Skip to main content
POST
/
kling
/
v1
/
videos
/
multi-image2video
cURL
curl https://api.cometapi.com/kling/v1/videos/multi-image2video \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "image_list": [
        {
          "image": "https://your-image-host/first-frame.jpg"
        },
        {
          "image": "https://your-image-host/second-frame.jpg"
        }
      ],
      "prompt": "A smooth transition between the two reference moments",
      "mode": "std",
      "duration": "5",
      "aspect_ratio": "1:1"
    }'
{
  "code": 0,
  "message": "SUCCEED",
  "data": {
    "task_id": "861309198188019719",
    "task_status": "submitted",
    "task_info": {},
    "created_at": 1773380633979,
    "updated_at": 1773380633979
  }
}
Use this endpoint when one source image is not enough and you want Kling to build motion from multiple image references.

​
Before you call it

  • Prepare 1 to 4 images in image_list
  • Use images that meet Kling pixel requirements; tiny thumbnails are rejected by the generation task
  • Omit model_name unless you specifically need to select a route-compatible model
  • Keep the first test simple: a short prompt, duration: 5, no extra callback settings
  • Do not send image-to-video mask fields such as static_mask or dynamic_masks on this route

​
Task flow

1

Submit the multi-image request

Send the image list, prompt, and duration, then save the returned Kling task_id.
2

Poll the task

Continue with Get a Kling task until the task reaches a terminal state.
3

Persist the result

Store the finished video if you need retention beyond the provider delivery URL.
For the complete parameter reference, see the official Kling documentation.

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your CometAPI key.

Body

application/json
​
image_list
object[]
required

Input image references. Provide 1 to 4 items that meet Kling pixel requirements; very small thumbnails are rejected.

Required array length: 1 - 4 elements
​
model_name
enum<string>
default:kling-v1-6

Kling model variant for multi-image video. Omit to use kling-v1-6.

Available options:
kling-v1-6
​
prompt
string

Text prompt describing the desired motion and scene.

​
negative_prompt
string

Elements to avoid in the generated video.

​
mode
enum<string>
default:std

Generation mode. Use std or pro; omitted requests use std.

Available options:
std,
pro
​
duration
string
default:5

Output video length in seconds. Use 5 or 10; omitted requests use 5.

​
aspect_ratio
enum<string>

Requested frame aspect ratio when the model needs an explicit frame shape.

Available options:
16:9,
9:16,
1:1
​
callback_url
string

Webhook URL to receive task status updates.

​
external_task_id
string

Custom task id for your own tracking. Must be unique per account.

Response

200 - application/json

Task accepted.

​
code
integer
required

Error code; specifically define the error code

​
message
string
required

error message

​
data
object
required