Skip to main content
POST
cURL
This is the Seedream Image Generation API text-to-image sync endpoint. Generate images only through prompt without any media files. Returns generation results directly after request, no additional query needed.

Sync Endpoint Description

Sync endpoint returns results directly without polling. All following scenarios use the same endpoint POST /sd/api/v3/images/generations, only parameters differ:
Recommended: Async endpoint: Recommended to use async endpoint in production (returns id, use query endpoint to get results), supports webhook callback notifications, more suitable for large-scale generation scenarios.

Authorizations

TT-API-KEY
string
header
required

Get your API key from the TTAPI Dashboard.

Body

application/json
model
enum<string>
required

Model name.

Available options:
doubao-seedream-5-0-pro-260628,
doubao-seedream-5-0-flash-260915
prompt
string
required

Text prompt.

size
enum<string>
default:2K

Image size. 5.0 pro/flash options: 1K, 1.5K, 2K (default 2K), or specify pixel values.

Available options:
1K,
1.5K,
2K
output_format
enum<string>
default:jpeg

Output image format.

Available options:
png,
jpeg
response_format
enum<string>
default:url

Return format. url returns image download link (24h valid), b64_json returns Base64 encoded data.

Available options:
url,
b64_json
background
enum<string>
default:opaque

Image alpha channel setting. transparent=transparent background (image-to-image only), opaque=opaque background. Only 5.0 pro/flash supports.

Available options:
transparent,
opaque
watermark
enum<boolean>
default:true

Whether to add watermark. true=Display "AI Generated" in bottom-right, false=Do not add.

Available options:
true,
false
Example:

false

optimize_prompt_options
object

Prompt optimization config

Response

200 - application/json

Generation successful

model
string
created
integer

Created time (Unix timestamp)

data
object[]
usage
object
Last modified on October 23, 2026