Skip to main content
Generate videos with Vidu Q4, ShengShu Technology’s video model released October 7, 2026. One model covers two modes, picked by which images you send: image-to-video animates a single image, and reference-to-video builds a new scene from up to 15 reference images plus up to 3 audio references. Every video comes with native audio. Images and audio are downloaded from their public URLs automatically. Try it in the browser: Vidu Q4 API playground.

Model

Modes

Send either image_url or reference_image_urls, not both.

Parameters

Image inputs must be at least 128x128 pixels with an aspect ratio between 1:4 and 4:1, up to 50 MB.

Example - Image-to-Video

Example - Reference-to-Video

Response

Poll GET /v1/tasks/<task_id> or set a callback_url on the request to receive the finished video.
Volume discounts are available for almost all models. Reach out at contact@unifically.com to discuss custom pricing.