Create Image

POST

/v1/images/generations

• Given a prompt and/or input image, the model will generate a new image.
• Supports text-to-image, image-to-image, multi-image fusion, and more.
• Supports seedream-5.0/4.5/4.0/3.0-t2i and seededit-3.0-i2i models.

Authorizations

bearer

Type

HTTP (bearer)

Request Body

application/json

object

• Supports: Text-to-Image
  • doubao-seedream-3-0-t2i-250415
• Supports: Image Editing
  • doubao-seededit-3-0-i2i-250628
• Supports: Text-to-Image, Image-to-Image
  • doubao-seedream-5-0-260128
  • doubao-seedream-4-5-251128
  • doubao-seedream-4-0-250828

Prompt used to generate the image.

Specifies the return format of the generated image. Two return methods are supported:

• url: Returns a download link for the image; the link is valid for 24 hours after the image is generated, please download the image in time.
• b64_json: Returns the image data in JSON format as a Base64-encoded string.

Default value: url

string

Only doubao-seedream-3.0-t2i/seededit-3.0-i2i support this parameter.
Random seed used to control the randomness of the model's generated content. Value range: [-1, 2147483647].
Note:

• With the same request, different seed values received by the model (e.g., not specifying a seed value, setting seed to -1 which uses a random number, or manually changing the seed value) will produce different results.
• With the same request, the model receiving the same seed value will produce similar results, but exact consistency is not guaranteed.

The degree of consistency between the model's output and the prompt, also known as text weight; a higher value means less creative freedom and stronger correlation with the user's input prompt. Value range: [1, 10].

• doubao-seedream-3.0-t2i default: 2.5
• doubao-seededit-3.0-i2i default: 5.5
• doubao-seedream-5.0-lite/4.5/4.0 not supported

Whether to add a watermark to the generated image.

• false: No watermark.
• true: Add an "AI Generated" watermark in the bottom-right corner of the image.

Default value: true

string |array

Input image information, supports URL or Base64 encoding.

• Image URL: Please ensure the image URL is accessible.
• Base64 encoding: Please follow this format: data:image/<image_format>;base64,<Base64_encoding>. Note that <image_format> must be lowercase, e.g. data:image/png;base64,<base64_image>.

Only doubao-seedream-5.0-lite/4.5/4.0 supports this parameter.
Controls whether to enable the image series feature; generates a
group of content-related images based on your input.

• auto: Automatic mode, the model will determine whether to return
  an image series and the number of images based on the prompt.
• disabled: Disables the image series feature, the model will only
  generate a single image.

Default value: disabled

object

Only doubao-seedream-5.0-lite/4.5/4.0 supports this parameter.
Configuration for the image series feature. Only effective when
sequential_image_generation is set to auto.

Only doubao-seedream-5.0 supports this parameter.
Specifies the file format of the generated image. Available values:

• png
• jpeg

Default value: jpeg