​
Image Generation (doubao-seededit-3-0-i2i)

Given a prompt and/or input image, the model will generate a new image. Related guide: Image Generation

​
Endpoint

POST /v1/images/generations

​
Authentication

All requests require a Bearer token in the Authorization header: 
Authorization: Bearer YOUR_API_KEY

​
Request Parameters

ParameterTypeRequiredDescription
modelstringYesThe ID of the model to use, e.g., doubao-seededit-3-0-i2i-250628
promptstringYesText description, the prompt for editing the image
imagestringYesThe image to edit, Base64 encoded or accessible URL. Supported formats: jpeg, png; aspect ratio within (1/3, 3); dimensions > 14px; size up to 10MB
response_formatstringNoOutput format. url: returns downloadable jpeg image link; b64_json: returns Base64 encoded JSON. Default: url
sizestringNoOutput image dimensions. Currently only supports adaptive, which automatically selects the closest ratio to the original
seedintegerNoRandom seed, range [-1, 2147483647]. Using the same seed ensures consistent results. Default: -1
guidance_scalenumberNoInfluence of text description vs input image on generation, range [1, 10]. Higher values mean more text influence. Default: 5.5
watermarkbooleanNoWhether to add watermark. true: adds “AI Generated” watermark; false: no watermark. Default: true

​
Request Example

curl -X POST "https://api.example.com/v1/images/generations" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seededit-3-0-i2i-250628",
    "prompt": "Change to heart-shaped bubbles",
    "image": "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream_i2i.jpeg",
    "response_format": "url",
    "size": "adaptive",
    "seed": 21,
    "guidance_scale": 5.5,
    "watermark": true
  }'

​
Response Example

{
  "created": 1753847978,
  "data": [
    {
      "url": "https://example.com/generated-image.jpeg"
    }
  ],
  "model": "doubao-seededit-3-0-i2i-250628",
  "usage": {
    "generated_images": 1,
    "output_tokens": 3772,
    "total_tokens": 3772
  }
}