SDK 与代码示例

Seedance 2.0 API 使用标准 REST 接口，可直接用任意 HTTP 客户端调用，无需安装任何 SDK。本页按三种生成模式给出完整可复制代码。

Base URL

https://api.evolink.ai

所有示例请先 export EVOLINK_API_KEY="your-api-key-here"。

文生视频（text-to-video）

Python

import os
import time
import requests

API_KEY = os.environ["EVOLINK_API_KEY"]
BASE_URL = "https://api.evolink.ai"

headers = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

# 1. 创建任务
response = requests.post(
    f"{BASE_URL}/v1/videos/generations",
    headers=headers,
    json={
        "model": "seedance-2.0-text-to-video",
        "prompt": "夕阳下的海面，电影级广角镜头",
        "duration": 5,
        "quality": "720p",
        "aspect_ratio": "16:9"
    }
)
task_id = response.json()["id"]
print(f"Task created: {task_id}")

# 2. 轮询
while True:
    result = requests.get(f"{BASE_URL}/v1/tasks/{task_id}", headers=headers).json()

    if result["status"] == "completed":
        print(f"Video URL: {result['results'][0]}")
        break
    if result["status"] == "failed":
        print("Generation failed")
        break

    print(f"Progress: {result['progress']}%")
    time.sleep(5)

Node.js

const API_KEY = process.env.EVOLINK_API_KEY;
const BASE_URL = "https://api.evolink.ai";

const headers = {
    "Authorization": `Bearer ${API_KEY}`,
    "Content-Type": "application/json"
};

// 1. 创建任务
const createRes = await fetch(`${BASE_URL}/v1/videos/generations`, {
    method: "POST",
    headers,
    body: JSON.stringify({
        model: "seedance-2.0-text-to-video",
        prompt: "夕阳下的海面，电影级广角镜头",
        duration: 5,
        quality: "720p",
        aspect_ratio: "16:9"
    })
});
const { id: taskId } = await createRes.json();
console.log(`Task created: ${taskId}`);

// 2. 轮询
while (true) {
    const res = await fetch(`${BASE_URL}/v1/tasks/${taskId}`, { headers });
    const result = await res.json();

    if (result.status === "completed") {
        console.log(`Video URL: ${result.results[0]}`);
        break;
    }
    if (result.status === "failed") {
        console.log("Generation failed");
        break;
    }

    console.log(`Progress: ${result.progress}%`);
    await new Promise(r => setTimeout(r, 5000));
}

cURL

# 1. 创建任务
curl -X POST https://api.evolink.ai/v1/videos/generations \
  -H "Authorization: Bearer $EVOLINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0-text-to-video",
    "prompt": "夕阳下的海面，电影级广角镜头",
    "duration": 5,
    "quality": "720p"
  }'

# 响应: {"id": "task-unified-...", "status": "pending", ...}

# 2. 查询状态
curl https://api.evolink.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $EVOLINK_API_KEY"

图生视频（image-to-video）

首帧驱动（1 张图）

response = requests.post(
    f"{BASE_URL}/v1/videos/generations",
    headers=headers,
    json={
        "model": "seedance-2.0-image-to-video",
        "prompt": "模特缓缓转身，头发在风中轻轻飘动",
        "image_urls": ["https://example.com/portrait.jpg"],
        "duration": 5,
        "quality": "720p",
        "aspect_ratio": "adaptive"
    }
)

首尾帧过渡（2 张图）

response = requests.post(
    f"{BASE_URL}/v1/videos/generations",
    headers=headers,
    json={
        "model": "seedance-2.0-image-to-video",
        "prompt": "从黎明的海面平滑过渡到日落的同一片海",
        "image_urls": [
            "https://example.com/sunrise.jpg",
            "https://example.com/sunset.jpg"
        ],
        "duration": 6,
        "quality": "720p"
    }
)

参考生视频（reference-to-video）

同时使用图片、视频、音频参考素材：

response = requests.post(
    f"{BASE_URL}/v1/videos/generations",
    headers=headers,
    json={
        "model": "seedance-2.0-reference-to-video",
        "prompt": (
            "参考视频 1 的第一人称视角和镜头节奏；"
            "以音频 1 作为整段背景音乐。"
            "内容：年轻骑手穿越雨后的城市街道，霓虹反射在湿漉漉的路面上。"
        ),
        "image_urls": ["https://example.com/rider-style.jpg"],
        "video_urls": ["https://example.com/pov-reference.mp4"],
        "audio_urls": ["https://example.com/synthwave-bgm.mp3"],
        "duration": 10,
        "quality": "720p",
        "aspect_ratio": "16:9"
    }
)

注意：reference-to-video 没有 @Image1、@Video1 之类的标签语法。用自然语言描述每份素材的作用即可。

使用 Fast 系列

把 model 字段从 seedance-2.0-xxx 换成 seedance-2.0-fast-xxx，其它参数完全不变：

response = requests.post(
    f"{BASE_URL}/v1/videos/generations",
    headers=headers,
    json={
        "model": "seedance-2.0-fast-text-to-video",  # ← 唯一改动
        "prompt": "夕阳下的海面，电影级广角镜头",
        "duration": 5,
        "quality": "720p"
    }
)

详见 Fast 系列。

使用 Webhook 替代轮询

response = requests.post(
    f"{BASE_URL}/v1/videos/generations",
    headers=headers,
    json={
        "model": "seedance-2.0-text-to-video",
        "prompt": "一只弹钢琴的猫",
        "duration": 5,
        "callback_url": "https://yourapp.com/api/video-callback"
    }
)
# 任务完成时，你的回调端点会收到 POST 请求，包含与任务查询接口相同的响应体

详见 Webhooks。

兼容 OpenAI 客户端

本 API 遵循 OpenAI 风格的 REST 约定（Bearer Token、JSON body、统一响应结构），你可以用任意 HTTP 客户端库调用，无需专用 SDK。

相关文档

了解详情