Kling 4.0 is LIVE — Unbelievably Real Video | Try Now →
Home/Explore/Kuaishou/Kling V4.0/Reference To Video

kwaivgi/kling-v4.0/reference-to-video

Kling V4.0 Reference-to-Video builds a new clip of 3 to 30 seconds from up to 10 reference images, 5 reference videos and 3 reference audios, following the subjects, motion and camera you point to in the prompt, with 720p and 1080p output and synchronized stereo audio. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Reference to Video
Input

Drag & drop or click to upload

preview
Keep the reference video's own sound instead of generating new audio. Requires videos.

Idle

$0.785per run·~12 / $10

Next:

ExamplesView all

The woman from @Image1 walks along a quiet cobblestone street at golden hour, smiling and looking around, cinematic tracking shot, soft footsteps and distant city sounds

The woman from @Image1 rows a small wooden boat across a misty lake at dawn, following the camera movement of @Video1

Related Models

README

Kling V4.0 Reference-to-Video

Kling V4.0 Reference-to-Video creates a new clip of 3 to 30 seconds from up to 10 reference images, up to 5 reference videos and up to 3 reference audios. Point to them in the prompt to keep a subject consistent, borrow a camera move or follow a performance. Output is 720p or 1080p with synchronized stereo audio.

Why Choose This?

  • Mix images, videos and audio Combine up to 10 images, 5 videos and 3 audios (15 files at most) in one request.
  • Prompt-level control Refer to inputs as @Image1, @Video1 and @Audio1 in the order you provide them.
  • Up to 30 seconds Output length is yours to choose, independent of the reference video.
  • Native audio New synchronized stereo audio, or keep the reference video's own sound.

Pricing

Without a reference video:

ResolutionPrice per second
720p$0.157
1080p$0.235

With reference videos, the price is per second counted as the output length plus the longer of the output length and the total length of the reference videos (in whole seconds, up to 30). Reference audios are not charged. Each counted second costs $0.094 at 720p and $0.141 at 1080p. When the output is as long as the reference videos this is $0.188 per output second at 720p and $0.282 at 1080p.

Parameters

ParameterDescription
promptRequired. Refer to images as @Image1, @Image2 ..., videos as @Video1 ... and audios as @Audio1 ....
imagesReference images, up to 10.
videosReference videos, up to 5. Together they are used for up to 30 seconds; longer clips are trimmed.
audiosReference audios, up to 3, 5 to 30 seconds each.
keep_original_soundKeep the reference video's own sound instead of generating new audio (default false). Requires videos.
resolution720p (default) or 1080p.
duration3 to 30 seconds, default 5.
aspect_ratioauto (default, follows the references), 16:9, 9:16, 1:1 or 21:9.

Prompting Guide

  • Say what each reference is for: "the character from @Image1 walks through the street from @Image2".
  • To reuse a camera move, say so: "follow the camera movement of @Video1".
  • Use clear, well-lit reference images; the subject should be easy to recognize.
Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Kling v4.0 Reference To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/kwaivgi/kling-v4.0/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Kling v4.0 Reference To Video below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "keep_original_sound": false,
    "resolution": "720p",
    "duration": 5,
    "aspect_ratio": "auto"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v4.0/reference-to-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v4.0/reference-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "keep_original_sound": false,
        "resolution": "720p",
        "duration": 5,
        "aspect_ratio": "auto"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "keep_original_sound": False,
    "resolution": "720p",
    "duration": 5,
    "aspect_ratio": "auto"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/kwaivgi/kling-v4.0/reference-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Kling v4.0 Reference To Video API — Frequently asked questions

What is the Kling v4.0 Reference To Video API?

Kling v4.0 Reference To Video is a Kuaishou model for reference-guided video generation, exposed as a REST API on WaveSpeedAI. Kling V4.0 Reference-to-Video builds a new clip of 3 to 30 seconds from up to 10 reference images, 5 reference videos and 3 reference audios, following the subjects, motion and camera you point to in the prompt, with 720p and 1080p output and synchronized stereo audio. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Kling v4.0 Reference To Video API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-v4.0-reference-to-video.

How much does Kling v4.0 Reference To Video cost per run?

Kling v4.0 Reference To Video starts at $0.785 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Kling v4.0 Reference To Video accept?

Key inputs: `prompt`, `images`, `aspect_ratio`, `resolution`, `duration`, `audios`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-v4.0-reference-to-video.

How do I get started with the Kling v4.0 Reference To Video API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Kling v4.0 Reference To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Kuaishou). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

llms.txt — kwaivgi/kling-v4.0/reference-to-video for AI agents and LLMs