> ## 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.

# Seedream Image Generation 4.5

Generate images based on input text prompts and/or reference images. Supports generating a single image or a set of images (a group of related images).

## 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="size" type="string" default="2048x2048">
  Specifies the size information of the generated image. Method 1: specify a resolution (2K, 4K); Method 2: specify width and height pixel values (such as 2048x2048). Total pixel range: \[3686400, 16777216], aspect ratio range: \[1/16, 16].
</ParamField>

<ParamField body="image" type="string[]">
  Array of input image information, supporting URL or Base64 encoding. Up to 14 reference images can be provided. Supported image formats include jpeg, png, webp, bmp, tiff, gif.

  Array length: 1 - 14
</ParamField>

<ParamField body="prompt" type="string" required={true}>
  The prompt used to generate the image, supporting Chinese and English. It is recommended not to exceed 300 Chinese characters or 600 English words.
</ParamField>

<ParamField body="watermark" type="boolean" default={true}>
  Whether to add a watermark to the generated image.
</ParamField>

<ParamField body="optimize_prompt_options" type="object">
  Configuration for the prompt optimization feature.

  <Expandable title="Properties" defaultOpen={true}>
    <ParamField body="mode" type="string" default="standard">
      Sets the mode used by the prompt optimization feature. standard: standard mode, higher quality and longer processing time; fast: fast mode, shorter processing time and average quality. Currently, only standard mode is supported.

      Allowed value: `standard`
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="sequential_image_generation" type="string" default="disabled">
  Controls whether to disable the image set feature. auto: automatic judgment mode, where the model independently determines whether to return a set of images based on the prompt; disabled: disables the image set feature and generates only one image.

  Allowed values: `auto`, `disabled`
</ParamField>

<ParamField body="sequential_image_generation_options" type="object">
  Configuration for the image set feature. Only takes effect when sequential\_image\_generation is auto.

  <Expandable title="Properties" defaultOpen={true}>
    <ParamField body="max_images" type="integer" default={15}>
      Specifies the maximum number of images that can be generated in this request. Number of input reference images + number of final generated images ≤ 15.

      Value range: \[1, 15]
    </ParamField>
  </Expandable>
</ParamField>

## Response Information

<ResponseField name="images" type="string[]" required={false}>
  Array of generated image information.
</ResponseField>