API reference · Vidu

vidu/q2/reference-to-video/pro

Integrate this model through SandBase's unified API, with production-ready schemas and examples.

VIDEOAsyncOpen model

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDvidu/q2/reference-to-video/pro

Input Schema

9 parameters · 1 required · 8 optional

Parameter	Type	Required	Description
`prompt`	string	Required	Text prompt for video generation, max 2000 characters · Max length: 2000
`bgm`	boolean	Optional	Whether to add background music to the generated video · Default: false
`seed`	integer	Optional	Random seed for reproducibility. If None, a random seed is chosen.
`duration`	integer	Optional	Duration of the video in seconds (0 for automatic duration) · Min: 1 · Max: 8 · Default: 4
`resolution`	string	Optional	Output video resolution · Options: 540p, 720p, 1080p · Default: "720p" 540p720p1080p
`aspect_ratio`	string	Optional	The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16
`movement_amplitude`	string	Optional	The movement amplitude of objects in the frame · Options: auto, small, medium, large · Default: "auto" autosmallmediumlarge
`reference_image_urls`	string[]	Optional	URLs of the reference images for subject appearance. If videos are provided, up to 4 images are allowed; otherwise up to 7 images.
`reference_video_urls`	string[]	Optional	URLs of the reference videos for video editing or motion reference. Supports up to 2 videos.

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "vidu/q2/reference-to-video/pro",
  "bgm": false,
  "prompt": "@Figure 1 Character Reference@Refer to the special effects, movements, and camera work of Video 1.",
  "duration": 4,
  "resolution": "720p",
  "movement_amplitude": "auto",
  "reference_image_urls": [
    "https://static.sandbase.ai/examples/shengshu/vidu/q2/reference-to-video/pro/input_reference_image_urls_0.png"
  ],
  "reference_video_urls": [
    "https://static.sandbase.ai/examples/shengshu/vidu/q2/reference-to-video/pro/input_reference_video_urls_1.mp4"
  ]
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Vidu Q2 Reference to Video Pro