Vidu 2.0 Reference to Video

Vidu 2.0 Reference to Video · ShengShu Technology — Image to video · 3 aspect ratios. Call it through one queue API and pay for the options you pick.

modellane/vidu-reference-to-video-2.0 · Image to video · ShengShu Technology

Image to video model: 3 aspect ratios.

Source images images — required, range: 1–3 Images used in the generation; their order can affect the result.
Prompt prompt — required Describe what you want produced as concretely as you can.
Aspect ratio aspect_ratio — optional, options: 16:9, 9:16, 1:1 Sets whether the output is square, portrait, or landscape.
Movement amplitude movement_amplitude — optional, options: Auto, Small, Medium, Large Sets how pronounced the motion in the output is.
Seed seed — optional, default: 0 The same seed and the same settings produce a similar result; leave it empty and one is picked at random.

Output and retention

The generated file and your input are kept for seven days and then deleted.

Submit to the queue: POST /v1/queue/modellane/vidu-reference-to-video-2.0

Status, result, cancellation and error codes work the same for every model; see the API docs.

Everything on this page is public; you need an account to run the model.