​
Image to Image

Generate new images using Jimeng (Dreamina) models based on reference images and text prompts.

​
Endpoint

POST /v1/images/edits

​
Authentication

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

​
Request Parameters

ParameterTypeRequiredDescription
modelstringYesModel ID, e.g., jimeng-2.1
imagestringYesReference image URL or Base64 encoded
promptstringYesText description for image generation
negative_promptstringNoNegative prompt
strengthnumberNoImage variation strength, 0-1, default 0.75
nintegerNoNumber of images to generate, default 1
sizestringNoImage size
response_formatstringNoResponse format, options: url, b64_json

​
Request Example

curl -X POST "https://api.example.com/v1/images/edits" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jimeng-2.1",
    "image": "https://example.com/reference-image.png",
    "prompt": "Transform the image style to watercolor painting",
    "strength": 0.75,
    "n": 1
  }'

​
Response Example

{
  "created": 1700000000,
  "data": [
    {
      "url": "https://example.com/edited-image.png"
    }
  ]
}

​
Response Fields

FieldTypeDescription
createdintegerCreation timestamp
dataarrayList of generated images
data[].urlstringImage URL
data[].b64_jsonstringBase64 encoded image