Skip to main content
POST
/
kling
/
v1
/
images
/
multi-image2image
cURL
curl https://api.cometapi.com/kling/v1/images/multi-image2image \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model_name": "kling-v2-1",
  "prompt": "Two product mascots standing together in a bright studio scene",
  "subject_image_list": [
    {
      "subject_image": "https://your-image-host/subject-1.png"
    },
    {
      "subject_image": "https://your-image-host/subject-2.png"
    }
  ],
  "scene_image": "https://your-image-host/scene.png",
  "style_image": "https://your-image-host/style.png",
  "n": 1,
  "aspect_ratio": "1:1"
}'
{
  "code": 123,
  "message": "<string>",
  "data": {
    "task_id": "<string>",
    "created_at": 123,
    "updated_at": 123,
    "task_status_msg": "<string>",
    "task_info": {
      "external_task_id": "<string>"
    },
    "task_result": {}
  },
  "request_id": "<string>"
}
Use this endpoint when you want Kling to generate one image from multiple subject references plus optional scene or style references.

​
Before you call it

  • Provide 1 to 4 images in subject_image_list
  • Use model_name: kling-v2-1 for new requests
  • Add scene_image or style_image only when the core subject composition already works
  • Treat this as an async generation route and save the returned task id

​
Task flow

1

Submit the image-generation task

Send the subject image list and prompt, then store the returned task id.
2

Poll the task

Poll the returned task with the matching Kling image query path until the task reaches a terminal state.
3

Persist the result

Save the generated image into your own storage if you need durable access.
For the complete parameter reference, see the official Kling documentation.

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your CometAPI key.

Headers

​
Content-Type
string
default:application/json

Must be application/json.

Body

application/json
​
subject_image_list
object[]
required

Subject reference images. Minimum 1, maximum 4.

Required array length: 1 - 4 elements
​
model_name
enum<string>
default:kling-v2

Model to use for multi-image generation. Use kling-v2-1 for new requests; omitting the field uses the legacy route default.

Available options:
kling-v2,
kling-v2-1
​
prompt
string

Text prompt describing the desired output. Maximum 2500 characters.

​
negative_prompt
string

Elements to exclude from the image. Maximum 2500 characters.

​
scene_image
string

Optional scene reference image. Image URL or raw Base64 string without a data: prefix. Supported formats: JPG, JPEG, PNG. Maximum 10 MB, minimum 300x300 px, aspect ratio between 1:2.5 and 2.5:1.

​
style_image
string

Optional style reference image. Image URL or raw Base64 string without a data: prefix. Supported formats: JPG, JPEG, PNG. Maximum 10 MB, minimum 300x300 px, aspect ratio between 1:2.5 and 2.5:1.

​
n
integer
default:1

Number of images to generate. Range: 1-9.

Required range: 1 <= x <= 9
​
aspect_ratio
enum<string>
default:16:9

Aspect ratio of the generated image.

Available options:
16:9,
9:16,
1:1,
4:3,
3:4,
3:2,
2:3,
21:9
​
watermark_info
object

Watermark options.

​
callback_url
string

Webhook URL for task status notifications.

​
external_task_id
string

Optional user-defined task ID for your own tracking. Must be unique per account.

Response

200 - application/json

Task request accepted or an error response returned by the API.

​
code
required

Response code. 0 means the task request was accepted.

​
message
string
required

Response message.

​
data
object
required
​
request_id
string

Request identifier returned when present.