> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# HiDreamO1ReferenceImages - ComfyUI Built-in Node Documentation

> Complete documentation for the HiDreamO1ReferenceImages node in ComfyUI. Learn its inputs, outputs, parameters and usage.

> 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/HiDreamO1ReferenceImages/en.md)

## Overview

Attach reference images to both positive and negative conditioning. This node allows you to provide one or more reference images that will be used to guide the image generation process, either for editing based on an instruction or for subject-driven personalization.

## Inputs

| Parameter  | Data Type    | Required | Range          | Description                                                                                                                     |
| ---------- | ------------ | -------- | -------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| `positive` | CONDITIONING | Yes      | -              | The positive conditioning to attach reference images to.                                                                        |
| `negative` | CONDITIONING | Yes      | -              | The negative conditioning to attach reference images to.                                                                        |
| `images`   | IMAGE        | Yes      | 1 to 10 images | Reference images. 1 image enables instruction-based editing; 2-10 images enable multi-reference subject-driven personalization. |

**Note on `images` parameter:** This is an autogrow input that accepts between 1 and 10 images. The images are labeled `image_1` through `image_10`. You must provide at least 1 image. The number of images determines the mode of operation: a single image is used for edit instructions, while multiple images (2-10) are used for subject-driven personalization.

## Outputs

| Output Name | Data Type    | Description                                                   |
| ----------- | ------------ | ------------------------------------------------------------- |
| `positive`  | CONDITIONING | The positive conditioning with the reference images attached. |
| `negative`  | CONDITIONING | The negative conditioning with the reference images attached. |

***

**Source fingerprint (SHA-256):** `b14a8fc2acd44618370bd7e94758d469ff37530f2e19498a6c72ee3748559303`