> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-feat-openapi-i18n.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# ImageOnlyCheckpointLoader - ComfyUI Built-in Node Documentation

> Complete documentation for the ImageOnlyCheckpointLoader node in ComfyUI. Learn its inputs, outputs, parameters and usage.

This node will detect models located in the `ComfyUI/models/checkpoints` folder, and it will also read models from additional paths configured in the extra\_model\_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder.

This node specializes in loading checkpoints specifically for image-based models within video generation workflows. It efficiently retrieves and configures the necessary components from a given checkpoint, focusing on image-related aspects of the model.

## Inputs

| Field       | Description                                                                                                                              | Data Type      |
| ----------- | ---------------------------------------------------------------------------------------------------------------------------------------- | -------------- |
| `ckpt_name` | Specifies the name of the checkpoint to load, crucial for identifying and retrieving the correct checkpoint file from a predefined list. | COMBO\[STRING] |

## Outputs

| Field         | Description                                                                                                          | Data Type     |
| ------------- | -------------------------------------------------------------------------------------------------------------------- | ------------- |
| `model`       | Returns the main model loaded from the checkpoint, configured for image processing within video generation contexts. | MODEL         |
| `clip_vision` | Provides the CLIP vision component from the checkpoint, tailored for image understanding and feature extraction.     | `CLIP_VISION` |
| `vae`         | Delivers the Variational Autoencoder (VAE) component, essential for image manipulation and generation tasks.         | VAE           |

> 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/ImageOnlyCheckpointLoader/en.md)