LTXVAudioVAEDecode too many values to unpack (expected 4)

### 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

LTXVAudioVAEDecode too many values to unpack (expected 4)

model_na.Itx-2-spatial-upscaler-x2-1.0.safetensors
提示执行失败
Prompt outputs failed validation:
LatentUpscaleModelLoader:
-Value not in list: model_name: 'tx-2-spatial-upscaler-x2-1.0.safetensors' not in [

### Actual Behavior

### Steps to Reproduce

谢谢

### Debug Logs

```powershell
File "D:\(03)comdyui\ComfyUI\execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "D:\(03)comdyui\ComfyUI\execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "D:\(03)comdyui\ComfyUI\comfy_api\internal\__init__.py", line 149, in wrapped_func
return method(locked_class, **inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\(03)comdyui\ComfyUI\comfy_api\latest\_io.py", line 1582, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\(03)comdyui\ComfyUI\comfy_extras\nodes_lt_audio.py", line 87, in execute
audio = audio_vae.decode(audio_latent).to(audio_latent.device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\(03)comdyui\ComfyUI\comfy\ldm\lightricks\vae\audio_vae.py", line 215, in decode
latents = self.normalizer.denormalize(latents)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\(03)comdyui\ComfyUI\comfy\ldm\lightricks\vae\audio_vae.py", line 87, in denormalize
patched, _ = self.patchifier.patchify(latents)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\(03)comdyui\ComfyUI\comfy\ldm\lightricks\symmetric_patchifier.py", line 167, in patchify
b, _, t, _ = audio_latents.shape
^^^^^^^^^^
ValueError: too many values to unpack (expected 4)
```

### Other

_No response_