bytedance/seedance-2.0/reference-to-video33 积分起 / 5 秒视频· 参考生视频

Seedance 2.0 是字节跳动的视频模型,支持文生视频、图生视频、参考场景和视频续写:4 到 15 秒,480p 到 4K,声音在同一次生成里完成。参考模式最多接收九张图、三段视频和三条音频,所以产品或演员能在一组镜头里保持不变。

在 POST /jobs/createTask 里把模型名写成 bytedance/seedance-2.0/reference-to-video 即可调用,33 积分/ 5 秒视频起(US$0.33)。新账户送 30 积分,可以先在 Playground 里免费试。

  • 生成视频
  • 图生视频
  • 参考生视频
  • 视频续写
  • 最高 4K
  • 4–15 秒
  • 自带声音
  • 首尾帧
  • 最多 9 张参考图
  • 6 种画幅
调用名bytedance/seedance-2.0/reference-to-video
接口POST 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": "bytedance/seedance-2.0/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": "adaptive",
    "resolution": "720p",
    "duration_seconds": 5,
    "generate_audio": true
  }
}'

# 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"

input 按下面的 Schema 生成,原样就能通过校验。把提示词和链接换成你自己的即可。

价格

选项积分 /秒≈ 美元
resolution 480pwith_video true6.47US$0.065
resolution 480pwith_video false10.5US$0.11
resolution 720pwith_video true13.92US$0.14
resolution 720pwith_video false22.8US$0.23
resolution 1080pwith_video true34.26US$0.34
resolution 1080pwith_video false56.1US$0.56
resolution 4Kwith_video false116.7US$1.17
resolution 4Kwith_video true116.7US$1.17

1 积分 = $0.01 · 全部选项及价格:GET /models/bytedance/seedance-2.0/reference-to-video

每个任务按整数积分向上取整,所以最低档跑一次是 33 积分/ 5 秒视频(US$0.33)。

限制

视频时长
4–15 s
分辨率
480p · 720p · 1080p · 4K
画面比例
21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 · adaptive
参考音频
3
参考图
9
参考视频
3

参数

这些字段来自我们校验每个请求所用的同一份 Schema。没列出的字段会被拒绝。

有些字段互相关联(例如至少要有一个参考素材)。确切规则见下方的原始 Schema。

  • promptstring必填

    What to generate: subject, action, camera movement and mood.

  • reference_image_urlsarray<string>视情况必填

    希望结果保留的人物、服装或场景的参考图。

    范围
    0 – 9 items · image/jpeg, image/png, image/webp, image/gif
  • reference_video_urlsarray<string>视情况必填影响价格

    希望结果跟随其动作、运镜或风格的参考视频。

    范围
    0 – 3 items · video/mp4, video/webm, video/quicktime
  • reference_audio_urlsarray<string>可选

    要匹配的声音:人声、音乐或节奏。

    范围
    0 – 3 items · audio/mpeg, audio/wav
  • aspect_ratiostring可选

    画面形状:横版、方形或竖版。

    默认值
    "adaptive"
    可选值
    "21:9""16:9""4:3""1:1""3:4""9:16""adaptive"
  • resolutionstring可选影响价格

    输出尺寸。越大越清晰,价格也越高。

    默认值
    "720p"
    可选值
    "480p""720p""1080p""4k"
  • duration_secondsinteger可选影响价格

    视频时长,按秒计费。

    默认值
    5
    可选值
    -1456789101112131415
  • generate_audioboolean可选影响价格

    加上和画面匹配的声音:人声、环境音和音效。

    默认值
    true
  • seedinteger可选

    用同一个数字,结果就能复现。

    范围
    0 – 2147483647
  • return_last_frameboolean可选

    Also return the clip’s final frame as a separate image.

    默认值
    false
  • bitrate_modestring可选

    Encoding bitrate of the delivered file: standard, or high for crisper detail and a larger file.

    默认值
    "standard"
    可选值
    "standard""high"
  • watermarkboolean可选

    Add the model’s visible "AI generated" watermark to the video.

    默认值
    false
原始 JSON Schema
{
  "additionalProperties": false,
  "anyOf": [
    {
      "required": [
        "reference_image_urls"
      ]
    },
    {
      "required": [
        "reference_video_urls"
      ]
    }
  ],
  "properties": {
    "aspect_ratio": {
      "default": "adaptive",
      "description": "Aspect ratio of the generated video.",
      "enum": [
        "21:9",
        "16:9",
        "4:3",
        "1:1",
        "3:4",
        "9:16",
        "adaptive"
      ],
      "type": "string"
    },
    "bitrate_mode": {
      "default": "standard",
      "description": "Encoding bitrate of the delivered file: standard, or high for crisper detail and a larger file.",
      "enum": [
        "standard",
        "high"
      ],
      "type": "string"
    },
    "duration_seconds": {
      "default": 5,
      "description": "Clip length in seconds. This is the billed quantity. Pass -1 for smart duration: the model picks the length itself instead of a fixed number.",
      "enum": [
        -1,
        4,
        5,
        6,
        7,
        8,
        9,
        10,
        11,
        12,
        13,
        14,
        15
      ],
      "type": "integer"
    },
    "generate_audio": {
      "default": true,
      "description": "Generate a native soundtrack synchronised to the picture.",
      "type": "boolean"
    },
    "prompt": {
      "description": "What to generate: subject, action, camera movement and mood.",
      "type": "string"
    },
    "reference_audio_urls": {
      "description": "Reference audio URLs (total length 15 s or less, up to 3). The generated soundtrack follows them.",
      "items": {
        "contentMediaType": [
          "audio/mpeg",
          "audio/wav"
        ],
        "type": "string"
      },
      "maxItems": 3,
      "type": "array"
    },
    "reference_image_urls": {
      "description": "Reference image URLs (up to 9). Characters, style and scene composition are carried over from them.",
      "items": {
        "contentMediaType": [
          "image/jpeg",
          "image/png",
          "image/webp",
          "image/gif"
        ],
        "type": "string"
      },
      "maxItems": 9,
      "type": "array"
    },
    "reference_video_urls": {
      "description": "Reference video URLs (total length 15 s or less, up to 3). Motion and pacing are carried over from them. Reference footage is billed on the same linear basis as clip length, so longer references cost more.",
      "items": {
        "contentMediaType": [
          "video/mp4",
          "video/webm",
          "video/quicktime"
        ],
        "type": "string"
      },
      "maxItems": 3,
      "type": "array"
    },
    "resolution": {
      "default": "720p",
      "description": "Output resolution. Super-resolution tiers are not offered.",
      "enum": [
        "480p",
        "720p",
        "1080p",
        "4k"
      ],
      "type": "string"
    },
    "return_last_frame": {
      "default": false,
      "description": "Also return the clip’s final frame as a separate image.",
      "type": "boolean"
    },
    "seed": {
      "description": "Random seed. Omit to let the model pick one.",
      "maximum": 2147483647,
      "minimum": 0,
      "type": "integer"
    },
    "watermark": {
      "default": false,
      "description": "Add the model’s visible \"AI generated\" watermark to the video.",
      "type": "boolean"
    }
  },
  "required": [
    "prompt"
  ],
  "type": "object"
}

Seedance 2.0 的真实成片

提示词Copy the camera language of the reference clip — low, drifting right, never cutting — but stage it in the tiled corridor from reference image 1. One figure walking away from us, footsteps timed to the pulse in the reference track.
通过 API 发出的同一个请求
{
  "model": "bytedance/seedance-2.0/reference-to-video",
  "input": {
    "prompt": "Copy the camera language of the reference clip — low, drifting right, never cutting — but stage it in the tiled corridor from reference image 1. One figure walking away from us, footsteps timed to the pulse in the reference track.",
    "reference_image_urls": [
      "https://media.popnow.ai/influencer/examples/ava.webp"
    ],
    "aspect_ratio": "21:9",
    "resolution": "1080p",
    "duration_seconds": 10,
    "generate_audio": true
  }
}

这条是从上传的文件开始的:把示例链接换成你自己的文件链接。

响应、轮询与回调

所有模型的用法都一样:先建任务,再轮询,或者等回调。

先报价

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": "bytedance/seedance-2.0/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": "adaptive",
    "resolution": "720p",
    "duration_seconds": 5,
    "generate_audio": true
  }
}'

请求体和 createTask 相同。它返回预计扣费和最高可能扣费,不会真正运行。

已受理

HTTP
HTTP/1.1 202 Accepted

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

HTTP 202 表示任务已受理,积分先冻结、还没有扣。最终扣费不会超过冻结额。

查询状态

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

每隔几秒查一次并逐步拉长间隔,state 变成 succeeded、failed、canceled 或 expired 时停止。

完成的任务

JSON
{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
    "model": "bytedance/seedance-2.0/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"
}

在 expiresAt 之前从 url 下载。之后要新链接,请调用 POST /common/download-url。

校验回调

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
});

设置了 callBackUrl,我们会把完成的任务发给你。先用原始请求体校验签名,再信任它。

上传本地文件

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.

公开的 https 链接可以直接用。本地文件要先经过 upload-url 和 commit。