kling/o3/reference-to-video51クレジットから / 5秒の動画· 参照から動画Kling O3(Kling 3.0 Omni)reference-to-video は、人物・衣装・場所などの参照画像を最大 7 枚、ひとつの新しいショットに登場させます。720p・1080p・4K の 3〜15 秒で、ネイティブ音声は任意です。
POST /jobs/createTask でモデル名に kling/o3/reference-to-video を指定すれば呼び出せます。51クレジット/ 5秒の動画から($0.51)。新規アカウントには 30 クレジットが付くので、まず Playground で無料で試せます。
- 動画を作成
- 画像から動画
- 参照から動画
- 動画を編集
- 最大4K
- 3〜15秒
- 音声付き
- 開始・終了フレーム
- 参照画像は最大7枚
- 3種類のアスペクト比
kling/o3/reference-to-videoPOST https://api.popnow.ai/api/v1/jobs/createTask# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-d '{
"model": "kling/o3/reference-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"reference_image_urls": [
"https://media.popnow.ai/influencer/examples/ava.webp"
],
"aspect_ratio": "16:9",
"resolution": "720p",
"duration_seconds": 5,
"shot_type": "single"
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $POPNOW_API_KEY"// Node 18+ (or any runtime with fetch). Keep the API key on your server.
const BASE = "https://api.popnow.ai/api/v1";
const headers = { Authorization: `Bearer ${process.env.POPNOW_API_KEY}` };
const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
async function call(path, init = {}) {
const res = await fetch(BASE + path, { ...init, headers: { ...headers, ...init.headers } });
const body = await res.json();
if (body.code !== 200) throw new Error(`${body.code} ${body.msg}`);
return body.data;
}
const { taskId } = await call("/jobs/createTask", {
method: "POST",
headers: { "Content-Type": "application/json", "Idempotency-Key": crypto.randomUUID() },
body: JSON.stringify({
"model": "kling/o3/reference-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"reference_image_urls": [
"https://media.popnow.ai/influencer/examples/ava.webp"
],
"aspect_ratio": "16:9",
"resolution": "720p",
"duration_seconds": 5,
"shot_type": "single"
}
}),
});
// Poll with backoff. A finished task may still be copying files: wait while an asset is pending.
let task;
for (let delay = 2000; ; delay = Math.min(delay * 1.5, 15000)) {
await sleep(delay);
task = await call(`/jobs/recordInfo?taskId=${taskId}`);
const copying = (task.output?.assets ?? []).some((a) => a.pending && !a.unavailable);
if (["succeeded", "failed", "canceled", "expired"].includes(task.state) && !copying) break;
}
if (task.state !== "succeeded") throw new Error(`${task.state}: ${task.errorMessage ?? "no detail"}`);
// Each asset has a signed url (no API key needed) that expires at expiresAt: save the file.
for (const asset of task.output.assets) console.log(asset.url);import os, time, uuid, requests
BASE = "https://api.popnow.ai/api/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['POPNOW_API_KEY']}"}
def call(method, path, **kwargs):
body = requests.request(method, BASE + path, headers={**HEADERS, **kwargs.pop("headers", {})}, timeout=30, **kwargs).json()
if body["code"] != 200:
raise RuntimeError(f'{body["code"]} {body["msg"]}')
return body["data"]
task_id = call(
"POST",
"/jobs/createTask",
headers={"Idempotency-Key": str(uuid.uuid4())}, # reuse it if you retry
json={
"model": "kling/o3/reference-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"reference_image_urls": [
"https://media.popnow.ai/influencer/examples/ava.webp"
],
"aspect_ratio": "16:9",
"resolution": "720p",
"duration_seconds": 5,
"shot_type": "single"
}
},
)["taskId"]
# Poll with backoff. A finished task may still be copying files: wait while an asset is pending.
delay = 2.0
while True:
time.sleep(delay)
task = call("GET", "/jobs/recordInfo", params={"taskId": task_id})
assets = (task.get("output") or {}).get("assets") or []
copying = any(a.get("pending") and not a.get("unavailable") for a in assets)
if task["state"] in ("succeeded", "failed", "canceled", "expired") and not copying:
break
delay = min(delay * 1.5, 15.0)
if task["state"] != "succeeded":
raise RuntimeError(f'{task["state"]}: {task.get("errorMessage", "no detail")}')
# Each asset has a signed url (no API key needed) that expires at expiresAt: save the file.
for asset in assets:
print(asset["url"])input は下のスキーマから作っているので、このままで検証を通ります。プロンプトとリンクを自分のものに替えてください。
料金
| オプション | クレジット /秒 | ≈ USD |
|---|---|---|
generate_audio falseresolution 720p | 10.08 | $0.10 |
generate_audio falseresolution 1080p | 13.44 | $0.13 |
generate_audio trueresolution 720p | 13.44 | $0.13 |
generate_audio falseresolution 720pwith_video true | 15.12 | $0.15 |
generate_audio trueresolution 1080p | 16.8 | $0.17 |
generate_audio falseresolution 1080pwith_video true | 20.16 | $0.20 |
generate_audio falseresolution 4K | 62.85 | $0.63 |
generate_audio trueresolution 4K | 62.85 | $0.63 |
1クレジット = $0.01 · すべてのオプションと料金:GET /models/kling/o3/reference-to-video
タスクごとにクレジットは整数に切り上げられるため、最安の設定で 1 回実行すると 51クレジット/ 5秒の動画($0.51)です。
制限
- 動画の長さ
- 3–15 s
- 解像度
- 720p · 1080p · 4K
- アスペクト比
- 16:9 · 9:16 · 1:1
- 参照画像
- 7
- 参照動画
- 1
- プロンプトの長さ(文字)
- 2,500
- アップロードの上限
- 10 MB
パラメーター
これらのフィールドは、すべてのリクエストの検証に使っているのと同じスキーマから来ています。ここにないフィールドは拒否されます。
フィールドどうしが関係している場合があります(たとえば参照素材が最低1つ必要など)。正確なルールは下の JSON スキーマを確認してください。
promptstring必須Say who and what each reference is (<<<image_1>>>, <<<image_2>>> and so on) and describe the shot they should produce.
reference_image_urlsarray<string>必須結果に残したい人物・衣装・場所の参照画像。
reference_video_urlsarray<string>任意料金が変わります動き・カメラワーク・スタイルを真似させたい参照動画。
elementsarray<object>任意One named subject built from 2 to 4 images of the same character or object. Write @name in the prompt where it should appear. 4K only.
内部のフィールド
elements[].descriptionstring必須One line on who or what this subject is.
elements[].image_urlsarray<string>必須2 to 4 images of this subject.
elements[].namestring必須Name for this subject; write @name in the prompt where it should appear.
elements[].end_msinteger任意Trim end, in milliseconds, when the subject is taken from a video clip. Defaults to 8000.
elements[].reference_audio_urlsarray<string>任意Optional voice samples for this subject, 5 to 30 seconds each.
elements[].start_msinteger任意Trim start, in milliseconds, when the subject is taken from a video clip. Defaults to 0.
aspect_ratiostring任意画面の形:横長、正方形、縦長。
resolutionstring任意料金が変わります出力サイズ。大きいほど鮮明で、料金も上がります。
generate_audioboolean任意料金が変わります映像に合った音(声、環境音、効果音)を付けます。
keep_original_audioboolean任意Keep the reference video's own sound in the result. Only matters when a reference video is given.
duration_secondsinteger任意料金が変わります動画の長さ。1秒ごとに課金されます。
shot_typestring任意single keeps one continuous shot; multi lets the model cut the prompt into several shots on its own; customize follows the shot list you give in multi_prompt.
multi_promptarray<object>条件付きで必須Shot list for shot_type customize: one entry per shot, in order, each with its own prompt and length in seconds. The lengths must add up to duration_seconds.
内部のフィールド
multi_prompt[].duration_secondsinteger必須Length of this shot in whole seconds, 1 to 15.
multi_prompt[].promptstring必須What happens in this shot, up to 512 characters.
JSON スキーマ(原文)
{
"additionalProperties": false,
"allOf": [
{
"if": {
"properties": {
"shot_type": {
"const": "customize"
}
},
"required": [
"shot_type"
]
},
"then": {
"required": [
"multi_prompt"
]
}
}
],
"properties": {
"aspect_ratio": {
"default": "16:9",
"description": "Output aspect ratio.",
"enum": [
"16:9",
"9:16",
"1:1"
],
"type": "string"
},
"duration_seconds": {
"default": 5,
"description": "Output length in whole seconds, from 3 to 15. Billed per second.",
"maximum": 15,
"minimum": 3,
"type": "integer"
},
"elements": {
"description": "One named subject built from 2 to 4 images of the same character or object. Write @name in the prompt where it should appear. 4K only.",
"items": {
"additionalProperties": false,
"properties": {
"description": {
"description": "One line on who or what this subject is.",
"maxLength": 500,
"minLength": 1,
"type": "string"
},
"end_ms": {
"description": "Trim end, in milliseconds, when the subject is taken from a video clip. Defaults to 8000.",
"minimum": 0,
"type": "integer"
},
"image_urls": {
"description": "2 to 4 images of this subject.",
"items": {
"format": "uri",
"type": "string"
},
"maxItems": 4,
"minItems": 2,
"type": "array"
},
"name": {
"description": "Name for this subject; write @name in the prompt where it should appear.",
"maxLength": 64,
"minLength": 1,
"type": "string"
},
"reference_audio_urls": {
"description": "Optional voice samples for this subject, 5 to 30 seconds each.",
"items": {
"format": "uri",
"type": "string"
},
"type": "array"
},
"start_ms": {
"description": "Trim start, in milliseconds, when the subject is taken from a video clip. Defaults to 0.",
"minimum": 0,
"type": "integer"
}
},
"required": [
"name",
"description",
"image_urls"
],
"type": "object"
},
"maxItems": 1,
"type": "array"
},
"generate_audio": {
"default": false,
"description": "Generate a native soundtrack (voices, effects, ambience) with the picture. Audio costs more per second. Not available with a reference video.",
"type": "boolean"
},
"keep_original_audio": {
"default": true,
"description": "Keep the reference video's own sound in the result. Only matters when a reference video is given.",
"type": "boolean"
},
"multi_prompt": {
"description": "Shot list for shot_type customize: one entry per shot, in order, each with its own prompt and length in seconds. The lengths must add up to duration_seconds.",
"items": {
"additionalProperties": false,
"properties": {
"duration_seconds": {
"description": "Length of this shot in whole seconds, 1 to 15.",
"maximum": 15,
"minimum": 1,
"type": "integer"
},
"prompt": {
"description": "What happens in this shot, up to 512 characters.",
"maxLength": 512,
"minLength": 1,
"type": "string"
}
},
"required": [
"prompt",
"duration_seconds"
],
"type": "object"
},
"maxItems": 6,
"minItems": 1,
"type": "array"
},
"prompt": {
"description": "Say who and what each reference is (<<<image_1>>>, <<<image_2>>> and so on) and describe the shot they should produce.",
"maxLength": 2500,
"minLength": 1,
"type": "string"
},
"reference_image_urls": {
"description": "Reference images for characters, objects, outfits or places, up to 7. Refer to them in the prompt as <<<image_1>>>, <<<image_2>>> and so on.",
"items": {
"contentMediaType": [
"image/jpeg",
"image/png",
"image/webp",
"image/gif"
],
"format": "uri",
"type": "string"
},
"maxItems": 7,
"minItems": 1,
"type": "array"
},
"reference_video_urls": {
"description": "Optional reference video (one clip) whose motion, camera or characters the new shot should draw on. Refer to it in the prompt as <<<video_1>>>. With a video, use up to 4 reference images. A run with a reference video is billed at a higher per-second rate.",
"items": {
"contentMediaType": [
"video/mp4",
"video/webm",
"video/quicktime"
],
"format": "uri",
"type": "string"
},
"maxItems": 1,
"minItems": 1,
"type": "array"
},
"resolution": {
"default": "720p",
"description": "Output resolution. Higher tiers cost more per second.",
"enum": [
"720p",
"1080p",
"4k"
],
"type": "string"
},
"shot_type": {
"default": "single",
"description": "single keeps one continuous shot; multi lets the model cut the prompt into several shots on its own; customize follows the shot list you give in multi_prompt.",
"enum": [
"single",
"multi",
"customize"
],
"type": "string"
}
},
"required": [
"prompt",
"reference_image_urls"
],
"type": "object"
}レスポンス、ポーリング、コールバック
どのモデルも使い方は同じです。タスクを作成し、ポーリングするかコールバックを待ちます。
先に見積もる
curl -X POST https://api.popnow.ai/api/v1/jobs/quote \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling/o3/reference-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"reference_image_urls": [
"https://media.popnow.ai/influencer/examples/ava.webp"
],
"aspect_ratio": "16:9",
"resolution": "720p",
"duration_seconds": 5,
"shot_type": "single"
}
}'本文は createTask と同じです。想定される請求額と最大の請求額を返し、何も実行しません。
受付済み
HTTP/1.1 202 Accepted
{
"code": 200,
"msg": "success",
"data": {
"taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
"state": "queued"
},
"request_id": "req_example_create"
}HTTP 202 はタスクを受け付けたという意味です。クレジットは確保されただけで、まだ引き落とされていません。最終的な請求額が確保額を超えることはありません。
状態の確認
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $POPNOW_API_KEY"間隔を少しずつ空けながら数秒ごとに確認し、state が succeeded、failed、canceled、expired のいずれかになったら止めます。
完了したタスク
{
"code": 200,
"msg": "success",
"data": {
"taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
"model": "kling/o3/reference-to-video",
"state": "succeeded",
"output": {
"assets": [
{
"url": "https://cdn.popnow.ai/tasks/task_01k3m8x9q2z4v7n5p6r8s0t1w3/output.mp4?signature=FROM_RESPONSE",
"expiresAt": "2026-10-17T12:20:00Z",
"mime": "video/mp4",
"width": 1280,
"height": 720,
"durationSeconds": 5
}
]
},
"settled": true
},
"request_id": "req_example_record"
}expiresAt までに url からダウンロードしてください。あとで新しいリンクが必要なら POST /common/download-url を使います。
コールバックを検証する
import { createHash, createHmac, timingSafeEqual } from "node:crypto";
import express from "express";
const app = express();
// express.raw keeps the exact bytes that were signed; express.json would not match.
app.post("/hooks/popnow", express.raw({ type: "application/json" }), (req, res) => {
const timestamp = req.header("X-Webhook-Timestamp");
const signature = req.header("X-Webhook-Signature") ?? "";
const body = JSON.parse(req.body.toString("utf8"));
const taskId = body.data?.taskId ?? body.task_id;
const digest = createHash("sha256").update(req.body).digest("hex");
const expected = createHmac("sha256", process.env.POPNOW_WEBHOOK_SECRET)
.update(`${taskId}.${timestamp}.${digest}`)
.digest("base64");
const ok = expected.length === signature.length && timingSafeEqual(Buffer.from(expected), Buffer.from(signature));
// Check the signature first, then reject anything older than five minutes.
if (!ok || Math.abs(Date.now() / 1000 - Number(timestamp)) > 300) return res.status(401).end();
res.status(200).end(); // answer fast, then fetch the task and store its files
});callBackUrl を指定すると、完了したタスクをお送りします。信頼する前に、生のリクエスト本文で署名を確認してください。
ローカルファイルを送る
curl -X POST https://api.popnow.ai/api/v1/common/upload-url \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contentType": "image/png", "bytes": 482113}'
# PUT the file bytes to data.uploadUrl with every header in data.headers, then commit it:
curl -X POST https://api.popnow.ai/api/v1/files/$FILE_ID/commit \
-H "Authorization: Bearer $POPNOW_API_KEY"
# The commit returns a popnow://f/... reference. Put it in any image, video or
# audio field of the task input instead of a public https URL.公開 https リンクはそのまま使えます。ローカルファイルは先に upload-url と commit を通します。

