Text Models
Image Models
Video Models
- POSTText to Video
- POSTImage to Video
- POSTMulti-Image to Video
- POSTVideo Extension
- POSTTTS
- POSTAvatar
- POSTLip-Sync
- POSTCounterpart Task Creation
- POSTVideo Effects
- POSTText to Audio
- POSTVideo to Audio
- POSTImage Generation
- POSTMulti-Image to Image
- POSTImage Expansion
- POSTImage Recognition
- POSTVirtual Try-On
- GETIndividual Queries
- POSTOmni Video
- GETOmni Query
- Callback URL
Multimodal Video Editing
Create Task
Create a Kling multimodal video editing task via CometAPI: POST /kling/v1/videos/multi-elements to combine multiple elements and generate videos asynchronously.
POST
/
kling
/
v1
/
videos
/
multi-elements
Create a Kling multimodal edit task
curl --request POST \
--url https://api.cometapi.com/kling/v1/videos/multi-elements \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"session_id": "784914037360041984",
"edit_mode": "replace",
"prompt": "Replace the selected object with a red paper boat."
}
'{
"code": 123,
"message": "<string>",
"data": {
"task_id": "<string>",
"task_status": "<string>",
"created_at": 123,
"updated_at": 123
}
}Use this endpoint to submit the final multimodal video-editing job after your session and selections are ready.Documentation Index
Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt
Use this file to discover all available pages before exploring further.
Full workflow
Initialize the editing session
Start with Initialize Video for Editing to obtain the
session_id for the clip you want to edit.Build the selection area
Use Add Video Selection and, when needed, Preview Selected Video Area to refine the edit region.
Before you call it
- Make sure the selection session is already initialized
- Confirm your region selection is correct before spending a generation call
- Treat this route as the final generation step, not the setup step
For the complete parameter reference, see the Kling API documentation.
Authorizations
Bearer token authentication. Use your CometAPI key.
Body
application/json
Session id returned by the video initialization endpoint.
Editing operation to apply. Options: replace, remove.
Text prompt describing the desired edit for the selected region.
⌘I
Create a Kling multimodal edit task
curl --request POST \
--url https://api.cometapi.com/kling/v1/videos/multi-elements \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"session_id": "784914037360041984",
"edit_mode": "replace",
"prompt": "Replace the selected object with a red paper boat."
}
'{
"code": 123,
"message": "<string>",
"data": {
"task_id": "<string>",
"task_status": "<string>",
"created_at": 123,
"updated_at": 123
}
}