AI model interfaceVideosSeedance
Seedance Video Generation
Doubao Seedance video generation API. This API follows an asynchronous video task process, returning a task ID upon submission, which can then be used to query the status and results. It supports text-to-video and image-to-video generation, and can also accept multimodal reference content such as video/audio through metadata.content.
Authorization
Bearer
AuthorizationBearer <token>
In: header
Request Body
application/json
model*string
Seedance 模型名称。
Value in
"doubao-seedance-1-0-pro-250528" | "doubao-seedance-1-0-lite-t2v" | "doubao-seedance-1-0-lite-i2v" | "doubao-seedance-1-5-pro-251215" | "doubao-seedance-2-0-260128" | "doubao-seedance-2-0-fast-260128"prompt*string
视频生成提示词。项目会把该字段追加为上游 content 中的 text 项。
image?string
单张图生视频参考图 URL。项目会转换为上游 content[].image_url.url。
images?array<string>
多张图生视频参考图 URL。项目会逐项转换为上游 content[].image_url.url。
seconds?string
视频时长，字符串格式；项目会转换为上游 duration。
duration?integer
兼容字段，整数秒。豆包 Seedance 上游请求建议使用 seconds，或通过 metadata.duration 透传。
metadata?
Seedance 上游扩展参数。适配器会将该对象合并进豆包任务请求。
Response Body
application/json
curl -X POST "https://nodekey.xinghanyun.cn/v1/video/generations" \ -H "Content-Type: application/json" \ -d '{ "model": "doubao-seedance-2-0-260128", "prompt": "手持镜头穿过清晨的咖啡店，阳光从窗边扫过桌面", "seconds": "5", "size": "1280x720", "metadata": { "ratio": "16:9", "resolution": "720p", "generate_audio": false } }'{
"id": "string",
"task_id": "string",
"object": "string",
"model": "string",
"status": "queued",
"progress": 0,
"created_at": 0
}Last updated on