kijai
TypeError: 'NoneType' object is not subscriptable
运行报错： TypeError: 'NoneType' object is not subscriptable
运行环境： os: windows11 python: 3.11.9 PyTorch版本: 2.9.0+cu128 CUDA版本: 12.8
Total timesteps: tensor([999.7998, 937.5000, 833.3333, 625.0000], device='cuda:0') Using timesteps: tensor([999.7998, 937.5000, 833.3333, 625.0000], device='cuda:0') Using sigmas: tensor([0.9998, 0.9375, 0.8333, 0.6250, 0.0000], device='cuda:0')
sigmas: tensor([0.9998, 0.9375, 0.8333, 0.6250, 0.0000], device='cuda:0') Swapping 19 transformer blocks Initializing block swap: 100%|██████████████████████████████████████████████████████████████████████| 40/40 [00:03<00:00, 10.56it/s]
Block swap memory summary: Transformer blocks on cpu: 9795.33MB Transformer blocks on cuda:0: 10826.42MB Total memory used by transformer blocks: 20621.76MB Non-blocking memory transfer: False
Multitalk mode: infinitetalk Error during sampling: 'NoneType' object is not subscriptable !!! Exception during processing !!! 'NoneType' object is not subscriptable Traceback (most recent call last): File "D:\softwares\ai\comfyui\comfyui_github_py311\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 "D:\softwares\ai\comfyui\comfyui_github_py311\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 "D:\softwares\ai\comfyui\comfyui_github_py311\ComfyUI\execution.py", line 298, in _async_map_node_over_list await process_inputs(input_dict, i) File "D:\softwares\ai\comfyui\comfyui_github_py311\ComfyUI\execution.py", line 286, in process_inputs result = f(**inputs) ^^^^^^^^^^^ File "D:\softwares\ai\comfyui\comfyui_github_py311\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\nodes_sampler.py", line 3071, in process raise e File "D:\softwares\ai\comfyui\comfyui_github_py311\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper\nodes_sampler.py", line 2093, in process if len(multitalk_embeds['audio_features'])==2 and (multitalk_embeds['ref_target_masks'] is None): ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^ TypeError: 'NoneType' object is not subscriptable
Prompt executed in 8.98 seconds
Its been a few, but think that might be missing mask when multiple persons, if i remember correctly, Do you have mask in the multitalk node that has a mask input ( one mask per speaker as input at ref_target_masks at the Multi/Infinite Talk Wav2Vec2 Embeds node )
See here also https://github.com/kijai/ComfyUI-WanVideoWrapper/issues/1194
