The size of tensor a (75600) must match the size of tensor b (18000) at non-singleton dimension 1


## Additional Context
(Please add any additional context or steps to reproduce the error here)Sampling audio indices 288-369: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [03:49<00:00, 28.64s/it]2025-09-17T04:22:31.529418 -
2025-09-17T04:22:31.529545 - Audio embedding for subject 0 not long enough: 375, need 441, padding...2025-09-17T04:22:31.529677 -
2025-09-17T04:22:31.529796 - Padding length: 692025-09-17T04:22:31.529853 -
2025-09-17T04:22:36.974368 -
Sampling audio indices 360-441:   0%|                                                                                                                                                            | 0/8 [00:00<?, ?it/s]2025-09-17T04:22:37.017724 - Error during model prediction: The size of tensor a (75600) must match the size of tensor b (18000) at non-singleton dimension 1
2025-09-17T04:22:37.683142 - Error during sampling: The size of tensor a (75600) must match the size of tensor b (18000) at non-singleton dimension 1
2025-09-17T04:22:38.036555 - !!! Exception during processing !!! The size of tensor a (75600) must match the size of tensor b (18000) at non-singleton dimension 1
2025-09-17T04:22:38.061614 - Traceback (most recent call last):
  File "/workspace/ComfyUI/execution.py", line 496, 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 "/workspace/ComfyUI/execution.py", line 315, 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 "/workspace/ComfyUI/execution.py", line 289, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "/workspace/ComfyUI/execution.py", line 277, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^
  File "/workspace/ComfyUI/custom_nodes/ComfyUI-WanVideoWrapper/nodes.py", line 4185, in process
    raise e
  File "/workspace/ComfyUI/custom_nodes/ComfyUI-WanVideoWrapper/nodes.py", line 3795, in process
    noise_pred, self.cache_state = predict_with_cfg(
                                   ^^^^^^^^^^^^^^^^^
  File "/workspace/ComfyUI/custom_nodes/ComfyUI-WanVideoWrapper/nodes.py", line 2996, in predict_with_cfg
    raise e
  File "/workspace/ComfyUI/custom_nodes/ComfyUI-WanVideoWrapper/nodes.py", line 2885, in predict_with_cfg
    noise_pred_cond, cache_state_cond = transformer(
                                        ^^^^^^^^^^^^
  File "/workspace/ComfyUI/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1773, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/workspace/ComfyUI/venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1784, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/workspace/ComfyUI/custom_nodes/ComfyUI-WanVideoWrapper/wanvideo/modules/model.py", line 2443, in forward
    x.add_(dwpose_emb, alpha=unianim_data['strength'])
RuntimeError: The size of tensor a (75600) must match the size of tensor b (18000) at non-singleton dimension 1

2025-09-17T04:22:38.067616 - Prompt executed in 00:20:09
2025-09-17T04:22:38.389711 -
Sampling audio indices 360-441:   0%|                                                                                                                                                            | 0/8 [00:01<?, ?it/s]2025-09-17T04:22:38.389905 -

```
## Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.
```
Workflow too large. Please manually upload the workflow from local file system.
```

## Additional Context
(Please add any additional context or steps to reproduce the error here)