Runware

Vidu 1.5

Vidu 1.5 multi-entity text to video with stable scenes

Launch model
Example 1
Example 2
Example 3
Example 4
Example 5
Example 6
Example 7
Example 8
Example 9
Example 10

Vidu 1.5 Overview

Vidu 1.5 is a multimodal text to video model that focuses on multi entity consistency across complex scenes. It keeps multiple characters and objects visually stable across frames and shots. Developers can build long form video workflows that need coherent motion and style control.