Text2Movie

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

Camera fields: how a camera move is asked for

21 of the 24 models' docs cover how a camera move is asked for. Of those, the commonest reading is “Words in the prompt”, for 12. Every row pairs a reading with the opening line taken from that model's docs. As of 2026-09-25.

Camera moves across the registerLit: the docs cover it. Dark: they do not, or could not be read.Camera moves across the registerReadingAdobe Firefly — Reading: Commands or presetsAdobe FireflyGoogle Veo — Reading: Words in the promptGoogle VeoGrok Imagine — Reading: Words in the promptGrok ImagineHiggsfield — Reading: Commands or presetsHiggsfieldHunyuanVideo 1.5 — Reading: Words in the promptHunyuanVideo 1.5Kling AI — Reading: Words in the promptKling AILeonardo Motion 2.0 — Reading: Commands or presetsLeonardo Motion 2.0LTX — Reading: Words in the promptLTXLTX Studio — Reading: Commands or presetsLTX StudioLuma Dream Machine — Reading: Commands or presetsLuma Dream MachineMidjourney — Reading: None in the docsMidjourneyMiniMax Hailuo — Reading: Commands or presetsMiniMax HailuoMoonvalley Marey — Reading: Drawn or set from an imageMoonvalley MareyOpen-Sora 2.0 — Reading: None in the docsOpen-Sora 2.0Pika — Reading: Words in the promptPikaPixVerse — Reading: Commands or presetsPixVerseRunway — Reading: Words in the promptRunwaySceneMixer — Reading: Words in the promptSceneMixerSeedance — Reading: From a referenceSeedanceSkyReels — Reading: Words in the promptSkyReelsSora — Reading: Words in the promptSoraStep-Video-TI2V — Reading: Words in the promptStep-Video-TI2VVidu — Reading: None in the docsViduWan — Reading: Words in the promptWan
Fig. 1 Lit: the docs cover it. Dark: they do not, or could not be read.
How a camera move is asked for: reading and doc line, by model, read 2026-09-25.
ModelReadingWhat the docs say
Adobe FireflyCommands or presetsCamera motion options to pick: zoom in or out, move left or right, tilt up or down, static and handheld
Google VeoWords in the promptCamera moves are prompt words, each defined with an example: static, pan, tilt, dolly and more
Grok ImagineWords in the promptCamera moves are written in the prompt, as in its example of panning out
HiggsfieldCommands or presetsMore than fifty named motion presets, from crash zooms to crane shots and bullet time
HunyuanVideo 1.5Words in the promptCamera movement is written into the prompt; the demo prompts circle, tilt and zoom the camera
Kling AIWords in the promptCamera moves are written into each shot of the prompt, as in its tracking-shot examples
Leonardo Motion 2.0Commands or presetsMotion Control presets for Motion 2.0, from crane and dolly moves to orbits and bullet time
LTXWords in the promptCamera movement is a step of the prompt: how and when the camera moves, relative to the subject
LTX StudioCommands or presetsCamera motion presets under the prompt field: static, handheld, dolly, crane, dolly zoom and whip out
Luma Dream MachineCommands or presetsCamera moves are words in the prompt, taken from a list the API returns
MidjourneyNone in the docsNot described in the docs read (2026-09-25)
MiniMax HailuoCommands or presetsFifteen bracketed camera commands, such as [Truck left] or [Push in], combined or in sequence
Moonvalley MareyDrawn or set from an imageCamera moves are made from a single image, and trajectories are drawn for elements
Open-Sora 2.0None in the docsNot described in the docs read (2026-09-25)
PikaWords in the promptCamera shots are keywords in the prompt, such as bullet time, vertigo or dolly down
PixVerseCommands or presetsA camera_movement field applies a named move such as zoom_in
RunwayWords in the promptCamera motion is one of the prompt ingredients, added after the subject's motion works
SceneMixerWords in the promptCamera moves are written into each shot's text: fixed, handheld, tracking or a slow push in
SeedanceFrom a referenceImages, audio and videos can serve as references for performance, light and camera movement
SkyReelsWords in the promptCamera moves are written in the prompt, as in its example of following a bird upward
SoraWords in the promptCamera motion is described in plain words, one clear move per shot
Step-Video-TI2VWords in the promptA table of supported camera movements, from a fixed camera to orbit shots and rack focus, asked for in the prompt
ViduNone in the docsNot described in the docs read (2026-09-25)
WanWords in the promptCamera moves are prompt words, each tied to an intent: push-in, pull-out, tracking, orbit, fixed

Inclusion rule. All 24 models on the register. Order. Alphabetical by model name.

1What this field covers

This field records how the docs say a camera move is asked for. 12 models take moves as words in the prompt, 7 as named commands, presets or fields, 1 from a reference, 1 from a drawn trajectory or a single image, and 3 are silent.

Words are flexible and hard to verify; commands are narrow and exact. A command list also tells a writer which moves the maker has trained for, which a free-text prompt never does.

2Readings and how many models carry each

  • Words in the prompt: 12 models
  • Commands or presets: 7 models
  • From a reference: 1 model
  • Drawn or set from an image: 1 model
  • None in the docs: 3 models

3Single models on this field

4The other five fields

Shot sizes and angles in the docs · Cuts inside one generation · Start and end frames · A negative prompt · A setting for how much the picture moves