Text2Movie

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

Runway beside Sora, point by point

The docs of Runway and Sora part on 4 of the six camera points: framing, cuts, frames and negative prompt. They read alike on camera moves and motion amount. 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 coverRunwaySoraHow a camera move is asked forHow a camera move is asked for — Runway: Words in the promptHow a camera move is asked for — Sora: Words in the promptShot sizes and angles in the docsShot sizes and angles in the docs — Runway: None in the docsShot sizes and angles in the docs — Sora: Shown in examplesCuts inside one generationCuts inside one generation — Runway: None in the docsCuts inside one generation — Sora: Several shots per clipStart and end framesStart and end frames — Runway: Several keyframesStart and end frames — Sora: First frame onlyA negative promptA negative prompt — Runway: Advised againstA negative prompt — Sora: None in the docsA setting for how much the picture movesA setting for how much the picture moves — Runway: None in the docsA setting for how much the picture moves — Sora: None in the docs
Fig. 1 Lit: the docs cover it. Dark: they do not.
Runway and Sora, reading by field, read 2026-09-25.
FieldRunwaySora
How a camera move is asked forWords in the promptWords in the prompt
Shot sizes and angles in the docsNone in the docsShown in examples
Cuts inside one generationNone in the docsSeveral shots per clip
Start and end framesSeveral keyframesFirst frame only
A negative promptAdvised againstNone in the docs
A setting for how much the picture movesNone in the docsNone in the docs

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

Runway's docs say nothing about cuts inside a clip, while Sora reads “Several shots per clip” on cuts inside a clip. Runway reads “Several keyframes” on start and end frames, while Sora reads “First frame only” on start and end frames. Runway's docs use 0 of the site's camera words and Sora's use 10, with none in common.

2The differing points, in the docs' words

Shot sizes and angles in the docs

Runway: the docs read do not cover this.

Weak Camera shot: cinematic look Strong Camera shot: wide shot, low angle

OpenAI Cookbook, Sora 2 prompting guide

Cuts inside one generation

Runway: the docs read do not cover this.

Optimized Shot List ( 2 shots / 4 s total)

OpenAI Cookbook, Sora 2 prompting guide

Start and end frames

Keyframes – Animate Frames app

Runway, camera control on Gen-3 Alpha Turbo

The model uses the image as an anchor for the first frame, while your text prompt defines what happens next.

OpenAI Cookbook, Sora 2 prompting guide

A negative prompt

Use positive phrasing and avoid negative prompts

Runway, Gen-4 video prompting guide

Sora: the docs read do not cover this.

3Runway, Sora and a third set of camera docs

On the camera points where Runway and Sora part, what SceneMixer's guides say, read 2026-10-13.
Camera pointSceneMixerSource
Shot sizes and angles in the docsEach numbered shot in a segment carries a framing change, written by the storyboard stepSceneMixer, AI storyboard generator page
Cuts inside one generationA segment holds several numbered shots and its length is the sum of themSceneMixer, AI storyboard generator page
A negative promptNegative wording is advised against: the guide says to describe what is there, because a named absence tends to be drawnSceneMixer, say what is there guide

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