> ## 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.

# LumaImageNode2 - ComfyUI Built-in Node Documentation

> Complete documentation for the LumaImageNode2 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/LumaImageNode2/en.md)

## Overview

This node generates images from text descriptions using the Luma UNI-1 model. It takes a text prompt and optional settings like aspect ratio and style, then sends the request to the Luma API to create an image.

## Inputs

| Parameter | Data Type | Required | Range                        | Description                                                                                                  |
| --------- | --------- | -------- | ---------------------------- | ------------------------------------------------------------------------------------------------------------ |
| `prompt`  | STRING    | Yes      | 1–6000 characters            | Text description of the desired image.                                                                       |
| `model`   | COMBO     | Yes      | `"uni-1"`<br />`"uni-1-max"` | Model to use for generation. Selecting a model reveals additional settings for that model.                   |
| `seed`    | INT       | Yes      | 0 to 2147483647              | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0) |

### Model-specific Inputs

When `"uni-1"` or `"uni-1-max"` is selected for the `model` parameter, the following inputs become available:

| Parameter      | Data Type | Required | Range                                                                                                                           | Description                                                                                      |
| -------------- | --------- | -------- | ------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ |
| `aspect_ratio` | COMBO     | Yes      | `"auto"`<br />`"3:1"`<br />`"2:1"`<br />`"16:9"`<br />`"3:2"`<br />`"1:1"`<br />`"2:3"`<br />`"9:16"`<br />`"1:2"`<br />`"1:3"` | Output image aspect ratio. `"auto"` lets the model pick based on the prompt. (default: `"auto"`) |
| `style`        | COMBO     | Yes      | `"auto"`<br />`"manga"`                                                                                                         | The visual style for the generated image. (default: `"auto"`)                                    |
| `web_search`   | BOOLEAN   | Yes      | True / False                                                                                                                    | Whether to allow the model to search the web for additional context. (default: False)            |
| `image_ref`    | IMAGE     | No       | Up to 9 images                                                                                                                  | Reference images to guide the generation.                                                        |

**Note on `style` and `aspect_ratio` constraints:** If `style` is set to `"manga"`, the `aspect_ratio` must be either `"auto"` or one of the following portrait ratios: `"2:3"`, `"9:16"`, `"1:2"`, `"1:3"`. Using a landscape or square ratio with `"manga"` style will cause an error.

## Outputs

| Output Name | Data Type | Description                      |
| ----------- | --------- | -------------------------------- |
| `image`     | IMAGE     | The generated image as a tensor. |

***

**Source fingerprint (SHA-256):** `cd680f8b9e6bcf5fa415aa2d9ec3126bf8873d14bd6f4cd127491cfa242e5548`