Vidu API 示例

Vidu 系列（例如 Vidu Q3）通过 Agentsflare 网关提供视频生成能力，通常使用通用异步接口：

-- 创建端点：POST https://api.agentsflare.com/v1/videos/generations -- 查询端点：GET https://api.agentsflare.com/v1/async-result/{task_id}

• 认证：Authorization: Bearer <API_KEY>

参考原厂文档：Vidu 详细说明（原厂）： https://zhipu-ai.feishu.cn/wiki/NSH1wPKppiVgsUkeqdccBo0qnAG

请求参数（摘要）

参数	必填	说明
model	是	例如 viduq3-turbo-text2video / viduq3-pro-img2video
prompt	是	文本提示，描述主体与动作
duration	是	视频时长（秒），常用 5
movement_amplitude	否	运动幅度，例如 low / medium / high
with_audio	否	是否生成音频，true / false
first_frame_image	条件	单图输入的首帧 URL（图生视频场景）
resolution	否	输出分辨率
aspect_ratio	否	画幅比，例如 16:9
callback_url	否	异步回调 URL
external_task_id	否	业务自定义任务 ID

文生视频（Text to Video）示例

单图生视频（Image to Video）示例

cURL

cURL

curl -X POST "https://api.agentsflare.com/v1/videos/generations" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "viduq3-pro-img2video",
    "prompt": "The man on the left has white light flashing in his glasses",
    "duration": 5,
    "first_frame_image": "https://example.com/first.png"
  }'

Python

import requests
import os

API_BASE = 'https://api.agentsflare.com/v1/videos/generations'
API_KEY = os.getenv('API_KEY')

payload = {
  'model': 'viduq3-pro-img2video',
  'prompt': 'The man on the left has white light flashing in his glasses',
  'duration': 5,
  'first_frame_image': 'https://example.com/first.png'
}

headers = {'Authorization': f'Bearer {API_KEY}', 'Content-Type': 'application/json'}
resp = requests.post(API_BASE, json=payload, headers=headers)
print(resp.status_code)
print(resp.text)

Node.js

const fetch = require('node-fetch');
const API_BASE = 'https://api.agentsflare.com/v1/videos/generations';
const API_KEY = process.env.API_KEY;

const payload = {
  model: 'viduq3-pro-img2video',
  prompt: 'The man on the left has white light flashing in his glasses',
  duration: 5,
  first_frame_image: 'https://example.com/first.png'
};

(async () => {
  const res = await fetch(API_BASE, {
    method: 'POST',
    headers: { 'Authorization': `Bearer ${API_KEY}`, 'Content-Type': 'application/json' },
    body: JSON.stringify(payload)
  });

  console.log(await res.text());
})();

Java

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class ViduImage2V {
  public static void main(String[] args) throws Exception {
    String apiBase = "https://api.agentsflare.com/v1/videos/generations";
    String apiKey = System.getenv("API_KEY");
    String json = "{\"model\":\"viduq3-pro-img2video\",\"prompt\":\"The man on the left has white light flashing in his glasses\",\"duration\":5,\"first_frame_image\":\"https://example.com/first.png\"}";

    HttpRequest req = HttpRequest.newBuilder()
      .uri(URI.create(apiBase))
      .header("Authorization", "Bearer " + apiKey)
      .header("Content-Type", "application/json")
      .POST(HttpRequest.BodyPublishers.ofString(json))
      .build();

    HttpResponse<String> resp = HttpClient.newHttpClient().send(req, HttpResponse.BodyHandlers.ofString());
    System.out.println(resp.statusCode());
    System.out.println(resp.body());
  }
}

查询任务示例

curl -X GET "https://api.agentsflare.com/v1/async-result/<task_id>" \
  -H "Authorization: Bearer $API_KEY"

---

支持的模型

以下模型可通过本接口调用（按推荐程度排序）：

• viduq3-pro-img2video New
• viduq3-turbo-text2video New
• viduq3-pro-text2video New
• viduq3-turbo-img2video New
• viduq3-turbo-img2video-frame New
• viduq3-pro-img2video-frame New

💡 提示

请求示例中的 model 字段可替换为上方任意模型名称。

curl -X POST "https://api.agentsflare.com/v1/videos/generations" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "viduq3-turbo-text2video",
    "prompt": "A silver spaceship glides above the sea at sunrise, cinematic light",
    "duration": 5,
    "movement_amplitude": "medium",
    "with_audio": true
  }'

import requests
import os

API_BASE = 'https://api.agentsflare.com/v1/videos/generations'
API_KEY = os.getenv('API_KEY')

payload = {
  'model': 'viduq3-turbo-text2video',
  'prompt': 'A silver spaceship glides above the sea at sunrise, cinematic light',
  'duration': 5,
  'movement_amplitude': 'medium',
  'with_audio': True
}

headers = {'Authorization': f'Bearer {API_KEY}', 'Content-Type': 'application/json'}
resp = requests.post(API_BASE, json=payload, headers=headers)
print(resp.status_code)
print(resp.text)

const fetch = require('node-fetch');
const API_BASE = 'https://api.agentsflare.com/v1/videos/generations';
const API_KEY = process.env.API_KEY;

const payload = {
  model: 'viduq3-turbo-text2video',
  prompt: 'A silver spaceship glides above the sea at sunrise, cinematic light',
  duration: 5,
  movement_amplitude: 'medium',
  with_audio: true
};

(async () => {
  const res = await fetch(API_BASE, {
    method: 'POST',
    headers: { 'Authorization': `Bearer ${API_KEY}`, 'Content-Type': 'application/json' },
    body: JSON.stringify(payload)
  });

  console.log(await res.text());
})();

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class ViduText2V {
  public static void main(String[] args) throws Exception {
    String apiBase = "https://api.agentsflare.com/v1/videos/generations";
    String apiKey = System.getenv("API_KEY");
    String json = "{\"model\":\"viduq3-turbo-text2video\",\"prompt\":\"A silver spaceship glides above the sea at sunrise, cinematic light\",\"duration\":5,\"movement_amplitude\":\"medium\",\"with_audio\":true}";

    HttpRequest req = HttpRequest.newBuilder()
      .uri(URI.create(apiBase))
      .header("Authorization", "Bearer " + apiKey)
      .header("Content-Type", "application/json")
      .POST(HttpRequest.BodyPublishers.ofString(json))
      .build();

    HttpResponse<String> resp = HttpClient.newHttpClient().send(req, HttpResponse.BodyHandlers.ofString());
    System.out.println(resp.statusCode());
    System.out.println(resp.body());
  }
}

:::