AI 模型接口视频（Videos）Happyhorse 快乐马
Happyhorse 快乐马视频生成
happyhorse-1.0-t2v-1080P、happyhorse-1.0-t2v-720P、happyhorse-1.0-r2v-1080P、happyhorse-1.0-r2v-720P 是 Happyhorse 快乐马可选模型。该接口走异步视频任务流程，提交后返回任务 ID，再通过查询接口获取状态和结果。r2v 模型需要通过 metadata.media 传入参考媒体，t2v 模型可不传。
Authorization
Bearer
AuthorizationBearer <token>
In: header
Request Body
application/json
model*string
模型名称，支持 happyhorse-1.0-t2v-1080P、happyhorse-1.0-t2v-720P、happyhorse-1.0-r2v-1080P、happyhorse-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 720P、1080P，或 1280*720、1920*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
}最后更新于