v1.6-standart/image-to-video

This documentation is valid for the following list of our models:

• kling-video/v1.6/standard/image-to-video

Model Overview

An advanced AI video generation model developed by Kuaishou Technology, designed to create high-quality videos from text prompts and images. This version introduces significant improvements in prompt adherence, visual quality, and dynamic action rendering, enabling users to generate more consistent and visually appealing results compared to its predecessor, Kling 1.5.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

Submit a request

API Schema

post

/v2/generate/video/kling/generation

Authorizations

Body

promptstringrequired

durationstring · default: 5

image_urlstring · urirequired

ratiostring · enum

Options: 16:9, 9:16, 1:1

modelundefined · enumrequired

Options: kling-video/v1.6/standard/image-to-video

Responses

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/v2/generate/video/kling/generation' \
  --header 'Authorization: Bearer JWT' \
  --header 'Content-Type: application/json' \
  --data '{
    "prompt": "text",
    "duration": "5",
    "image_url": "https://example.com",
    "ratio": "16:9",
    "model": "kling-video/v1.6/standard/image-to-video"
  }'

201

201

No body

get

/v2/generate/video/kling/generation

Authorizations

Query parameters

Kling.v2.PollGenerationPayloadDTOobjectrequired

Responses

cURL

JavaScript

Python

HTTP

cURL

curl -L \
  --url 'https://api.aimlapi.com/v2/generate/video/kling/generation?Kling.v2.PollGenerationPayloadDTO=%5Bobject+Object%5D' \
  --header 'Authorization: Bearer JWT'

200

200

No body