Vidu Video
Video Generation
Submit a Vidu Video task. Vidu provides text-to-video, image-to-video, first-and-last-frame, and multi-image reference generation through the OpenAI-compatible video API.
Submit a Vidu Video task. Vidu provides text-to-video, image-to-video, first-and-last-frame, and multi-image reference generation through the OpenAI-compatible video API.
Authorization
BearerAuth
AuthorizationBearer <token>
使用 API Token 认证
In: header
model*string
Vidu 模型
Value in
"viduq2" | "viduq1" | "vidu2.0" | "vidu1.5"prompt?string
视频描述提示词
images?array<string>
图片 URL 列表：1 张为图生视频，2 张为首尾帧，超过 2 张为参考生视频
image?string
单张图片 URL，兼容字段，会转为 images
input_reference?string
单张参考图片 URL，兼容字段
seconds?integer
视频时长，兼容 duration
duration?integer
视频时长
size?string
输出尺寸或分辨率，例如 720p、1920x1080
metadata?
扩展参数；metadata.action 可指定 generate、textGenerate、firstTailGenerate、referenceGenerate 或 remixGenerate
[key: string]?any
Response Body
application/json
curl -X POST "https://loading/v1/videos" \ -H "Content-Type: application/json" \ -d '{ "model": "viduq2", "prompt": "一只猫在海边奔跑", "seconds": 5, "size": "720p" }'{
"id": "string",
"object": "video",
"model": "string",
"status": "queued",
"progress": 0,
"created_at": 0,
"completed_at": 0,
"error": {}
}Empty
How is this guide?
Last updated on