Skip to main content
Seedream 3.0 Text-to-Image is a text-to-image model from ByteDance’s Seedream series, available through the Starrise AI API.

​
Key Capabilities

  • Text-to-image — Generate images from text prompts
  • Custom size — Flexible output dimensions
  • Watermark control — Optional watermark and logo configuration

​
Quick Example

curl https://ai.alad.com/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-3-0-t2i-250415",
    "prompt": "Generate an image of a girl and a cow plush toy happily riding a roller coaster at an amusement park",
    "size": "1024x1024",
    "watermark": false
  }'

​
Parameters

ParameterTypeRequiredDescription
modelstringYesMust be doubao-seedream-3-0-t2i-250415
promptstringYesImage generation prompt
sizestringNoOutput image size, e.g. 1024x1024, 2K
watermarkbooleanNoDefault false
seedintegerNoRandom seed for reproducibility
logo_infoobjectNoCustom logo watermark config: add_logo, position, language, opacity

API Reference

View the interactive API Playground for Seedream 3.0 Text-to-Image.