Skip to main content

Documentation Index

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

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

Submit an asynchronous video generation task using Vidu’s AI models. The API returns a task id immediately — you then poll the Query Video Task endpoint until the task reaches completed or failed status. Vidu supports pure text-to-video, image-to-video (driven by a first frame), and first/last frame guidance mode for precise scene control.

​
Base URL

https://zcbservice.aizfw.cn/kyyReactApiServer

​
Endpoint

POST /v1/vidu/videos

​
Authentication

Include your API key as a Bearer token in every request: 
Authorization: Bearer YOUR_API_KEY

​
Models

Vidu offers two models with different performance characteristics:
ModelDescription
viduq3-proHigher quality output — richer motion, more vivid and cinematic results
viduq3-turboFaster generation — same capabilities, reduced wait time
Use viduq3-pro when output quality is the priority. Use viduq3-turbo when you need faster turnaround for iteration or previews.

​
Request Parameters

​
model
string
required
The model to use for generation.Supported values:
  • viduq3-pro — higher quality, cinematic output
  • viduq3-turbo — faster generation
​
prompt
string
required
A text description of the video content you want to generate. Be specific about subject, action, camera movement, and visual style.Example: "A cat dancing in the rain, cinematic style"
​
duration
number
Output video length in seconds. Defaults to 5.
  • Supported range: 1–16 seconds
  • Default: 5
​
aspect_ratio
string
Output video aspect ratio. Defaults to 16:9.
ValueDescription
16:9Landscape (default)
9:16Portrait
1:1Square
4:3Standard screen
3:4Portrait standard
​
resolution
string
Output resolution. Defaults to 720p.
ValueDescription
540pStandard definition
720pHD (default)
1080pFull HD

​
Image-to-Video Parameters

​
first_image
string
URL of the first-frame image. Enables image-to-video mode.
  • Used alone: drives image-to-video generation from this starting frame
  • Used with last_image: enables first/last frame mode — the model transitions from the first frame to the last
Accepted formats: jpeg, png, webp
Value must be a publicly accessible URL.
​
last_image
string
URL of the last-frame image. Enables first/last frame guidance mode.
  • Must be used together with first_image — cannot be used alone
  • The model generates a smooth transition between the two frames
Accepted formats: jpeg, png, webp
Value must be a publicly accessible URL.
last_image cannot be used without first_image. Both fields are required for first/last frame mode.

​
Response Fields

​
id
string
Unique task identifier. Save this value — you’ll use it to poll the Query Video Task endpoint.
​
object
string
Object type. Always "video".
​
created
integer
Unix timestamp of when the task was created.
​
model
string
The model name used for this task.
​
status
string
Task status at creation time. Always "queued" on successful submission.Possible lifecycle values:
  • queued — task accepted and waiting in queue
  • processing — model is actively generating
  • completed — generation finished; video_url is available
  • failed — generation failed; see error for details
​
error
string
Error message. null on successful submission; populated when status is "failed".

​
Code Examples

curl --request POST \
  --url https://zcbservice.aizfw.cn/kyyReactApiServer/v1/vidu/videos \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "viduq3-pro",
    "prompt": "A cat dancing in the rain, cinematic style",
    "duration": 5,
    "aspect_ratio": "16:9",
    "resolution": "1080p"
  }'

​
Example Response

{
  "id": "video_fd35ee52-2a98-44a6-b930-29a88ce9b8fd",
  "object": "video",
  "created": 1774836724,
  "model": "viduq3-pro",
  "status": "queued",
  "error": null
}

​
Usage Modes

​
Text-to-Video

Send only model, prompt, and optional duration/aspect_ratio/resolution. The model generates content entirely from the text description.

​
Image-to-Video

Include first_image (without last_image). The model anchors the video to your provided first frame and generates a natural continuation.

​
First/Last Frame Guidance

Include both first_image and last_image. The model creates a smooth transition between your two provided frames — ideal for controlled scene transitions and specific visual storytelling.
All image URLs must be publicly accessible on the internet. Base64-encoded images are not supported.

​
Next Steps

After receiving the task id, poll the Query Video Task endpoint to check status and retrieve the video_url when generation completes.