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

# Image Generation

> Generate original images from a text prompt with Google Gemini / Imagen.

# Image Generation

> **In one line:** Let your UnleashX agent create original images from a written description and return ready-to-use image links.

|                    |                                                                           |
| ------------------ | ------------------------------------------------------------------------- |
| **Category**       | AI & Media                                                                |
| **Authentication** | Platform-managed                                                          |
| **Setup time**     | \~1 minute                                                                |
| **Difficulty**     | Easy                                                                      |
| **Best for**       | Marketing visuals, social posts, mockups, and illustrations from a prompt |

## 1. Overview

Image Generation turns a text prompt into a brand-new picture using Google's Imagen models via the Gemini API. Describe what you want — a style, a subject, a mood — and it produces one or more images.

Once connected, your agent can generate images from a prompt, request several at once, and choose an aspect ratio. Generated images are uploaded to UnleashX media storage and returned as links you can drop into a post, a doc, or a campaign.

Connecting Image Generation to UnleashX means your agents can produce visuals on demand — no stock library, no design tool, no manual export.

## 2. What you'll need

<Note>
  Image Generation is **built into UnleashX**. There is no Google or Gemini account for you to create and no API key for you to manage.
</Note>

* An active UnleashX account.
* The image-generation feature enabled on your workspace/plan.
* A clear text prompt describing the image you want.
* Permission to edit the agent (admin or editor role). Without it, ask a workspace admin to enable the feature.

## 3. Get your credentials

<Info>
  There are **no credentials to create**. Image Generation is platform-managed — UnleashX provisions and rotates the underlying Gemini key and handles media storage. You never see or handle an API key.
</Info>

If you are a workspace admin, optional platform-side configuration includes the image model (with automatic fallbacks) and the default aspect ratio. UnleashX ships sensible defaults (an Imagen 4 model, square 1:1); most teams never change them.

| Platform-managed setting       | Plain-English reason it exists                                                 |
| ------------------------------ | ------------------------------------------------------------------------------ |
| Image model (+ fallbacks)      | Controls image quality and auto-retries if a model is unavailable.             |
| Default aspect ratio           | Sets the default image shape (e.g. 1:1 square).                                |
| Gemini API key & media storage | Provisioned and rotated by UnleashX so images generate and save automatically. |

## 4. Connect on UnleashX

<Steps>
  <Step title="Open your agent">
    Go to [https://www.tryunleashx.com](https://www.tryunleashx.com) and open the agent that should generate images.
  </Step>

  <Step title="Open Data Connectors">
    In the agent, click **Data Connectors**.
  </Step>

  <Step title="Find Image Generation and add it">
    Locate **Image Generation** and click **Connect** / **Add**. It's platform-managed — no key to paste, it activates immediately.
  </Step>

  <Step title="Confirm it's connected">
    The Image Generation tool should now show a **Connected** badge.
  </Step>
</Steps>

### Use Image Generation in a Workflow

Once connected, you can add **Image Generation** to any automation from the **Workflows** builder. Its triggers and tools appear in the Apps panel, marked with an **MCP** badge.

<Steps>
  <Step title="Add a trigger or action node">
    Open **Workflows → New Workflow**. On the canvas, click **+ Add Trigger** (or the **+** below any node) to add a step.

    <img src="https://mintcdn.com/unleashx/LXZeho1M8XzFkz0k/images/mcp/workflows/05-add-trigger.png?fit=max&auto=format&n=LXZeho1M8XzFkz0k&q=85&s=449a0c03b0c7b40e571ec02373a85259" alt="Add a trigger on the workflow canvas" width="1390" height="722" data-path="images/mcp/workflows/05-add-trigger.png" />
  </Step>

  <Step title="Pick Image Generation from the Apps panel">
    In the **Paths** panel, open the **Apps** tab and select **Image Generation**. Use the search box if you have many connectors.

    <img src="https://mintcdn.com/unleashx/LXZeho1M8XzFkz0k/images/mcp/workflows/06-apps-list.png?fit=max&auto=format&n=LXZeho1M8XzFkz0k&q=85&s=bbb8bb6e668c4f8e1f6fd5e4955a45f0" alt="Choose your app from the Apps list" width="2446" height="1550" data-path="images/mcp/workflows/06-apps-list.png" />
  </Step>

  <Step title="Choose a trigger or tool">
    Pick the trigger or action you want. Configure its fields — required fields are marked with a red asterisk (\*).
  </Step>

  <Step title="Add or select your account">
    Under **Selected account**, choose an already-connected account, or click **Add Account** to connect one now.
  </Step>

  <Step title="Save and test">
    Fill in the remaining fields and click **Save**. Use **Test** to verify the step, then toggle **Publish** when the workflow is ready.
  </Step>
</Steps>

<Note>
  The steps are the same for every connector. For the full workflow builder guide, see [Using MCP in Workflows](/mcp/workflows).
</Note>

## 5. Available tools

| Tool           | What it does                                   | Changes data? |
| -------------- | ---------------------------------------------- | ------------- |
| Image Created  | Generate one or more images from a text prompt | ✏️ Yes        |
| Generate Image | Generate images with Imagen via the Gemini API | ✏️ Yes        |
| Get Info       | Report Image MCP configuration and readiness   | No            |

<Note>
  The generate tools are marked ✏️ Yes because they create new image files and save them to UnleashX media storage. They do not modify or delete existing data. **Image Created** and **Generate Image** are equivalent entry points for the same generation flow.
</Note>

## 6. Example usage

**"Create a square image of a friendly robot waving, flat-illustration style."**
→ Runs **Generate Image** (or **Image Created**) with that prompt and a 1:1 aspect ratio, returning an image URL.

**"Give me three banner options for a summer sale, wide format."**
→ Runs the generation tool with `number_of_images` = 3 and a wide aspect ratio.

## 7. Permissions & data access

**UnleashX can:**

* Send your prompt to the image model and generate images.
* Save the generated images to UnleashX media storage and return links.

**UnleashX cannot:**

* Generate images from content you don't provide.
* Edit or delete images created elsewhere.
* Access your device or cloud storage on its own.

**To disconnect:** Open the agent → **Data Connectors** → **Image Generation** → **Disconnect**. Access is revoked immediately.

## 8. Troubleshooting

| Problem                                     | What it means                                      | How to fix it                                                       |
| ------------------------------------------- | -------------------------------------------------- | ------------------------------------------------------------------- |
| "prompt is required"                        | No text prompt was supplied                        | Provide a descriptive prompt                                        |
| "number\_of\_images must be greater than 0" | Asked for zero images                              | Request at least one image                                          |
| "did not return any generated images"       | The model returned nothing (e.g. safety filtering) | Adjust the prompt and retry                                         |
| 401 / credential error                      | The platform-managed Gemini key is unavailable     | Platform-side — contact **[cs@unleashx.ai](mailto:cs@unleashx.ai)** |
| 403 / feature not enabled                   | Image generation isn't enabled on your plan        | Ask a workspace admin or contact support                            |

For general connector issues, see [/mcp/integrations](/mcp/integrations).

## 9. Frequently asked questions

**Are my images stored?**
Yes — generated images are uploaded to UnleashX media storage so you can use the returned link. Your prompt is used to generate them and isn't retained as part of the integration.

**Do I need a Google or Gemini account?**
No. Image Generation is platform-managed — UnleashX provides and rotates the key.

**Can I generate more than one image at a time?**
Yes. Set `number_of_images` to request a batch.

**What aspect ratios are supported?**
Common shapes including square (1:1), portrait, and landscape. The default is square.

## 10. References

* Google Imagen / Gemini image generation docs: [https://ai.google.dev/gemini-api/docs/image-generation](https://ai.google.dev/gemini-api/docs/image-generation)
* UnleashX dashboard: [https://www.tryunleashx.com](https://www.tryunleashx.com)
* UnleashX integrations help: [/mcp/integrations](/mcp/integrations)