ComfyUI Cloud crashes with ServiceError while using video_wan_vace_14b_v2 model

### Custom Node Testing

- [x] 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

When running a workflow with the video_wan_vace_14b_v2 model, the process should finish video generation without any ServiceError or server crash.

### Actual Behavior

ComfyUI crashed with a ServiceError saying “RIP to the server your workflow was running on” while using the video_wan_vace_14b_v2 model. The workflow stopped without producing output.

### Steps to Reproduce

Open ComfyU CloudI.

Load a workflow using the video_wan_vace_14b_v2 model.

Run the workflow.

Observe that the workflow stops and displays the ServiceError message.

Note: The issue occurs consistently when using this specific model.

### Debug Logs

```powershell
# ComfyUI Error Report
## Error Details
- **Node ID:** N/A
- **Node Type:** N/A
- **Exception Type:** ServiceError
- **Exception Message:** RIP to the server your workflow was running on.
## Stack Trace

No stack trace available

## System Information
- **ComfyUI Version:**
- **Arguments:**
- **OS:**
- **Python Version:**
- **Embedded Python:** false
- **PyTorch Version:**
## Devices

## 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)
```

### Other

_No response_