py", line 329, 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 "/Volumes/External/ComfyUI/execution.py", line 303, in _async_map_node_over_list await process_inputs(input_dict, i) File "/Volumes/External/ComfyUI/execution.py", line 291, in process_inputs result = f(**inputs) File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/AILab_QwenTTS.py", line 733, in generate return _voice_clone_generate( File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/AILab_QwenTTS.py", line 508, in _voice_clone_generate model = _load_model("Base", model_size, device, precision) File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/AILab_QwenTTS.py", line 319, in _load_model raise e File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/AILab_QwenTTS.py", line 311, in _load_model model = Qwen3TTSModel.from_pretrained(source, **kwargs) File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/inference/qwen3_tts_model.py", line 112, in from_pretrained model = AutoModel.from_pretrained(pretrained_model_name_or_path, **kwargs) File "/Volumes/External/ComfyUI/venv/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 372, in from_pretrained return model_class.from_pretrained( File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/core/models/modeling_qwen3_tts.py", line 1872, in from_pretrained model = super().from_pretrained( File "/Volumes/External/ComfyUI/venv/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4032, in from_pretrained model = cls(config, *model_args, **model_kwargs) File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/core/models/modeling_qwen3_tts.py", line 1821, in __init__ self.talker = Qwen3TTSTalkerForConditionalGeneration(self.config.talker_config) File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/core/models/modeling_qwen3_tts.py", line 1574, in __init__ self.model = Qwen3TTSTalkerModel(config) File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/core/models/modeling_qwen3_tts.py", line 1440, in __init__ self.rotary_emb = Qwen3TTSTalkerRotaryEmbedding(config) File "/Volumes/External/ComfyUI/custom_nodes/ComfyUI-QwenTTS/qwen_tts/core/models/modeling_qwen3_tts.py", line 539, in __init__ self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type] ``` ## System Information - **ComfyUI Version:** 0.10.0 - **Arguments:** main.py - **OS:** darwin - **Python Version:** 3.10.18 (main, Jun 3 2025, 18:23:41) [Clang 17.0.0 (clang-1700.0.13.3)] - **Embedded Python:** false - **PyTorch Version:** 2.10.0 ## Devices - **Name:** mps - **Type:** mps - **VRAM Total:** 25769803776 - **VRAM Free:** 10485432320 - **Torch VRAM Total:** 25769803776 - **Torch VRAM Free:** 10485432320
bsakaguchi commented 2026-10-30 21:03:19 +00:00
Author
Owner
Copy link

@jimdogx commented on GitHub (Jan 25, 2026):

I guess my "clean install" wasn't as clean as I thought. I did a proper clean install and it is working now.

<!-- gh-comment-id:3795817348 --> @jimdogx commented on GitHub (Jan 25, 2026): I guess my "clean install" wasn't as clean as I thought. I did a proper clean install and it is working now.
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
1038lab/ComfyUI-QwenTTS#2
No description provided.