Vidu Q3 系列

POST

tasks

Vidu Q3 系列

curl --request POST \
  --url https://www.qingbo.dev/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "resolution": "<string>",
  "duration": 123,
  "image_urls": [
    "<string>"
  ],
  "callback_url": "<string>",
  "callback_events": [
    "<string>"
  ]
}
'

import requests

url = "https://www.qingbo.dev/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "resolution": "<string>",
    "duration": 123,
    "image_urls": ["<string>"],
    "callback_url": "<string>",
    "callback_events": ["<string>"]
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    action: '<string>',
    prompt: '<string>',
    resolution: '<string>',
    duration: 123,
    image_urls: ['<string>'],
    callback_url: '<string>',
    callback_events: ['<string>']
  })
};

fetch('https://www.qingbo.dev/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://www.qingbo.dev/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"duration\": 123,\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://www.qingbo.dev/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"duration\": 123,\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")
  .asString();

{
  "task_id": "task-wave1775285160b950328499",
  "model": "vidu-q3",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

生数科技 Vidu Q3 系列视频生成模型,参考生视频(R2V) 是看家本事 — 接受公网图作为主体 / 风格参考,prompt 负责描述动作与镜头,人物外观由参考图决定,适合 角色一致性 / 风格延续 / 多机位切换 三类场景。 两档可选:

vidu-q3 — 标准档,日常默认首选,镜头切换更聪明,540p / 720p / 1080p,1-16 秒。比例由参考图决定,不接受 aspect_ratio 参数
vidu-q3-mix — 混剪档,支持多图混剪生成连贯视频,540p / 720p / 1080p,1-16 秒,支持 aspect_ratio,适合短剧分镜重组、广告素材二创

按 分辨率 × 时长 计费,每秒单价,1-16 秒任意整数。

定价

模型	540p	720p	1080p
`vidu-q3`	`$0.045` / 秒	`$0.09` / 秒	`$0.1125` / 秒
`vidu-q3-mix`	`$0.1125` / 秒	`$0.1125` / 秒	`$0.135` / 秒

实际费用 = 单价 / 秒 × duration。例:vidu-q3 1080p 5 秒 = $0.1125 × 5 = $0.5625。

调用示例

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vidu-q3",
    "prompt": "黄昏的海滩,女孩迎着夕阳奔跑,长发飞扬,电影感光影",
    "duration": 5,
    "resolution": "1080p"
  }'

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vidu-q3",
    "prompt": "人物缓缓转身,镜头推近",
    "image_urls": ["https://cdn.example.com/portrait.jpg"],
    "duration": 5,
    "resolution": "1080p"
  }'

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vidu-q3",
    "prompt": "保持角色形象,在森林中奔跑,镜头跟随",
    "image_urls": [
      "https://cdn.example.com/char-1.jpg",
      "https://cdn.example.com/style-ref.jpg"
    ],
    "duration": 6,
    "resolution": "1080p"
  }'

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vidu-q3-mix",
    "prompt": "镜头在多个场景间平滑切换,氛围连贯",
    "image_urls": [
      "https://cdn.example.com/scene-1.jpg",
      "https://cdn.example.com/scene-2.jpg",
      "https://cdn.example.com/scene-3.jpg"
    ],
    "duration": 8,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }'

{
  "task_id": "task-wave1775285160b950328499",
  "model": "vidu-q3",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

提交后用 GET /v1/tasks/{task_id} 轮询状态,详见任务系统。

可用模型

模型 ID	分辨率	时长(秒)	Actions	aspect_ratio	备注
`vidu-q3`	540p / 720p / 1080p	1-16	generate	不支持	标准档,日常首选,比例由参考图决定
`vidu-q3-mix`	540p / 720p / 1080p	1-16	generate	支持	混剪档,多素材连贯生成

通用参数

string

必填

模型 ID,可选值:

vidu-q3
vidu-q3-mix

string

默认值:"generate"

操作类型,固定为 generate。传入 image_urls 即自动走 参考生 / 图生视频,否则为文生视频

string

必填

视频描述文本,建议描述 动作 / 镜头 / 氛围,人物外观由 image_urls 决定

string

默认值:"720p"

输出分辨率,可选值:

540p
720p
1080p

integer

默认值:"5"

视频时长(秒),范围 1-16 任意整数

string[]

参考图片 URL 数组,作为主体 / 风格参考(R2V),或作为首帧 / 混剪素材

string

Webhook 回调地址,任务终态时调用。详见回调机制

string[]

订阅的回调事件,默认订阅终态(succeeded / failed / cancelled)

模型特定参数

vidu-q3
vidu-q3-mix

标准档无特定参数,所有可选项在通用参数中。

vidu-q3 不接受 aspect_ratio 参数,输出比例由参考图 / 模型决定。若需指定比例请用 vidu-q3-mix。

string

默认值:"16:9"

画面宽高比(仅 Mix 档支持),可选值:

16:9 — 横版宽屏
9:16 — 竖版长屏
1:1 — 正方形

Mix 档支持多张参考图混剪,系统会智能转场,适合短剧分镜重组、广告素材二创。

资源限制

项目	限制
参考图片(`image_urls`)	JPG / PNG / WEBP,需公网可下载链接
Prompt 长度	建议 ≤ 2000 字符
视频时长	1-16 秒任意整数
输出	MP4,链接 24 小时有效

相关文档

任务系统详解 — 任务状态机 / 轮询节奏 / 异步推送
请求响应格式 — 通用错误码 / Headers / 限流
认证 — API Key 申请与使用

Vidu Q3 系列

curl --request POST \
  --url https://www.qingbo.dev/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "resolution": "<string>",
  "duration": 123,
  "image_urls": [
    "<string>"
  ],
  "callback_url": "<string>",
  "callback_events": [
    "<string>"
  ]
}
'

import requests

url = "https://www.qingbo.dev/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "resolution": "<string>",
    "duration": 123,
    "image_urls": ["<string>"],
    "callback_url": "<string>",
    "callback_events": ["<string>"]
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    action: '<string>',
    prompt: '<string>',
    resolution: '<string>',
    duration: 123,
    image_urls: ['<string>'],
    callback_url: '<string>',
    callback_events: ['<string>']
  })
};

fetch('https://www.qingbo.dev/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://www.qingbo.dev/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"duration\": 123,\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://www.qingbo.dev/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"duration\": 123,\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")
  .asString();

{
  "task_id": "task-wave1775285160b950328499",
  "model": "vidu-q3",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

文本生成

图像生成

视频生成

音频处理

工具与嵌入

任务管理

定价

调用示例

可用模型

通用参数

模型特定参数

资源限制

相关文档

​定价

​调用示例

​可用模型

​通用参数

​模型特定参数

​资源限制

​相关文档

定价

调用示例

可用模型

通用参数

模型特定参数

资源限制

相关文档