Model pair: Grok Imagine and Vidu

The docs of Grok Imagine and Vidu part on 3 of the six camera points: camera moves, frames and motion amount. They read alike on framing, cuts and negative prompt. As of 2026-09-25.

Fig. 1 Lit: the docs cover it. Dark: they do not.

Grok Imagine and Vidu, reading by field, read 2026-09-25.
Field	Grok Imagine	Vidu
How a camera move is asked for	Words in the prompt	None in the docs
Shot sizes and angles in the docs	None in the docs	None in the docs
Cuts inside one generation	None in the docs	None in the docs
Start and end frames	First frame only	First and last frame
A negative prompt	None in the docs	None in the docs
A setting for how much the picture moves	None in the docs	A motion setting

Inclusion rule. The six points every model on the register is read on. Order. The order the points take on every model page.

1How the two differ

Grok Imagine reads “Words in the prompt” on camera moves, while Vidu's docs say nothing about camera moves. Grok Imagine reads “First frame only” on start and end frames, while Vidu reads “First and last frame” on start and end frames. Only Vidu documents a motion setting. Grok Imagine's docs use 1 of the site's camera words and Vidu's use 0, with none in common.

2The differing points, in the docs' words

How a camera move is asked for

Make the water crash down and slowly pan out the camera
xAI, Grok Imagine documentation

Vidu: the docs read do not cover this.

Start and end frames

video generation from text or still images
xAI, Grok Imagine documentation

Two images: first is start frame, second is end frame.
Vidu, platform start-end-to-video API

A setting for how much the picture moves

Grok Imagine: the docs read do not cover this.

The movement amplitude of objects in the frame
Vidu, platform text-to-video API

Example request
Camera moves are written in the prompt, as in its example of panning outxAI, Grok Imagine documentation / recorded 2026-09-25
Overview
Video is generated from text or from a still imagexAI, Grok Imagine documentation / recorded 2026-09-25
images parameter
Two images set the start frame and the end frameVidu, platform start-end-to-video API / recorded 2026-09-25
movement_amplitude parameter
movement_amplitude sets how much things in the frame move, auto by defaultVidu, platform text-to-video API / recorded 2026-09-25

3Grok Imagine, Vidu and a third set of camera docs

On the camera points where Grok Imagine and Vidu part, what SceneMixer's guides say, read 2026-10-13.
Camera point	SceneMixer	Source
How a camera move is asked for	Camera moves are written into each shot's text: fixed, handheld, tracking or a slow push in	SceneMixer, how to write one shot

Inclusion rule. Points where the two models above differ and SceneMixer's guides say something; points its guides leave open are not shown. Order. The order the points take on every model page.