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

# Nano Banana Pro Light Image-to-Image (reverse)

Generate a new image based on an input image and text description.

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum value: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="n" type="integer" default={1}>
  The number of images to generate. Must be between 1 and 10.

  Value range: \[1, 10]
</ParamField>

<ParamField body="mask" type="string">
  Mask image URL or Base64 encoding
</ParamField>

<ParamField body="size" type="string" default="1x1">
  The size of the generated image

  Optional values: `1x1`, `2x3`, `3x2`, `3x4`, `4x3`, `4x5`, `5x4`, `9x16`, `16x9`, `21x9`
</ParamField>

<ParamField body="images" type="string[]" required={true}>
  List of input images to process

  Array length: 1 - 10

  Image URL or Base64 encoding
</ParamField>

<ParamField body="prompt" type="string" required={true}>
  Text description of the desired image.
</ParamField>

<ParamField body="quality" type="string" default="1k">
  Select image generation quality

  Optional values: `1k`, `2k`, `4k`
</ParamField>

<ParamField body="response_format" type="string" default="url">
  The format in which to return the generated image. Must be one of url—b64\_json.

  Optional values: `url`, `b64_json`
</ParamField>

## Response Information

<ResponseField name="data" type="object[]" required={true}>
  List of generated images

  <Expandable title="properties" defaultOpen={true}>
    <ResponseField name="url" type="string" required={false}>
      Image URL (when response\_format is url)
    </ResponseField>

    <ResponseField name="b64_json" type="string" required={false}>
      Base64-encoded image data (when response\_format is b64\_json)
    </ResponseField>

    <ResponseField name="revised_prompt" type="string" required={false}>
      Revised prompt (if any)
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="created" type="integer" required={true}>
  Creation timestamp
</ResponseField>