Skip to main content
POST
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

string
required
Enum value: application/json
string
required
Bearer authentication format: Bearer {{API Key}}.

Request Body

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].
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
string
required
The prompt used to generate the image, supporting Chinese and English. It is recommended not to exceed 300 Chinese characters or 600 English words.
boolean
default:true
Whether to add a watermark to the generated image.
object
Configuration for the prompt optimization feature.
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
object
Configuration for the image set feature. Only takes effect when sequential_image_generation is auto.

Response Information

string[]
Array of generated image information.