The USOStyleReference node applies style reference patches to models using encoded image features from CLIP vision output. It creates a modified version of the input model by incorporating style information extracted from visual inputs, enabling style transfer or reference-based generation capabilities.

## Inputs

| Parameter | Description | Data Type | Required | Range |
| --- | --- | --- | --- | --- |
| `model` | The base model to apply the style reference patch to | MODEL | Yes | - |
| `model_patch` | The model patch containing style reference information | MODEL_PATCH | Yes | - |
| `clip_vision_output` | The encoded visual features extracted from CLIP vision processing | CLIP_VISION_OUTPUT | Yes | - |

## Outputs

| Output Name | Description | Data Type |
| --- | --- | --- |
| `model` | The modified model with applied style reference patches | MODEL |

> 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/USOStyleReference/en.md)

---
**Source fingerprint (SHA-256):** `fd800fb927677da29e148bfa1b287efed82895860ce4b0241d662579d2c07ff4`