Text2Movie

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

Camera fields: six points, every model

Each page here takes one point, start and end frames for instance, and lays it out for every model on the register. Pages under each point look at one model's docs in detail. As of 2026-09-25.

What this reel holdsEach camera point across all 24 models, with single-model pages where the docs say more. The reel holds 6 pages.ReelCamera fields6 pagesEach pageOne question, answered from the docs.Each quoteDoc page and day read.
Fig. 1 Each page on the reel links back here.

Start here with a directing question rather than a model: can I pin the last frame, can I cut inside a clip, can I rule something out.

The points run from the shot itself, moves, framing and cuts, to the controls around the prompt.

Each field page sets every model's reading beside the line copied from its docs.

Where a model's docs could not be read, the page says so rather than counting it as silent.

Camera moves and start and end frames are the two points most models document; negative prompts and motion settings are the two that the fewest document, which makes those pages mostly lists of silence.

1On this reel

  • Camera moves — How a camera move is asked for across 24 AI video models, as their own docs describe it, each reading quoted and dated 2026-09-25.
  • Framing — Shot sizes and angles in the docs across 24 AI video models, as their own docs describe it, each reading quoted and dated 2026-09-25.
  • Cuts — Cuts inside one generation across 24 AI video models, as their own docs describe it, each reading quoted and dated 2026-09-25.
  • Frames — Start and end frames across 24 AI video models, as their own docs describe it, each reading quoted and dated 2026-09-25.
  • Negative prompt — A negative prompt across 24 AI video models, as their own docs describe it, each reading quoted and dated 2026-09-25.
  • Motion amount — A setting for how much the picture moves across 24 AI video models, as their own docs describe it, each reading quoted and dated 2026-09-25.

2The film language, written for you

Where “Camera fields” has to be written by hand, SceneMixer's pipeline writes the shots; its guides explain:

Typically 60–120 seconds, always 9:16 vertical, ending on a hook. SceneMixer's episode outlines are generated with that pacing, and setting a project to 9:16 makes every segment vertical (the default is 16:9).

SceneMixer, How to Make ReelShort-Style Dramas with AI — “How long is a ReelShort-style episode?” (read 2026-10-13)

For vehicle interiors the site sets it so every row is visible. Individual shots in the video still use their own angles.

SceneMixer, Scenes Inside a Car, a Bus, a Train or a Plane: How the Location Image Is Drawn — “Can I choose a different angle for the location image?” (read 2026-10-13)

3Other reels