Seedream 5.0 Pro is LIVE | Try in Image Generator →
Home/Explore/Kuaishou/Kling Video O1/Reference To Video

Kling Video O1 Reference to Video

kwaivgi /

Kling Omni Video O1 Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Ready-to-use REST API, best performance, no cold starts, affordable pricing.

image-to-video
Input

Idle

$0.56per run·~17 / $10

Next:

ExamplesView all

Use reference image 1 as the female character and reference image 2 as the male character. Blend their appearances into the same semi-realistic anime / 3D animated style so they look like they belong in one world, keeping their facial features clearly recognizable. Create a cozy 10-second Christmas scene in a warm living room at night: a large decorated Christmas tree with glowing fairy lights and red ornaments stands in the background, soft yellow light from the tree and a fireplace. The two characters are sitting together on a rug in front of the tree, facing each other slightly, holding mugs of hot chocolate, chatting and laughing gently as if sharing Christmas stories. The camera starts with a medium two-shot of both of them, then slowly dollies in and slightly arcs around them, with shallow depth of field and bokeh from the Christmas lights. Atmosphere: warm, festive, romantic, soft film look, subtle lens glow from the lights, no text on screen.

The robot is dancing with the teddy bear

The girl in Picture 1 is skateboarding in the environment of Picture 2

A women in ornate dresses, wearing a necklace and a handbag, is walking on the street.

The banana cat plays games by the Christmas tree.

Related Models

README

Kling Omni Video O1 — Reference-to-Video

Kling Omni Video O1 is Kuaishou's groundbreaking unified multi-modal video model. The Reference-to-Video mode creates new video content based on subject references — maintaining character, prop, and scene identity while generating entirely new creative scenarios.

Key Capabilities

Multi-Reference Subject Creation

Build subjects from multiple reference viewpoints:

  • Extract features from character, prop, or scene images
  • Maintain consistent identity in generated videos
  • Create new scenarios with familiar subjects

Subject Consistency Technology

Advanced feature extraction ensures:

  • Stable character appearance across all frames
  • Consistent clothing, accessories, and props
  • Maintained facial features and expressions
  • Coherent scene elements and backgrounds

Creative Freedom

Generate entirely new content while preserving identity:

  • New poses and actions
  • Different scenes and environments
  • Various camera angles and movements
  • Fresh creative scenarios

Core Features

  • Identity Lock — Subject features remain consistent throughout video
  • Multi-Angle Support — Use references from various viewpoints
  • Scene Flexibility — Place subjects in new environments
  • Motion Control — Guide actions with text prompts

How to Use

  1. Upload Reference Images Provide one or more images of your subject (character, object, or scene).

  2. Describe the Scenario Write a prompt for the new video content.

Example: "The character walking through a futuristic city at night, neon lights reflecting on wet streets"

  1. Set Parameters Choose duration, resolution, and output format.

  2. Generate Receive video with your subject in the new scenario.

Pricing

Reference TypePrice per Second
Image Reference$0.112
Video Reference$0.168

$0.112/s for image reference only; $0.168/s when using video reference.

Pro Tips

  • Use multiple reference angles for better identity capture
  • Provide clear, high-resolution reference images
  • Describe actions and environments clearly in prompts
  • Works best for characters, products, and distinct objects

Note

  • If the input reference parameters include a video, then the number of reference images that can be entered will be reduced to 4.
Note:This website uses AI models provided by third parties.

Kling Video O1 Reference To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/kwaivgi/kling-video-o1/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 Video O1 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": true,
    "aspect_ratio": "16:9",
    "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-video-o1/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=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 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' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/kwaivgi/kling-video-o1/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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "keep_original_sound": true,
        "aspect_ratio": "16:9",
        "duration": 5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  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": True,
    "aspect_ratio": "16:9",
    "duration": 5
}

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-video-o1/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 = task.get("urls", {}).get("get") or 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"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Kling Video O1 Reference To Video API — Frequently asked questions

What is the Kling Video O1 Reference To Video API?

Kling Video O1 Reference To Video is a Kuaishou model for video generation from images, exposed as a REST API on WaveSpeedAI. Kling Omni Video O1 Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Ready-to-use REST API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Kling Video O1 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 production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-video-o1-reference-to-video.

How much does Kling Video O1 Reference To Video cost per run?

Kling Video O1 Reference To Video starts at $0.56 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 Video O1 Reference To Video accept?

Key inputs: `prompt`, `images`, `video`, `aspect_ratio`, `duration`, `keep_original_sound`. 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-video-o1-reference-to-video.

How long does Kling Video O1 Reference To Video take to generate?

Median end-to-end generation time on WaveSpeedAI is around 143 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Kling Video O1 Reference To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Kuaishou). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Kling Video O1 Reference to Video | Fast Image-to-Video API | WaveSpeedAI