> ## 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.
# Extender un video de Kling
> Extiende videos generados por Kling mediante POST /kling/v1/videos/video-extend usando task_id y video_id; ejecútalo como una sub-tarea en la cuenta principal.
Usa este endpoint para extender un video de Kling existente como una tarea de seguimiento.
## Antes de llamarlo
* Comienza a partir del resultado finalizado de un video de Kling
* Pasa el `video_id` del resultado de la tarea principal
* Pasa el `task_id` principal junto con el `video_id`
* Usa un video de origen que sea compatible con la extensión; los videos de origen no compatibles devuelven HTTP 400 en lugar de crear una tarea de extensión
* Un padre completado de 5 s de Kling v1 o v1-6 de texto a video o de imagen a video es un punto de partida más seguro para la compatibilidad de la extensión
* Agrega `prompt`, `negative_prompt` o `cfg_scale` solo cuando necesites orientar la continuación
* Ejecuta la extensión en el mismo contexto de cuenta que la tarea principal
* Activa la extensión rápidamente antes de que expiren los recursos de la tarea principal
## Flujo de la tarea
Crea el video original de Kling y espera hasta que su resultado esté disponible.
Envía el `task_id` principal, el `video_id` y el prompt opcional, y luego guarda el id de tarea devuelto.
Continúa con [Obtener una tarea de Kling](./individual-queries) hasta que el video extendido alcance un estado terminal.
Para la referencia completa de parámetros, consulta la [documentación oficial de Kling](https://kling.ai/document-api/apiReference/model/videoDuration).
## OpenAPI
````yaml api/openapi/video/kling/post-video-extension.openapi.json POST /kling/v1/videos/video-extend
openapi: 3.1.0
info:
title: Video Extension API
version: 1.0.0
servers:
- url: https://api.cometapi.com
security:
- bearerAuth: []
paths:
/kling/v1/videos/video-extend:
post:
summary: Video Extension
description: Only videos from supported generation types can be extended.
operationId: video_extension
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- video_id
- task_id
properties:
task_id:
type: string
description: >-
Parent Kling task id for the extension-compatible video
being extended.
video_id:
type: string
description: >-
Video id from a parent task result. The source video must be
extension-compatible; unsupported videos return HTTP 400.
prompt:
type: string
description: >-
Text prompt describing the desired motion for the extended
segment. Maximum 500 characters.
callback_url:
type: string
description: >-
Webhook URL to receive task status updates when the task
completes.
negative_prompt:
type: string
description: Elements to avoid in the extension.
cfg_scale:
type: number
description: 'Prompt adherence strength for the extension. Range: 0-1.'
default:
task_id:
video_id:
prompt: Continue with the same calm morning atmosphere
cfg_scale: 0.5
examples:
Default:
summary: >-
Video extension request with an extension-compatible parent
task
value:
task_id:
video_id:
prompt: Continue with the same calm morning atmosphere
cfg_scale: 0.5
responses:
'200':
description: Successful Response
content:
application/json:
schema:
type: object
required:
- code
- message
- request_id
- data
properties:
code:
type: integer
description: Error code; specifically define the error code
message:
type: string
description: error message
request_id:
type: string
description: >-
Request ID, system-generated, for tracking requests,
troubleshooting issues
data:
type: object
required:
- task_id
- task_status
- task_status_msg
- task_info
- task_result
- created_at
- updated_at
properties:
task_id:
type: string
description: Task ID, system generated
task_status:
type: string
description: >-
Task status, enumerated values: submitted, processing,
succeed, failed.
task_status_msg:
type: string
task_info:
type: object
required:
- parent_video
properties:
parent_video:
type: object
required:
- id
- url
- duration
properties:
id:
type: string
url:
type: string
duration:
type: string
task_result:
type: object
required:
- videos
properties:
videos:
type: array
items:
type: object
properties:
id:
type: string
url:
type: string
duration:
type: string
created_at:
type: integer
description: Task creation time, Unix timestamp, in ms.
updated_at:
type: integer
description: Task update time, Unix timestamp, in ms.
x-codeSamples:
- lang: Shell
label: Default
source: |
curl https://api.cometapi.com/kling/v1/videos/video-extend \
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"task_id": "",
"video_id": "",
"prompt": "Continue with the same calm morning atmosphere",
"cfg_scale": 0.5
}'
- lang: Python
label: Default
source: |
import os
import requests
response = requests.post(
"https://api.cometapi.com/kling/v1/videos/video-extend",
headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]},
json={
"task_id": "",
"video_id": "",
"prompt": "Continue with the same calm morning atmosphere",
"cfg_scale": 0.5
},
)
result = response.json()
print(result.get("code"), result.get("data", {}).get("task_id"))
- lang: JavaScript
label: Default
source: >
const response = await
fetch("https://api.cometapi.com/kling/v1/videos/video-extend", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.COMETAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"task_id": "",
"video_id": "",
"prompt": "Continue with the same calm morning atmosphere",
"cfg_scale": 0.5
}),
});
const result = await response.json();
console.log(result.code, result.data?.task_id);
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: Bearer token authentication. Use your CometAPI key.
````