Get API Key Get API
Docs

Vidu Q3(mix/standard) Reference-to-Video

- Async processing mode, returns task ID for subsequent queries

  • Upload 1-7 reference images + text prompt to generate short videos containing reference subjects
  • Supports 540p / 720p / 1080p resolution
  • Duration range 1-16 seconds, suitable for character consistency and style continuation

Request example

curl --request POST \
  --url https://api.openveer.com/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "viduq3",
    "prompt": "Santa Claus and the bear hug by the lakeside",
    "image_urls": [
      "https://example.com/santa.png",
      "https://example.com/bear.png"
    ],
    "duration": 8,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }'

Response example

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_xxxxxxxxxx"
    }
  ]
}

Authorization

Authorization string

All API endpoints require Bearer Token authentication

Get your API Key:

Visit the API Key Management Page to get your API Key

Add it to the request header:

Authorization: Bearer YOUR_API_KEY

Request Parameters

model string

Video generation model name

Supported models:

  • viduq3-mix - Premium quality, stronger smart transitions, supports 1-second short videos
  • viduq3 - Default choice, smarter camera switching

Note



How to choose: Use viduq3 for everyday use; use viduq3-mix for premium quality or 1-2 second motion effects.

nsfw_check boolean

Whether to run content moderation before submitting the video task.

  • true: use omni-moderation-latest to review prompts and input images
  • false or omitted: do not send a moderation request, adding no moderation cost or latency (default)
prompt string

Text prompt, maximum 5000 characters

Describe actions and camera movements, not appearance (appearance is determined by reference images).

Example: "Santa Claus and the bear hug by the lakeside"

image_urls string

" required>
Reference image URL array, 1-7 images

Supports publicly accessible image URLs (http\:// or https\://)

Example: ["https://example.com/santa.png", "https://example.com/bear.png"]

Warning



* Quantity: 1-7 images

* Supported formats: PNG, JPEG, JPG, WebP

* Minimum size: 128×128

* Aspect ratio: between 1:4 and 4:1

* Maximum file size: ≤ 50MB per image

* Must be publicly accessible URLs

duration integer

Video duration (seconds)

  • viduq3-mix: 1 to 16
  • viduq3: 3 to 16

Default: 5

Warning



viduq3 supports minimum 3 seconds, viduq3-mix supports minimum 1 second. Please pass a valid duration based on the selected model.

resolution string

Video resolution

  • viduq3-mix: 720p (default) / 1080p
  • viduq3: 540p / 720p (default) / 1080p

Warning



viduq3-mix does not support 540p, please use 720p or 1080p.

aspect_ratio string

Video aspect ratio

Options:

  • 16:9 - Landscape (default)
  • 9:16 - Portrait
  • 4:3 - Traditional
  • 3:4 - Portrait traditional
  • 1:1 - Square
seed integer

Random seed for controlling generation randomness

If not provided, a random seed will be used.

Note



Using the same seed with identical parameters will produce similar results, but not guaranteed to be exactly the same.

Model Comparison

Feature viduq3 viduq3-mix
Recommended for Everyday use, multi-angle camera switching Premium quality, 1-2 second motion effects
Duration range 3-16 seconds 1-16 seconds
Resolution 540p / 720p / 1080p 720p / 1080p
Reference images 1-7 images 1-7 images

Response

code integer

Response status code, 200 on success

data array
Response data array
status string

Task status, submitted when initially submitted

task_id string

Unique task identifier for querying task status and results

Use Cases

Case 1: viduq3 Basic Reference-to-Video

{
  "model": "viduq3",
  "prompt": "Santa Claus and the bear hug by the lakeside",
  "image_urls": [
    "https://example.com/santa.png",
    "https://example.com/bear.png"
  ]
}

Case 2: viduq3-mix High Quality Reference-to-Video

{
  "model": "viduq3-mix",
  "prompt": "A cyberpunk neon street with the cat from reference image walking by",
  "image_urls": [
    "https://example.com/cat-1.png",
    "https://example.com/cat-2.png",
    "https://example.com/cat-3.png"
  ],
  "duration": 8,
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "seed": 42
}
Note

Query Task Results

Video generation is an async task that returns a task_id upon submission. Use the Get Task Status endpoint to query generation progress and results.

This documentation is built and hosted on Mintlify, a developer documentation platform.