Kling Video O3 Pro Video To Video API

Edit
Reference

Endpoint: POST https://fal.run/fal-ai/kling-video/o3/pro/video-to-video/edit Endpoint ID: fal-ai/kling-video/o3/pro/video-to-video/edit

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/kling-video/o3/pro/video-to-video/edit",
    arguments={
        "prompt": "Change environment to be fully snow as @Image1. Replace animal with @Element1",
        "video_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-edit/video_reference.mp4"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/kling-video/o3/pro/video-to-video/edit", {
  input: {
      prompt: "Change environment to be fully snow as @Image1. Replace animal with @Element1",
      video_url: "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-edit/video_reference.mp4"
    },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

curl --request POST \
  --url https://fal.run/fal-ai/kling-video/o3/pro/video-to-video/edit \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "Change environment to be fully snow as @Image1. Replace animal with @Element1",
  "video_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-edit/video_reference.mp4"
}'

Input Schema

string

required

Text prompt for video generation. Reference video as @Video1.

string

required

Reference video URL. Only .mp4/.mov formats, 3-10s duration, 720-2160px resolution, max 200MB.

list<string>

Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.

boolean

default:"true"

Whether to keep the original audio from the reference video. Default value: true

list<KlingV3ImageElementInput>

Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2.

string

default:"customize"

The type of multi-shot video generation. Default value: "customize"

Output Schema

File

required

The generated video.

Input Example

{
  "prompt": "Change environment to be fully snow as @Image1. Replace animal with @Element1",
  "video_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-edit/video_reference.mp4",
  "image_urls": [
    "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-edit/image_url1.jpg"
  ],
  "keep_audio": true,
  "elements": [
    {
      "frontal_image_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-edit/element1_front.png",
      "reference_image_urls": [
        "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-edit/element1_reference1.png"
      ]
    }
  ],
  "shot_type": "customize"
}

Output Example

{
  "video": {
    "content_type": "video/mp4",
    "file_name": "output.mp4",
    "file_size": 4322769,
    "url": "https://storage.googleapis.com/falserverless/example_outputs/kling-o3/pro-v2v-edit/output.mp4"
  }
}

Endpoint: POST https://fal.run/fal-ai/kling-video/o3/pro/video-to-video/reference Endpoint ID: fal-ai/kling-video/o3/pro/video-to-video/reference

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/kling-video/o3/pro/video-to-video/reference",
    arguments={
        "prompt": "Integrate @Element1 in the scene. Style video should be following watercolor style of @Image1",
        "video_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/video_reference.mp4"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/kling-video/o3/pro/video-to-video/reference", {
  input: {
      prompt: "Integrate @Element1 in the scene. Style video should be following watercolor style of @Image1",
      video_url: "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/video_reference.mp4"
    },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

curl --request POST \
  --url https://fal.run/fal-ai/kling-video/o3/pro/video-to-video/reference \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "Integrate @Element1 in the scene. Style video should be following watercolor style of @Image1",
  "video_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/video_reference.mp4"
}'

Input Schema

string

required

Text prompt for video generation. Reference video as @Video1.

string

required

Reference video URL. Only .mp4/.mov formats, 3-10s duration, 720-2160px resolution, max 200MB.

list<string>

Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 4 total (elements + reference images) when using video.

boolean

default:"true"

Whether to keep the original audio from the reference video. Default value: true

list<KlingV3ImageElementInput>

Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2.

string

default:"customize"

The type of multi-shot video generation. Default value: "customize"

AspectRatioEnum

default:"auto"

Aspect ratio. Default value: "auto"Possible values: auto, 16:9, 9:16, 1:1

Enum

Video duration in seconds (3-15s for reference video).Possible values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15

Output Schema

File

required

The generated video.

Input Example

{
  "prompt": "Integrate @Element1 in the scene. Style video should be following watercolor style of @Image1",
  "video_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/video_reference.mp4",
  "image_urls": [
    "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/image_url1.jpg",
    "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/image_url2.jpg"
  ],
  "keep_audio": false,
  "elements": [
    {
      "frontal_image_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/element1_front.png",
      "reference_image_urls": [
        "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/element1_reference1.png"
      ]
    }
  ],
  "shot_type": "customize",
  "aspect_ratio": "auto",
  "duration": "5"
}

Output Example

{
  "video": {
    "content_type": "video/mp4",
    "file_name": "output.mp4",
    "file_size": 15809901,
    "url": "https://storage.googleapis.com/falserverless/example_outputs/kling-o3/pro-v2v-reference/output.mp4"
  }
}

Kling O3 Image to Video [Pro] — Video Generation
Kling O3 Reference to Video [Pro] — Video Generation
Kling O3 Text to Video [Pro] — Video Generation
Kling O3 Reference Video to Video [Pro] — Video Generation
Kling O3 Edit Video [Standard] — Video Generation

Limitations

aspect_ratio restricted to: auto, 16:9, 9:16, 1:1

Video Generation

Image Generation

Audio

Vision

3D

Kling Video O3 Pro Video To Video API

Try it in the Playground

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Try it in the Playground

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Limitations

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

​Related

​Limitations

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Related

Limitations