> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apimart.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Pembuatan Video SkyReels V4

>  - Dua tingkat model: Cepat (dioptimalkan untuk kecepatan) dan Std (dioptimalkan untuk kualitas)
- Tiga mode dirutekan otomatis oleh field permintaan: Teks-ke-Video (T2V), Gambar-ke-Video (I2V), Referensi Multimodal (Omni)
- Resolusi 480p / 720p / 1080p, durasi 3 ~ 15 detik
- Fitur lanjutan: frame pertama/akhir/kunci, gambar referensi, video referensi, kolase grid, perpanjangan video, sinkronisasi audio
- Mode pemrosesan async, mengembalikan ID tugas untuk kueri berikutnya 

<RequestExample>
  ```bash cURL theme={null}
  curl --request POST \
    --url https://api.apimart.ai/v1/videos/generations \
    --header 'Authorization: Bearer <token>' \
    --header 'Content-Type: application/json' \
    --data '{
      "model": "skyreels-v4-fast",
      "prompt": "A serene forest at sunset with golden light filtering through the trees.",
      "duration": 5,
      "resolution": "1080p",
      "aspect_ratio": "16:9",
      "prompt_optimizer": true
    }'
  ```

  ```python Python theme={null}
  import requests

  url = "https://api.apimart.ai/v1/videos/generations"

  payload = {
      "model": "skyreels-v4-fast",
      "prompt": "A serene forest at sunset with golden light filtering through the trees.",
      "duration": 5,
      "resolution": "1080p",
      "aspect_ratio": "16:9",
      "prompt_optimizer": True
  }

  headers = {
      "Authorization": "Bearer <token>",
      "Content-Type": "application/json"
  }

  response = requests.post(url, json=payload, headers=headers)

  print(response.json())
  ```

  ```javascript JavaScript theme={null}
  const url = "https://api.apimart.ai/v1/videos/generations";

  const payload = {
    model: "skyreels-v4-fast",
    prompt: "A serene forest at sunset with golden light filtering through the trees.",
    duration: 5,
    resolution: "1080p",
    aspect_ratio: "16:9",
    prompt_optimizer: true
  };

  const headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
  };

  fetch(url, {
    method: "POST",
    headers: headers,
    body: JSON.stringify(payload)
  })
    .then(response => response.json())
    .then(data => console.log(data))
    .catch(error => console.error('Error:', error));
  ```

  ```go Go theme={null}
  package main

  import (
      "bytes"
      "encoding/json"
      "fmt"
      "io/ioutil"
      "net/http"
  )

  func main() {
      url := "https://api.apimart.ai/v1/videos/generations"

      payload := map[string]interface{}{
          "model":            "skyreels-v4-fast",
          "prompt":           "A serene forest at sunset with golden light filtering through the trees.",
          "duration":         5,
          "resolution":       "1080p",
          "aspect_ratio":     "16:9",
          "prompt_optimizer": true,
      }

      jsonData, _ := json.Marshal(payload)

      req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
      req.Header.Set("Authorization", "Bearer <token>")
      req.Header.Set("Content-Type", "application/json")

      client := &http.Client{}
      resp, err := client.Do(req)
      if err != nil {
          panic(err)
      }
      defer resp.Body.Close()

      body, _ := ioutil.ReadAll(resp.Body)
      fmt.Println(string(body))
  }
  ```

  ```java Java theme={null}
  import java.net.http.HttpClient;
  import java.net.http.HttpRequest;
  import java.net.http.HttpResponse;
  import java.net.URI;

  public class Main {
      public static void main(String[] args) throws Exception {
          String url = "https://api.apimart.ai/v1/videos/generations";

          String payload = """
          {
            "model": "skyreels-v4-fast",
            "prompt": "A serene forest at sunset with golden light filtering through the trees.",
            "duration": 5,
            "resolution": "1080p",
            "aspect_ratio": "16:9",
            "prompt_optimizer": true
          }
          """;

          HttpClient client = HttpClient.newHttpClient();
          HttpRequest request = HttpRequest.newBuilder()
              .uri(URI.create(url))
              .header("Authorization", "Bearer <token>")
              .header("Content-Type", "application/json")
              .POST(HttpRequest.BodyPublishers.ofString(payload))
              .build();

          HttpResponse<String> response = client.send(request,
              HttpResponse.BodyHandlers.ofString());

          System.out.println(response.body());
      }
  }
  ```

  ```php PHP theme={null}
  <?php

  $url = "https://api.apimart.ai/v1/videos/generations";

  $payload = [
      "model" => "skyreels-v4-fast",
      "prompt" => "A serene forest at sunset with golden light filtering through the trees.",
      "duration" => 5,
      "resolution" => "1080p",
      "aspect_ratio" => "16:9",
      "prompt_optimizer" => true
  ];

  $ch = curl_init($url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
  curl_setopt($ch, CURLOPT_POST, true);
  curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
  curl_setopt($ch, CURLOPT_HTTPHEADER, [
      "Authorization: Bearer <token>",
      "Content-Type: application/json"
  ]);

  $response = curl_exec($ch);
  curl_close($ch);

  echo $response;
  ?>
  ```

  ```ruby Ruby theme={null}
  require 'net/http'
  require 'json'
  require 'uri'

  url = URI("https://api.apimart.ai/v1/videos/generations")

  payload = {
    model: "skyreels-v4-fast",
    prompt: "A serene forest at sunset with golden light filtering through the trees.",
    duration: 5,
    resolution: "1080p",
    aspect_ratio: "16:9",
    prompt_optimizer: true
  }

  http = Net::HTTP.new(url.host, url.port)
  http.use_ssl = true

  request = Net::HTTP::Post.new(url)
  request["Authorization"] = "Bearer <token>"
  request["Content-Type"] = "application/json"
  request.body = payload.to_json

  response = http.request(request)
  puts response.body
  ```

  ```swift Swift theme={null}
  import Foundation

  let url = URL(string: "https://api.apimart.ai/v1/videos/generations")!

  let payload: [String: Any] = [
      "model": "skyreels-v4-fast",
      "prompt": "A serene forest at sunset with golden light filtering through the trees.",
      "duration": 5,
      "resolution": "1080p",
      "aspect_ratio": "16:9",
      "prompt_optimizer": true
  ]

  var request = URLRequest(url: url)
  request.httpMethod = "POST"
  request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
  request.setValue("application/json", forHTTPHeaderField: "Content-Type")
  request.httpBody = try? JSONSerialization.data(withJSONObject: payload)

  let task = URLSession.shared.dataTask(with: request) { data, response, error in
      if let error = error {
          print("Error: \(error)")
          return
      }

      if let data = data, let responseString = String(data: data, encoding: .utf8) {
          print(responseString)
      }
  }

  task.resume()
  ```

  ```csharp C# theme={null}
  using System;
  using System.Net.Http;
  using System.Text;
  using System.Threading.Tasks;

  class Program
  {
      static async Task Main(string[] args)
      {
          var url = "https://api.apimart.ai/v1/videos/generations";

          var payload = @"{
              ""model"": ""skyreels-v4-fast"",
              ""prompt"": ""A serene forest at sunset with golden light filtering through the trees."",
              ""duration"": 5,
              ""resolution"": ""1080p"",
              ""aspect_ratio"": ""16:9"",
              ""prompt_optimizer"": true
          }";

          using var client = new HttpClient();
          client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

          var content = new StringContent(payload, Encoding.UTF8, "application/json");
          var response = await client.PostAsync(url, content);
          var result = await response.Content.ReadAsStringAsync();

          Console.WriteLine(result);
      }
  }
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "code": 200,
    "data": [
      {
        "status": "submitted",
        "task_id": "task_01KPEY5H3NQ2W8D7T6VB3F9GR4"
      }
    ]
  }
  ```

  ```json 400 theme={null}
  {
    "error": {
      "code": 400,
      "message": "Invalid request parameters",
      "type": "invalid_request_error"
    }
  }
  ```

  ```json 401 theme={null}
  {
    "error": {
      "code": 401,
      "message": "Authentication failed, please check your API key",
      "type": "authentication_error"
    }
  }
  ```

  ```json 402 theme={null}
  {
    "error": {
      "code": 402,
      "message": "Insufficient account balance, please top up and try again",
      "type": "payment_required"
    }
  }
  ```

  ```json 422 theme={null}
  {
    "error": {
      "code": 422,
      "message": "Parameter conflict or invalid value (e.g. I2V and Omni fields passed simultaneously)",
      "type": "invalid_request_error"
    }
  }
  ```

  ```json 429 theme={null}
  {
    "error": {
      "code": 429,
      "message": "Too many requests, please try again later",
      "type": "rate_limit_error"
    }
  }
  ```

  ```json 500 theme={null}
  {
    "error": {
      "code": 500,
      "message": "Internal server error, please retry later",
      "type": "server_error"
    }
  }
  ```
</ResponseExample>

## Otorisasi

<ParamField header="Authorization" type="string" required>
  Semua endpoint API memerlukan autentikasi Bearer Token

  Dapatkan API Key Anda:

  Kunjungi [Halaman Manajemen API Key](https://apimart.ai/keys) untuk mendapatkan API Key Anda

  Tambahkan ke header permintaan:

  ```
  Authorization: Bearer YOUR_API_KEY
  ```
</ParamField>

## Mode Pembuatan

SkyReels V4 otomatis merutekan ke mode yang benar berdasarkan field permintaan — **tanpa `mode` field diperlukan**:

| Mode                            | Pemicu                                                                       | Kemampuan                                                                                |
| ------------------------------- | ---------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
| **T2V** (Teks-ke-Video)         | Hanya `prompt` + field umum                                                  | Pembuatan murni berbasis teks                                                            |
| **I2V** (Gambar-ke-Video)       | Salah satu dari `first_frame_image` / `end_frame_image` / `mid_frame_images` | Kontrol frame pertama/akhir/kunci                                                        |
| **Omni** (Referensi Multimodal) | Salah satu dari `ref_images` / `ref_videos`                                  | Subjek referensi, kolase grid, gerakan referensi, perpanjangan video, sinkronisasi audio |

<Warning>
  **Saling eksklusif secara ketat**: Field I2V (`first_frame_image` / `end_frame_image` / `mid_frame_images`) dan field Omni (`ref_images` / `ref_videos`) tidak dapat digunakan bersama, jika tidak akan mengembalikan 422.
</Warning>

<Note>
  **Mekanisme `@tag`**: Saat menggunakan `mid_frame_images` / `ref_images` / `ref_videos`, setiap elemen harus mendeklarasikan `tag` yang dimulai dengan `@` (misalnya, `@image1`, `@Actor-1`, `@video1`), dan `tag` **harus muncul di `prompt`**.

  Anggap `prompt` sebagai "skrip" dan `tag` sebagai "penunjuk karakter" ke aset tertentu (gambar / video). Misalnya, prompt seperti `"@Actor-1 walks into the scene of @video1"` menginstruksikan sistem untuk memasukkan gambar referensi subjek yang ditautkan ke `@Actor-1` dan gerakan referensi yang ditautkan ke `@video1` ke dalam proses pembuatan.
</Note>

## Parameter Permintaan

### Field Umum

<ParamField body="model" type="string" required>
  Tersedia dua tingkat model:

  | Model              | Posisi                                                  | Kasus Penggunaan                                         |
  | ------------------ | ------------------------------------------------------- | -------------------------------------------------------- |
  | `skyreels-v4-fast` | Prioritas kecepatan                                     | Pratinjau cepat, pembuatan batch, konten harian          |
  | `skyreels-v4-std`  | Prioritas kualitas (25\~30% lebih mahal daripada Cepat) | Shot penting, kebutuhan detail tinggi, pengiriman formal |

  <Warning>
    **Field `model` harus disediakan secara eksplisit — tidak ada nilai default.**
  </Warning>

  <Tip>
    **Harga sangat terkait dengan resolusi dan apakah `ref_videos` digunakan**: 1080p jauh lebih mahal daripada 480p / 720p; tier dengan `ref_videos` (input video) berbiaya \~1,5 \~ 2× dibandingkan yang tanpa itu. Output audio dan video secara bersamaan belum didukung.
  </Tip>
</ParamField>

<ParamField body="prompt" type="string" required>
  Prompt teks, maksimum **1280 tokens**

  Jelaskan adegan, subjek, aksi, dan gaya secara detail untuk hasil pembuatan yang lebih baik.

  Saat menggunakan `ref_images` / `ref_videos` / `mid_frame_images`, `prompt` **harus berisi** `@tag` terkait (misalnya, `@Actor-1`, `@video1`, `@image1`).

  Contoh: `"@Actor-1 walks through a neon-lit street at night."`
</ParamField>

<ParamField body="duration" type="integer" default="5">
  Durasi video output (detik)

  * Rentang: `[3, 15]`
  * Default: `5`

  <Warning>
    Saat `ref_videos.type=reference` disediakan, `duration` ditimpa oleh durasi video referensi (maks. 10 detik).
  </Warning>
</ParamField>

<ParamField body="resolution" type="string" default="1080p">
  Resolusi video

  Opsi:

  * `480p`
  * `720p`
  * `1080p` (default)
</ParamField>

<ParamField body="aspect_ratio" type="string" default="16:9">
  Rasio aspek

  Opsi:

  * `16:9` (default)
  * `4:3`
  * `1:1`
  * `9:16`
  * `3:4`

  <Warning>
    **`aspect_ratio` diabaikan dalam mode I2V** (rasio output ditentukan oleh gambar input); juga diabaikan saat Omni dikombinasikan dengan `ref_videos`.
  </Warning>
</ParamField>

<ParamField body="prompt_optimizer" type="boolean" default="true">
  Apakah mengoptimalkan prompt secara otomatis

  Jika diaktifkan, sistem otomatis mengoptimalkan prompt Anda untuk hasil pembuatan yang lebih baik.
</ParamField>

### Field Khusus I2V

<ParamField body="first_frame_image" type="string">
  URL gambar frame pertama (jpg / jpeg / png / gif / bmp)

  Saat disediakan, gambar ini digunakan sebagai **frame awal** video.
</ParamField>

<ParamField body="end_frame_image" type="string">
  URL gambar frame akhir (jpg / jpeg / png / gif / bmp)

  Saat disediakan, gambar ini digunakan sebagai **frame akhir** video. Dapat dikombinasikan dengan `first_frame_image` untuk kontrol frame pertama dan terakhir.
</ParamField>

<ParamField body="mid_frame_images" type="object[]">
  Daftar keyframe tengah, **hingga 6**. Setiap elemen memiliki struktur berikut:

  <Expandable title="mid_frame_images elemen">
    <ResponseField name="tag" type="string" required>
      Harus dimulai dengan `@` dan muncul di `prompt`, misalnya `@image1`
    </ResponseField>

    <ResponseField name="image_url" type="string" required>
      URL gambar (jpg / jpeg / png / gif / bmp)
    </ResponseField>

    <ResponseField name="time_stamp" type="integer" default="-1">
      Timestamp kemunculan (detik). Default `-1` (tidak ditentukan); jika ditentukan, harus memenuhi `0 < time_stamp < duration`.
    </ResponseField>
  </Expandable>
</ParamField>

### Field Khusus Omni

<ParamField body="ref_images" type="object[]">
  Daftar gambar referensi (semua elemen harus memiliki `type`). Setiap elemen memiliki struktur berikut:

  <Expandable title="ref_images elemen">
    <ResponseField name="tag" type="string" required>
      Harus dimulai dengan `@` dan muncul di `prompt`, misalnya `@Actor-1`
    </ResponseField>

    <ResponseField name="type" type="string" required>
      Tipe referensi:

      * `image` - Gambar referensi biasa (panjang daftar 1~~3; panjang setiap `image_urls` 1~~5)
      * `grid` - Kolase grid, yaitu satu gambar yang terdiri dari beberapa tile (misalnya 2×2, 3×3); panjang daftar harus = 1, `image_urls` harus 1 gambar
    </ResponseField>

    <ResponseField name="image_urls" type="string[]" required>
      Array URL gambar
    </ResponseField>

    <ResponseField name="audio_url" type="string">
      URL audio suara (**hanya didukung saat `type=image`**, durasi audio ≤ 15 detik)
    </ResponseField>
  </Expandable>
</ParamField>

<ParamField body="ref_videos" type="object[]">
  Daftar video referensi, **hingga 1**. Setiap elemen memiliki struktur berikut:

  <Expandable title="ref_videos elemen">
    <ResponseField name="tag" type="string" required>
      Harus dimulai dengan `@` dan muncul di `prompt`, misalnya `@video1`
    </ResponseField>

    <ResponseField name="type" type="string" required>
      Tipe referensi:

      * `reference` - Referensi gerakan / subjek, **menimpa `duration`** (mengikuti durasi video referensi, maks. 10 detik), membawa audio video input secara default; **dapat dikombinasikan dengan `ref_images.type=image`**
      * `extend` - Perpanjangan video, ditagih berdasarkan `duration`; **tidak dapat dikombinasikan dengan `ref_images`**
    </ResponseField>

    <ResponseField name="video_url" type="string" required>
      URL video (MP4 / MOV, durasi ≤ 15 detik)
    </ResponseField>
  </Expandable>
</ParamField>

## Skenario yang Didukung

Skenario berikut **didukung oleh keduanya** `skyreels-v4-fast` dan `skyreels-v4-std`:

| Skenario                        | Mode | Field Wajib                               | Kasus Penggunaan Umum                                              |
| ------------------------------- | ---- | ----------------------------------------- | ------------------------------------------------------------------ |
| Teks-ke-Video                   | T2V  | `prompt`                                  | Murni berbasis teks, shot konsep cepat                             |
| Gambar-ke-Video - Frame Pertama | I2V  | `first_frame_image`                       | Still-to-video dengan frame awal yang ditentukan                   |
| Gambar-ke-Video - Frame Akhir   | I2V  | `end_frame_image`                         | Menentukan frame penutup                                           |
| Gambar-ke-Video - Keyframes     | I2V  | `mid_frame_images` (1 \~ 6)               | Frame pertama + akhir + tengah untuk pengaturan tempo yang presisi |
| Omni Subjek Tunggal/Multi       | Omni | `ref_images` (`type=image`)               | Konsistensi karakter, framing multi-subjek                         |
| Omni Kolase Grid                | Omni | `ref_images` (`type=grid`, 1 gambar)      | Video proses langkah demi langkah (tutorial, resep, demo)          |
| Omni Gerakan Referensi          | Omni | `ref_videos` (`type=reference`)           | Mereplikasi gerakan, subjek, atau gaya video referensi             |
| Omni Perpanjangan Video         | Omni | `ref_videos` (`type=extend`)              | Melanjutkan video yang ada dengan konten baru                      |
| Omni Sinkronisasi Audio         | Omni | `ref_images` (`type=image`) + `audio_url` | Narasi manusia digital, lip-sync berbasis audio                    |

## Batasan Parameter

Melanggar salah satu di bawah ini akan menyebabkan permintaan ditolak dengan respons **422**, **tidak ada biaya yang dikenakan**:

| Parameter                       | Batasan                                                                                                                                       |
| ------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------- |
| `prompt`                        | Maks. 1280 token                                                                                                                              |
| `duration`                      | `[3, 15]` detik; ditimpa oleh durasi video referensi (maks. 10 dtk) saat `ref_videos.type=reference`                                          |
| `resolution`                    | Hanya `480p` / `720p` / `1080p`                                                                                                               |
| `aspect_ratio`                  | `16:9` / `4:3` / `1:1` / `9:16` / `3:4`; diabaikan dalam I2V; diabaikan saat Omni membawa `ref_videos`                                        |
| `mid_frame_images`              | Hingga 6; `time_stamp` harus `-1` atau dalam `(0, duration)`                                                                                  |
| `ref_images` secara keseluruhan | Semua elemen harus berbagi `type` yang sama; tidak dapat berdampingan dengan field I2V                                                        |
| `ref_images.type=grid`          | Panjang daftar harus = 1; `image_urls` harus 1 gambar                                                                                         |
| `ref_images.type=image`         | Panjang daftar 1 \~ 3; panjang setiap `image_urls` 1 \~ 5                                                                                     |
| `ref_images.audio_url`          | Hanya didukung saat `type=image`, audio ≤ 15 detik                                                                                            |
| `ref_videos`                    | Hingga 1; `video_url` MP4 / MOV, ≤ 15 detik                                                                                                   |
| `ref_videos.type=reference`     | Menimpa `duration` yang diminta (maks. 10 dtk), dapat dikombinasikan dengan `ref_images.type=image`, membawa audio video input secara default |
| `ref_videos.type=extend`        | Ditagih berdasarkan `duration` yang diminta; **tidak dapat dikombinasikan dengan `ref_images`**                                               |
| Field `tag`                     | Harus dimulai dengan `@` dan muncul di `prompt`                                                                                               |
| Eksklusi I2V / Omni             | Field I2V dan field Omni tidak dapat digunakan bersama                                                                                        |

## Respons

<ResponseField name="code" type="integer">
  Kode status respons, 200 jika berhasil
</ResponseField>

<ResponseField name="data" type="array">
  Array data respons

  <Expandable title="Elemen Array">
    <ResponseField name="status" type="string">
      Status tugas, `submitted` saat pertama kali dikirim
    </ResponseField>

    <ResponseField name="task_id" type="string">
      Pengidentifikasi tugas unik untuk mengueri status dan hasil tugas
    </ResponseField>
  </Expandable>
</ResponseField>

## Contoh Permintaan

### Kasus 1: Teks-ke-Video (Minimal)

```json theme={null}
{
  "model": "skyreels-v4-fast",
  "prompt": "A serene forest at sunset with golden light filtering through the trees."
}
```

### Kasus 2: Teks-ke-Video (Parameter Lengkap)

```json theme={null}
{
  "model": "skyreels-v4-std",
  "prompt": "A serene forest at sunset.",
  "duration": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "prompt_optimizer": true
}
```

### Kasus 3: Gambar-ke-Video - Frame Pertama

```json theme={null}
{
  "model": "skyreels-v4-fast",
  "prompt": "Slowly pull the camera back to reveal the entire scene.",
  "first_frame_image": "https://example.com/start.png",
  "duration": 5
}
```

### Kasus 4: Gambar-ke-Video - Frame Pertama/Akhir + Keyframe Tengah

```json theme={null}
{
  "model": "skyreels-v4-std",
  "prompt": "The King summons a flying dragon. @image1 The dragon lowers. The King mounts and flies away.",
  "duration": 8,
  "resolution": "1080p",
  "first_frame_image": "https://example.com/k2v_0.png",
  "end_frame_image":   "https://example.com/k2v_2.png",
  "mid_frame_images": [
    { "tag": "@image1", "image_url": "https://example.com/k2v_1.png", "time_stamp": 3 }
  ]
}
```

### Kasus 5: Omni - Subjek Referensi Tunggal

```json theme={null}
{
  "model": "skyreels-v4-fast",
  "prompt": "@Actor-1 walks through a neon-lit street at night.",
  "ref_images": [
    { "tag": "@Actor-1", "type": "image", "image_urls": ["https://example.com/actor.jpg"] }
  ]
}
```

### Kasus 6: Omni - Multi-Subjek + Video Gerakan Referensi

```json theme={null}
{
  "model": "skyreels-v4-fast",
  "prompt": "The man from @image_1 imitates the move on the left in @video_1. The woman from @image_2 imitates the right side.",
  "duration": 5,
  "ref_images": [
    { "tag": "@image_1", "type": "image", "image_urls": ["https://example.com/a.png"] },
    { "tag": "@image_2", "type": "image", "image_urls": ["https://example.com/b.png"] }
  ],
  "ref_videos": [
    { "tag": "@video_1", "type": "reference", "video_url": "https://example.com/motion.mp4" }
  ]
}
```

<Warning>
  Kasus ini menggunakan `ref_videos.type=reference`, sehingga \*\* `duration` akan ditimpa oleh durasi aktual video referensi\*\* (maks. 10 detik). Meskipun `"duration": 5` dikirim di sini, durasi video final mengikuti video referensi.
</Warning>

### Kasus 7: Omni - Kolase Grid

```json theme={null}
{
  "model": "skyreels-v4-fast",
  "prompt": "Create a video showing how to make tomato and egg noodles based on @image1.",
  "ref_images": [
    { "tag": "@image1", "type": "grid", "image_urls": ["https://example.com/recipe_grid.png"] }
  ]
}
```

### Kasus 8: Omni - Perpanjangan Video (extend)

```json theme={null}
{
  "model": "skyreels-v4-fast",
  "prompt": "Video extended @video1, someone walks over and sits on the sofa.",
  "duration": 8,
  "ref_videos": [
    { "tag": "@video1", "type": "extend", "video_url": "https://example.com/source.mp4" }
  ]
}
```

### Kasus 9: Omni - Sinkronisasi Audio (Berbasis Suara)

```json theme={null}
{
  "model": "skyreels-v4-std",
  "prompt": "@Actor-1 speaks with a calm tone.",
  "ref_images": [
    {
      "tag": "@Actor-1",
      "type": "image",
      "image_urls": ["https://example.com/actor.jpg"],
      "audio_url":  "https://example.com/voice.mp3"
    }
  ]
}
```

<Note>
  **Kueri Hasil Tugas**

  Pembuatan video adalah tugas asinkron yang mengembalikan `task_id` saat dikirim. Gunakan endpoint [Dapatkan Status Tugas](/id/api-reference/tasks/status) untuk mengueri progres dan hasil pembuatan.
</Note>