Yusu MiniMax H3 Unified unsupported operand type(s) for //: 'str' and 'int' is:issue

### Custom Node Testing

- [ ] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

unsupported operand type(s) for //: 'str' and 'int' is:issue# ComfyUI Error Report
## Error Details
- **Node ID:** 212
- **Node Type:** Yusu MiniMax H3 Unified
- **Exception Type:** TypeError
- **Exception Message:** unsupported operand type(s) for //: 'str' and 'int'
## Stack Trace
```
File "/workspace/ComfyUI/execution.py", line 1805, 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 "/workspace/ComfyUI/execution.py", line 576, 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 "/workspace/ComfyUI/execution.py", line 550, in _async_map_node_over_list
await process_inputs(input_dict, i)

File "/workspace/ComfyUI/execution.py", line 538, in process_inputs
result = f(**inputs)

File "/workspace/ComfyUI/comfy_api/internal/__init__.py", line 149, in wrapped_func
return method(locked_class, **inputs)

File "/workspace/ComfyUI/comfy_api/latest/_io.py", line 2046, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)

File "/workspace/ComfyUI/custom_nodes/ComfyUI-MiniMaxH3-Unified/nodes.py", line 488, in execute
output = MiniMaxH3ReferenceToVideo.execute(

File "/workspace/ComfyUI/comfy_extras/nodes_minimax_h3.py", line 290, in execute
latent, frame_count = _empty_av_latent(width, height, length)

File "/workspace/ComfyUI/comfy_extras/nodes_minimax_h3.py", line 85, in _empty_av_latent
video = torch.zeros([batch_size, 24, latent_t, height // 16, width // 16],

```
## Logs
```
[object Object]
```
## 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)

### Actual Behavior

# ComfyUI Error Report
## Error Details
- **Node ID:** 212
- **Node Type:** Yusu MiniMax H3 Unified
- **Exception Type:** TypeError
- **Exception Message:** unsupported operand type(s) for //: 'str' and 'int'
## Stack Trace
```
File "/workspace/ComfyUI/execution.py", line 1805, 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 "/workspace/ComfyUI/execution.py", line 576, 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 "/workspace/ComfyUI/execution.py", line 550, in _async_map_node_over_list
await process_inputs(input_dict, i)

File "/workspace/ComfyUI/execution.py", line 538, in process_inputs
result = f(**inputs)

File "/workspace/ComfyUI/comfy_api/internal/__init__.py", line 149, in wrapped_func
return method(locked_class, **inputs)

File "/workspace/ComfyUI/comfy_api/latest/_io.py", line 2046, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)

File "/workspace/ComfyUI/custom_nodes/ComfyUI-MiniMaxH3-Unified/nodes.py", line 488, in execute
output = MiniMaxH3ReferenceToVideo.execute(

File "/workspace/ComfyUI/comfy_extras/nodes_minimax_h3.py", line 290, in execute
latent, frame_count = _empty_av_latent(width, height, length)

File "/workspace/ComfyUI/comfy_extras/nodes_minimax_h3.py", line 85, in _empty_av_latent
video = torch.zeros([batch_size, 24, latent_t, height // 16, width // 16],

```
## Logs
```
[object Object]
```
## 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)

### Steps to Reproduce

1

### Debug Logs

```powershell
1
```

### Other

_No response_

Start by tracing the Yusu MiniMax H3 Unified call in custom_nodes/ComfyUI-MiniMaxH3-Unified/nodes.py:488 into comfy_extras/nodes_minimax_h3.py, especially _empty_av_latent at line 85. Reproduce with a valid workflow and inspect the width, height, and length values reaching the torch.zeros shape; done means the node no longer raises this TypeError and its workflow runs successfully.

Written by the indexing model from the issue text.