The VAEDecodeHunyuan3D node converts latent representations into 3D voxel data using a VAE decoder. It processes the latent samples through the VAE model with configurable chunking and resolution settings to generate volumetric data suitable for 3D applications.

## Inputs

| Parameter | Description | Data Type | Required | Range |
| --- | --- | --- | --- | --- |
| `samples` | The latent representation to be decoded into 3D voxel data | LATENT | Yes | - |
| `vae` | The VAE model used for decoding the latent samples | VAE | Yes | - |
| `num_chunks` | The number of chunks to split the processing into for memory management (default: 8000) | INT | Yes | 1000-500000 |
| `octree_resolution` | The resolution of the octree structure used for 3D voxel generation (default: 256) | INT | Yes | 16-512 |

## Outputs

| Output Name | Description | Data Type |
| --- | --- | --- |
| `voxels` | The generated 3D voxel data from the decoded latent representation | VOXEL |

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEDecodeHunyuan3D/en.md)

---
**Source fingerprint (SHA-256):** `04818af007257ec0c73873dba703465960e7adae8a9b22649e118116c388da56`