Runflow
Back to Gallery

kuaishou/kling-video/v3/pro/image-to-video

Kling 3.0 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.

$0.14/second 2026-04-05

Install

pip install requests

Run the model

import requests

response = requests.post(
    "https://api.runflow.io/v1/run/kling-video/v3/pro/image-to-video",
    headers={"Authorization": "Bearer RUNFLOW_API_KEY"},
    json={
    "prompt": "Gentle head turn with a warm smile, hair blowing slightly in a soft breeze, c...",
    "image_url": "https://public.runflow.io/images/models/_base/portrait-woman-studio.png"
    },
)

data = response.json()
print(data["video"]["url"])

Input schema

ParameterTypeDescription
promptstringText prompt for video generation. Either prompt or multi_prompt must be provided, but not both.
voice_idsstringOptional Voice IDs for video generation. Reference voices in your prompt with <<<voice_1>>> and <<<voice_2>>> (maximum 2 voices per task). Get voice IDs from the kling video create-voice endpoint: https://fal.ai/models/fal-ai/kling-video/create-voice
elementsstringElements (characters/objects) to include in the video. Each example can either be an image set (frontal + reference images) or a video. Reference in prompt as @Element1, @Element2, etc.
multi_promptarrayList of prompts for multi-shot video generation. If provided, divides the video into multiple shots.
generate_audiobooleanWhether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.
durationstringThe duration of the generated video in seconds
shot_typestringThe type of multi-shot video generation. Required when multi_prompt is provided.
start_image_urlimageURL of the image to be used for the video
end_image_urlimageURL of the image to be used for the end of the video
negative_promptstring
cfg_scalenumberThe CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt.

Output schema

FieldTypeDescription
videostringThe generated video

Related models

Start generating with Kling v3 Pro — Image to Video

Get API access in minutes. No GPU setup, no infrastructure to manage.