Qwen Image VAE + Latent Composite Masked Bug

### 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

Using any other VAE works fine.

### Actual Behavior

### Steps to Reproduce

### Debug Logs

```powershell
got prompt
Using pytorch attention in VAE
Using pytorch attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Requested to load WanVAE
loaded completely 10460.561256408691 242.02829551696777 True
Prompt executed in 1.65 seconds
```

### Other

_No response_