All models

Vidu Q3 Pro

vidu/q3-pro
Vidu Video GenerationImage-to-VideoAudio

Vidu Q3 Pro is a high-quality video generation model supporting text-to-video, image-to-video, and start/end-frame-to-video workflows with audio and up to 16-second clips.

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
  -H "content-type: application/json" \
  -d '{
    "model": "vidu/q3-pro",
    "audio": <boolean>,
    "prompt": <string>
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
  -J '{"model": "vidu/q3-pro", "audio": "<boolean>", "prompt": "<string>"}'

Examples

Parameters

Input
aspect_ratio string

Video aspect ratio (text-to-video only). Default: 16:9

audio boolean

Enable audio-video synchronization. Default: true for Q3 models. When false, outputs silent video

duration integer required

Video duration in seconds (1-16)

end_image string

End image for start/end-to-video generation. Must be used together with start_image. Accepts public URL or Base64 data URI (data:image/png;base64,...)

prompt string

Text prompt describing what should appear in the video

resolution string required

Video resolution

start_image string

Start image for video generation. Use alone for image-to-video, or with end_image for start/end-to-video. Accepts public URL or Base64 data URI (data:image/png;base64,...)

Output
video: URL to the generated video