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

# Gemini Native (Image)

> Gemini image generation models: text-to-image and image-to-image

## Introduction

Nano Banana refers to Google Gemini image generation models: **Nano Banana** (`gemini-2.5-flash-image`) and **Nano Banana Pro** (`gemini-3-pro-image-preview`). They are called via the unified image API `POST /v1/images/generations`, supporting text-to-image, image-to-image, and multi-image composition.

For full parameters and multi-model details, see [Image Generation](/en/api-reference/endpoint/image-generation).

## Authentication

<ParamField header="Authorization" type="string" required>
  Bearer Token, e.g. `Bearer sk-xxxxxxxxxx`
</ParamField>

## Supported models

| Model ID                     | Description                                         |
| ---------------------------- | --------------------------------------------------- |
| `gemini-2.5-flash-image`     | Nano Banana, cost-effective text/image-to-image     |
| `gemini-3-pro-image-preview` | Nano Banana Pro, higher quality and controllability |

## Request examples

<Tabs>
  <Tab title="Text-to-image">
    ```bash theme={null}
    curl -X POST "https://api.leapx-hub.com/v1/images/generations" \
      -H "Authorization: Bearer sk-xxxxxxxxxx" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "gemini-2.5-flash-image",
        "prompt": "A cute orange cat sitting in a garden, sunny, high-quality photo",
        "size": "16:9",
        "quality": "high",
        "n": 1,
        "response_format": "b64_json",
        "image_size": "2K",
        "mime_type": "image/png",
        "response_modalities": "image"
      }'
    ```
  </Tab>

  <Tab title="Image-to-image">
    ```bash theme={null}
    curl -X POST "https://api.leapx-hub.com/v1/images/generations" \
      -H "Authorization: Bearer sk-xxxxxxxxxx" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "gemini-2.5-flash-image",
        "size": "16:9",
        "quality": "high",
        "image_size": "3K",
        "response_format": "b64_json",
        "contents": [
          {
            "role": "user",
            "parts": [
              {"text": "Generate an aerial view of Canton Tower based on this image"},
              {"image": "data:image/png;base64,iVBORw0KGgo..."}
            ]
          }
        ]
      }'
    ```
  </Tab>
</Tabs>

## Common parameters

* **prompt**: Text prompt for text-to-image
* **size**: Aspect ratio, e.g. `16:9`, `1:1`
* **quality**: Quality level, e.g. `high`
* **image\_size**: Output size, e.g. `1K`, `2K`, `3K`
* **response\_format**: Gemini series only supports `b64_json` (base64 image)
* **contents**: Used for image-to-image or multi-turn; format in [Image Generation](/en/api-reference/endpoint/image-generation)

For more parameters and model differences, see [Image Generation](/en/api-reference/endpoint/image-generation).