Text2Movie

The film language each AI video model's docs let you write

Model pair: Moonvalley Marey and Vidu

The docs of Moonvalley Marey 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.

What the two sets of docs coverLit: the docs cover it. Dark: they do not.What the two sets of docs coverMoonvalley MareyViduHow a camera move is asked forHow a camera move is asked for — Moonvalley Marey: Drawn or set from an imageHow a camera move is asked for — Vidu: None in the docsShot sizes and angles in the docsShot sizes and angles in the docs — Moonvalley Marey: None in the docsShot sizes and angles in the docs — Vidu: None in the docsCuts inside one generationCuts inside one generation — Moonvalley Marey: None in the docsCuts inside one generation — Vidu: None in the docsStart and end framesStart and end frames — Moonvalley Marey: Several keyframesStart and end frames — Vidu: First and last frameA negative promptA negative prompt — Moonvalley Marey: None in the docsA negative prompt — Vidu: None in the docsA setting for how much the picture movesA setting for how much the picture moves — Moonvalley Marey: None in the docsA setting for how much the picture moves — Vidu: A motion setting
Fig. 1 Lit: the docs cover it. Dark: they do not.
Moonvalley Marey and Vidu, reading by field, read 2026-09-25.
FieldMoonvalley MareyVidu
How a camera move is asked forDrawn or set from an imageNone in the docs
Shot sizes and angles in the docsNone in the docsNone in the docs
Cuts inside one generationNone in the docsNone in the docs
Start and end framesSeveral keyframesFirst and last frame
A negative promptNone in the docsNone in the docs
A setting for how much the picture movesNone in the docsA 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

Moonvalley Marey reads “Drawn or set from an image” on camera moves, while Vidu's docs say nothing about camera moves. Moonvalley Marey reads “Several keyframes” on start and end frames, while Vidu reads “First and last frame” on start and end frames. Only Vidu documents a motion setting. Moonvalley Marey's docs use 0 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

Create cinematic camera moves using just a single image.

Moonvalley, Marey

Vidu: the docs read do not cover this.

Start and end frames

Upload multiple reference images and place them on a timeline.

Moonvalley, Marey

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

Moonvalley Marey: the docs read do not cover this.

The movement amplitude of objects in the frame

Vidu, platform text-to-video API
  • Camera control
    Camera moves are made from a single image, and trajectories are drawn for elementsMoonvalley, Marey / recorded 2026-09-25
  • Keyframing
    Several reference images are placed on a timeline and the model makes the transitionsMoonvalley, Marey / 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

3Moonvalley Marey, Vidu and a third set of camera docs

On the camera points where Moonvalley Marey and Vidu part, what SceneMixer's guides say, read 2026-10-13.
Camera pointSceneMixerSource
How a camera move is asked forCamera moves are written into each shot's text: fixed, handheld, tracking or a slow push inSceneMixer, 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.

4More on the reel