HappyHorse

HappyHorse 支持文生视频、图生视频、参考图生视频与视频编辑。

API 接口

操作	端点	模式
视频生成任务	POST /v1/async/videos/generations	仅异步

模型

模型 id	说明
happyhorse-1.0	文生视频 / 图生视频；也可通过 providerOptions 做参考图生视频 / 视频编辑。seconds：3–15。

价格

按 n × seconds × 单价(resolution) 计费。默认 1080p。

模型	720p	1080p
happyhorse-1.0	13/秒	23/秒

请求字段

字段	类型	必填	说明
model	string	是	happyhorse-1.0
prompt	string	是	1–2000 字符
seconds	integer	是	3–15
resolution	string	否	720p / 1080p（默认）
n	integer	否	默认 1
image	string | string[]	否	图生视频公网 URL
providerOptions	object	否	可选模型扩展参数。详见下方 providerOptions。

providerOptions

字段	类型	说明
aspect_ratio	string	16:9 / 9:16 / 1:1 / 4:3 / 3:4
action	string	生成模式：text-to-video / image-to-video / reference-to-video / video-edit
reference_images	array	reference-to-video 的参考图
image_with_roles	object[]	需要时使用的带角色参考图
url	string	video-edit 的源视频 URL
audio_setting	string	编辑时的音频处理：auto 或 origin
seed	integer	随机种子，用于尽量复现结果
watermark	boolean	是否加水印

示例

cURL

curl https://api.pixapi.ai/v1/async/videos/generations \
  -H "Authorization: Bearer $PIXAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "happyhorse-1.0",
  "prompt": "柔和产品展示，镜头缓慢环绕",
  "n": 1,
  "seconds": 5,
  "resolution": "1080p",
  "providerOptions": {
    "aspect_ratio": "16:9",
    "action": "text-to-video"
  }
}'

Python

import os
import requests

response = requests.post(
    "https://api.pixapi.ai/v1/async/videos/generations",
    headers={
        "Authorization": f"Bearer {os.environ['PIXAPI_KEY']}",
        "Content-Type": "application/json",
    },
    json={
    "model": "happyhorse-1.0",
    "prompt": "柔和产品展示，镜头缓慢环绕",
    "n": 1,
    "seconds": 5,
    "resolution": "1080p",
    "providerOptions": {
        "aspect_ratio": "16:9",
        "action": "text-to-video"
    }
},
)
response.raise_for_status()
task = response.json()
print(task["id"])

JavaScript

const response = await fetch('https://api.pixapi.ai/v1/async/videos/generations', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.PIXAPI_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "happyhorse-1.0",
  "prompt": "柔和产品展示，镜头缓慢环绕",
  "n": 1,
  "seconds": 5,
  "resolution": "1080p",
  "providerOptions": {
    "aspect_ratio": "16:9",
    "action": "text-to-video"
  }
}),
});

if (!response.ok) {
  throw new Error(await response.text());
}

const task = await response.json();
console.log(task.id);

Go

package main

import (
  "bytes"
  "fmt"
  "io"
  "net/http"
  "os"
)

func main() {
  body := []byte(`{
  "model": "happyhorse-1.0",
  "prompt": "柔和产品展示，镜头缓慢环绕",
  "n": 1,
  "seconds": 5,
  "resolution": "1080p",
  "providerOptions": {
    "aspect_ratio": "16:9",
    "action": "text-to-video"
  }
}`)

  req, err := http.NewRequest(
    "POST",
    "https://api.pixapi.ai/v1/async/videos/generations",
    bytes.NewBuffer(body),
  )
  if err != nil {
    panic(err)
  }
  req.Header.Set("Authorization", "Bearer "+os.Getenv("PIXAPI_KEY"))
  req.Header.Set("Content-Type", "application/json")

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

  result, _ := io.ReadAll(resp.Body)
  fmt.Println(string(result))
}

响应

返回已提交任务。轮询 GET /v1/tasks/{id} 获取结果。