NodeKeyNodeKey
AI model interfaceVideosHappyhorse

Happyhorse Video Generation

happyhorse-1.0-t2v-1080P, happyhorse-1.0-t2v-720P, happyhorse-1.0-r2v-1080P, happyhorse-1.0-r2v-720P are the optional models for Happyhorse. This interface follows an asynchronous video task process, returning a task ID upon submission, which can then be used to query the status and results. The r2v model requires a reference media to be passed through metadata.media, while the t2v model does not require it.

POST
/v1/video/generations
AuthorizationBearer <token>

In: header

Request Body

application/json

model*string

模型名称,支持 happyhorse-1.0-t2v-1080Phappyhorse-1.0-t2v-720Phappyhorse-1.0-r2v-1080Phappyhorse-1.0-r2v-720P

Value in"happyhorse-1.0-t2v-1080P" | "happyhorse-1.0-t2v-720P" | "happyhorse-1.0-r2v-1080P" | "happyhorse-1.0-r2v-720P"
prompt*string

视频生成提示词。

seconds?string

视频时长,字符串格式;项目会转换为整数秒。未传时默认按 5 秒处理。

duration?integer

视频时长,整数秒。若同时传 seconds,优先使用 seconds

size?string

分辨率或尺寸。可传 720P1080P,或 1280*7201920*1080 这类尺寸。Happyhorse 当前不自动补默认分辨率,建议显式传入。

metadata?

Happyhorse 扩展参数。适配器会透传到阿里请求,并可在 metadata.media 中传入 r2v 参考媒体。

Response Body

application/json

curl -X POST "https://nodekey.xinghanyun.cn/v1/video/generations" \  -H "Content-Type: application/json" \  -d '{    "model": "happyhorse-1.0-t2v-1080P",    "prompt": "手持镜头穿过清晨的咖啡店,阳光从窗边扫过桌面",    "duration": 1,    "metadata": {      "media": [        {          "type": "example-type",          "url": "示例值"        }      ],      "input": {        "negative_prompt": "blurry, low quality"      },      "parameters": {        "ratio": "16:9",        "duration": 1,        "prompt_extend": false,        "seed": 1      }    }  }'
{
  "id": "string",
  "task_id": "string",
  "object": "string",
  "model": "string",
  "status": "queued",
  "progress": 0,
  "created_at": 0
}

Last updated on