AI Models
What each model is good at, where it differs from the others, and what it costs to run.
Shengshu's Vidu Q4. A clip that starts from a picture, with optional sound, or from many reference pictures you name in the prompt.
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Vidu Q4 is Shengshu's Vidu video model for performance, camera, and effects. It does not start from a prompt alone. A picture starts the clip.
Vidu describes Q4 as more natural acting, camera moves that follow the story, and effects such as explosions and particles that sit in the scene. Vidu also describes reference pictures for keeping characters, places, and props consistent across a more complicated idea.
Start from one picture. Turn sound on if you want it. Or open Vidu Q4 Reference, attach two to fifteen pictures, and name them @image1 onward in the prompt.
PixVerse V6 can start from text alone. Vidu Q4 cannot. Wan 3.0 can start from text and takes fewer reference pictures. Vidu's reference set is the large one.
No. One picture starts the clip. Text-only is a different model.
Two to fifteen, named @image1 onward, on Vidu Q4 Reference.
Yes. The switch starts off until you turn it on.
Shengshu. Vidu Q4 is their video model. A picture starts the clip, unless you are on the reference path.
