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

# Images

> Configure AI image generation engines and connections.

<Info>Admin › Settings › Images</Info>

Configure AI image generation.

<Frame caption="Connect image generation engines and enable for agents">
  <img src="https://mintcdn.com/cloocus/Or1RjU_AzOVJRxuS/images/admin/settings-images.png?fit=max&auto=format&n=Or1RjU_AzOVJRxuS&q=85&s=f7479beaa243e886db5d724e34709e3a" alt="Images settings tab" width="2880" height="1800" data-path="images/admin/settings-images.png" />
</Frame>

***

## Enable Image Generation

| Setting                      | Description                     | Default  |
| ---------------------------- | ------------------------------- | -------- |
| **Image generation enabled** | Image generation feature ON/OFF | Disabled |

<Note>
  Image generation is only exposed to users when enabled as an agent capability.
</Note>

***

## Supported Engines

Add and manage image generation connections.

* Multiple engines can be configured simultaneously.

| Engine              | Strengths                                                        |
| ------------------- | ---------------------------------------------------------------- |
| **DALL-E (OpenAI)** | OpenAI image generation API                                      |
| **Azure OpenAI**    | Azure gpt-image-1.5, quality/format/background options supported |
| **Gemini**          | Google Gemini image generation (API Key auth)                    |
| **Vertex AI**       | Google Vertex AI image generation (OAuth2 token caching)         |

***

## Per-Engine Settings

<Tabs>
  <Tab title="OpenAI / DALL-E">
    | Setting          | Description                      |
    | ---------------- | -------------------------------- |
    | **API Base URL** | OpenAI API Endpoint              |
    | **API Key**      | API authentication key           |
    | **Model**        | e.g., `dall-e-3`                 |
    | **Image size**   | Default size (e.g., `1024x1024`) |
  </Tab>

  <Tab title="Azure OpenAI">
    | Setting           | Description           | Options                         |
    | ----------------- | --------------------- | ------------------------------- |
    | **API Base URL**  | Azure OpenAI Endpoint | -                               |
    | **API Key**       | Azure auth key        | -                               |
    | **Quality**       | Image quality         | `auto`, `low`, `medium`, `high` |
    | **Output Format** | Output format         | `png`, `jpeg`, `webp`           |
    | **Background**    | Background handling   | `auto`, `transparent`, `opaque` |

    Default image size is **1024x1024**.
  </Tab>

  <Tab title="Gemini">
    | Setting     | Description                   |
    | ----------- | ----------------------------- |
    | **API Key** | Google AI Studio API key      |
    | **Model**   | Gemini image generation model |
  </Tab>

  <Tab title="Vertex AI">
    | Setting        | Description                   |
    | -------------- | ----------------------------- |
    | **Project ID** | Google Cloud project ID       |
    | **Location**   | Region                        |
    | **Model**      | Gemini image generation model |
  </Tab>
</Tabs>

Multiple engines can be added simultaneously, and the image generation connection used per agent can be selected.

***

## Agent Integration

For image generation to work, **all 3 conditions** must be met:

1. Image generation **enabled** + engine connected in this tab
2. Image generation capability set to **Default On** or **Default Off** in agent settings
3. User **manually toggles** image generation in chat (when Default Off)

<Note>
  Image generation operates as an agent **Tool**. When the AI decides "an image is needed", it auto-invokes the image generation tool.
</Note>