Skip to main content
POST
/
kyyReactApiServer
/
v1
/
starvideos
/
videos
curl --request POST \
  --url https://zcbservice.aizfw.cn/kyyReactApiServer/v1/starvideos/videos \
  --header 'Authorization: Bearer {{key}}' \
  --header 'Content-Type: application/json' \
  --data '{
    "prompt": "A cyberpunk city at night with a slow camera push-in",
    "model": "starvideos_v3",
    "duration": 5,
    "ratio": "16:9"
  }'

{
  "id": "video_starvideos_1234567890",
  "object": "video",
  "created": 1774836724,
  "model": "starvideos_v3",
  "status": "queued",
  "error": null
}

Documentation Index

Fetch the complete documentation index at: https://docs.globalaiopc.com/llms.txt

Use this file to discover all available pages before exploring further.

​
StarVideos Create Video Task

Create a StarVideos video generation task. This API supports text-to-video, single-image-to-video, and first/last frame video generation.

​
Authentication

All requests require a Bearer token in the request header: 
Authorization: Bearer {{key}}

​
Base URL

https://zcbservice.aizfw.cn/kyyReactApiServer
baseUrl is the shared prefix for all public APIs. The api field in the current page frontmatter shows the full endpoint. Use this baseUrl as the common prefix when reading or composing request paths.

​
Request Parameters

​
prompt
string
required
Video generation prompt.Example: "A cyberpunk city at night with a slow camera push-in"
​
model
string
required
Model name. The current value is fixed to starvideos_v3.
​
duration
integer
Video duration in seconds. Defaults to 5. Supported range: 3-15.
​
ratio
string
Output aspect ratio. Defaults to 16:9.Available values:
  • 16:9
  • 9:16
​
images
array
Reference image URL list. Only the first 2 images are used.Rules:
  • No images: text-to-video
  • 1 image: single-image-to-video
  • 2 images: first/last frame mode
If more than 2 images are provided, only the first 2 take effect.

​
Modes

Text to Video

Do not provide images. The result is generated only from the prompt.

Single Image

Provide 1 image to strengthen subject and style control.

First/Last Frame

Provide 2 images as the start frame and end frame.

​
Response Parameters

​
id
string
Unique identifier for the video generation task, used for subsequent status queries.
​
object
string
Object type, always video.
​
created
integer
Task creation timestamp.
​
model
string
Model name used for generation.
​
status
string
Task status:
  • queued - Queued
  • processing - Processing
  • completed - Completed
  • failed - Failed
​
error
string
Error message returned when the task status is failed.

​
Constraints

Key constraints:
  • model currently only supports starvideos_v3
  • duration must be between 3 and 15 seconds
  • ratio only supports 16:9 or 9:16
  • only the first 2 items in images are used
Best practices:
  1. Task creation is asynchronous, so save the returned id.
  2. Include subject, action, camera, and style details in your prompt.
  3. In first/last frame mode, keep the 2 images visually consistent.
  4. Image URLs must be publicly accessible when the request is sent.
curl --request POST \
  --url https://zcbservice.aizfw.cn/kyyReactApiServer/v1/starvideos/videos \
  --header 'Authorization: Bearer {{key}}' \
  --header 'Content-Type: application/json' \
  --data '{
    "prompt": "A cyberpunk city at night with a slow camera push-in",
    "model": "starvideos_v3",
    "duration": 5,
    "ratio": "16:9"
  }'

{
  "id": "video_starvideos_1234567890",
  "object": "video",
  "created": 1774836724,
  "model": "starvideos_v3",
  "status": "queued",
  "error": null
}