Prendi la chiave API

di Kuaishou

Il modello unificato di Kling: crea, anima, usa riferimenti e modifica fino al 4K

kling/o3/video-editDa 18,78 creditial secondo · 0,19 USD
  • Fino a 4K
  • Clip da 3 a 15 s
  • Audio incluso
  • Fotogramma iniziale e finale
  • Fino a 7 immagini di riferimento
  • 3 formati
  • Crea video
  • Da immagine a video
  • Da riferimenti a video
  • Modifica video
Guarda gli esempi

Lo chiami con il nome di modello kling/o3/video-edit su POST /jobs/createTask, da 18,78 crediti al secondo (0,19 USD). I nuovi account ricevono 30 crediti gratuiti per provarlo prima nel Playground.

Nome del modellokling/o3/video-edit
EndpointPOST 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/video-edit",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
    "resolution": "720p"
  }
}'

# 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"

L’input è costruito dallo schema qui sotto, quindi supera la verifica così com’è. Sostituisci prompt e link con i tuoi.

Prezzo

OpzioneCrediti al secondo≈ USD
resolution 720p18,780,19 USD
resolution 1080p25,20,25 USD

1 credito = 0,01 $ · Tutte le opzioni e i prezzi: GET /models/kling/o3/video-edit

Limiti

Risoluzioni
720p · 1080p
Immagini di riferimento
4
Lunghezza del prompt (caratteri)
2,500
Caricamento massimo
10 MB

Parametri

Questi campi vengono dallo stesso schema con cui verifichiamo ogni richiesta. I campi non elencati vengono rifiutati.

  • promptstringObbligatorio

    Say what to change in the clip: the subject, outfit, setting, style or weather. Anything you do not mention stays as it is.

    Intervallo
    1 – 2500 chars
  • video_urlstringObbligatorio

    La clip su cui lavorare.

    Intervallo
    video/mp4, video/webm, video/quicktime
  • elementsarray<object>Facoltativo

    One named subject to bring into the edited clip, built from 2 to 4 images of the same character or object. Write @name in the prompt where it should appear.

    Intervallo
    0 – 1 items
    Campi interni
    • elements[].descriptionstringObbligatorio

      One line on who or what this subject is.

      Intervallo
      1 – 500 chars
    • elements[].image_urlsarray<string>Obbligatorio

      2 to 4 images of this subject.

      Intervallo
      2 – 4 items
    • elements[].namestringObbligatorio

      Name for this subject; write @name in the prompt where it should appear.

      Intervallo
      1 – 64 chars
    • elements[].reference_audio_urlsarray<string>Facoltativo

      Optional voice samples for this subject, 5 to 30 seconds each.

  • reference_image_urlsarray<string>Facoltativo

    Immagini di persone, abiti o luoghi che il risultato deve mantenere.

    Intervallo
    1 – 4 items · image/jpeg, image/png, image/webp, image/gif · ≤ 10 MB
  • resolutionstringFacoltativoCambia il prezzo

    Dimensione dell'output. Più grande è più nitido e costa di più.

    Predefinito
    "720p"
    Valori ammessi
    "720p""1080p"
  • keep_original_audiobooleanFacoltativo

    Keep the source clip's own sound in the result.

    Predefinito
    true
JSON Schema grezzo
{
  "additionalProperties": false,
  "properties": {
    "elements": {
      "description": "One named subject to bring into the edited clip, built from 2 to 4 images of the same character or object. Write @name in the prompt where it should appear.",
      "items": {
        "additionalProperties": false,
        "properties": {
          "description": {
            "description": "One line on who or what this subject is.",
            "maxLength": 500,
            "minLength": 1,
            "type": "string"
          },
          "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"
          }
        },
        "required": [
          "name",
          "description",
          "image_urls"
        ],
        "type": "object"
      },
      "maxItems": 1,
      "type": "array"
    },
    "keep_original_audio": {
      "default": true,
      "description": "Keep the source clip's own sound in the result.",
      "type": "boolean"
    },
    "prompt": {
      "description": "Say what to change in the clip: the subject, outfit, setting, style or weather. Anything you do not mention stays as it is.",
      "maxLength": 2500,
      "minLength": 1,
      "type": "string"
    },
    "reference_image_urls": {
      "description": "Optional reference images, up to 4, for a new character, outfit, object or style. Refer to them as <<<image_1>>>, <<<image_2>>> and so on.",
      "items": {
        "contentMediaType": [
          "image/jpeg",
          "image/png",
          "image/webp",
          "image/gif"
        ],
        "format": "uri",
        "type": "string"
      },
      "maxItems": 4,
      "minItems": 1,
      "type": "array"
    },
    "resolution": {
      "default": "720p",
      "description": "Output resolution. Higher tiers cost more per second.",
      "enum": [
        "720p",
        "1080p"
      ],
      "type": "string"
    },
    "video_url": {
      "contentMediaType": [
        "video/mp4",
        "video/webm",
        "video/quicktime"
      ],
      "description": "Source clip to edit, 3 to 10 seconds, at least 720 pixels on each side. The result is as long as this clip.",
      "format": "uri",
      "type": "string"
    }
  },
  "required": [
    "prompt",
    "video_url"
  ],
  "type": "object"
}

Un risultato reale di Kling O3

PromptDress the rider on the left, in the blue shirt, in the wine-red velvet jacket from <<<image_1>>>. Keep the rider in the red shirt, the street, the bicycles, the yellow tram, the riders' movement and the camera move exactly as they are.
La stessa richiesta tramite API
{
  "model": "kling/o3/video-edit",
  "input": {
    "prompt": "Dress the rider on the left, in the blue shirt, in the wine-red velvet jacket from <<<image_1>>>. Keep the rider in the red shirt, the street, the bicycles, the yellow tram, the riders' movement and the camera move exactly as they are.",
    "video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
    "resolution": "720p"
  }
}

Questo risultato parte da un file caricato: metti il tuo link al posto di quello d’esempio.

Risposte, polling e callback

Tutti i modelli funzionano allo stesso modo: crei un task, poi lo interroghi o aspetti la callback.

Prima il prezzo

cURL
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/video-edit",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
    "resolution": "720p"
  }
}'

Stesso corpo di createTask. Restituisce l’addebito previsto e quello massimo possibile, senza eseguire nulla.

Accettata

HTTP
HTTP/1.1 202 Accepted

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
    "state": "queued"
  },
  "request_id": "req_example_create"
}

HTTP 202 significa che il task è stato accettato e i crediti sono riservati, non ancora addebitati. L’addebito finale non supera mai la riserva.

Controlla lo stato

cURL
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Controlla ogni pochi secondi allungando via via l’intervallo e fermati quando state è succeeded, failed, canceled o expired.

Task completato

JSON
{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
    "model": "kling/o3/video-edit",
    "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"
}

Scarica dall’url prima di expiresAt. Ti serve un link nuovo più tardi? Chiedilo con POST /common/download-url.

Verifica una callback

Node.js
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
});

Con callBackUrl impostata ti inviamo il task completato. Verifica la firma sul corpo grezzo prima di fidarti.

Invia un file locale

cURL
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.

I link https pubblici funzionano così come sono. I file locali passano prima da upload-url e commit.