Dolly in AI video prompts: which docs use it
7 of the 24 models' docs use dolly: Google Veo, Higgsfield, Leonardo Motion 2.0, LTX Studio, Pika, Sora and Step-Video-TI2V. A dolly move carries the whole camera toward, away from or alongside a subject. As of 2026-09-25.
A dolly move carries the whole camera toward, away from or alongside a subject. Unlike a zoom, the perspective changes, so the background shifts against the subject.
| Model | How the docs use it | From the docs |
|---|---|---|
| Google Veo | defines it | Dolly (in/out) : the camera physically moves closer to the subject or further away. |
| Higgsfield | lists it as a preset | Dolly In Dolly Left Dolly Out Dolly Right |
| Leonardo Motion 2.0 | defines it | Dolly in / out - Moves in / out: The camera moves in or out of the scene. |
| LTX Studio | defines it | Dolly In/Out: Simulate smooth forward or backward gliding, drawing viewers closer to or farther from a subject. |
| Pika | uses it in an example | dolly down |
| Sora | uses it in an example | slow dolly left |
| Step-Video-TI2V | lists it as a command | Dolly In/Out |
Inclusion rule. Models whose own docs define the word, list it as a command or preset, or use it in an example prompt. Order. Alphabetical by model name.
1How the docs use it
Google Veo, Leonardo Motion 2.0 and LTX Studio define it; Higgsfield lists it as a preset; Pika and Sora use it in an example; Step-Video-TI2V lists it as a command.
A word the docs define is one the maker explains to users. A command or preset is one the model is set up to perform on request. A word that appears only in an example prompt is one the maker shows working, without promising more.
The other 17 models' docs do not use it in the pages read: Adobe Firefly, Grok Imagine, HunyuanVideo 1.5, Kling AI, LTX, Luma Dream Machine and others.
Dolly (in/out) : the camera physically moves closer to the subject or further away.
Google Cloud, Veo video prompt guide
Dolly In Dolly Left Dolly Out Dolly Right
Higgsfield, camera controls
- Camera word: dollyThe docs define dolly and describe what it does
- Camera word: dollyDolly is one of the named camera presets
- Camera word: dollyThe docs define dolly and describe what it does
- Camera word: dollyThe docs define dolly and describe what it does
- Camera word: dollyDolly appears in the docs' own prompt examples
- Camera word: dollyDolly appears in the docs' own prompt examples
- Camera word: dollyDolly is in the list of supported camera movements
2The film language, written for you
Where “Dolly” has to be written by hand, SceneMixer's pipeline writes the shots; its guides explain:
SceneMixer generates each character once as a full-body reference sheet — 9:16, plain background, directional key light, identity features written before any technical instruction — and then attaches crops of that sheet to every shot the character appears in.
SceneMixer, AI Character Sheet Generator (read 2026-10-13)
Video is 16:9 landscape by default, with 9:16 vertical available; you set it once per project. Segments are typically 4 to 15 seconds, and some model tiers go to 30.
SceneMixer, AI Short Drama Generator — “What length and aspect ratio does it output?” (read 2026-10-13)
3Neighbouring camera words
- tilt: A tilt turns the camera up or down from a fixed point.
- truck: A truck moves the whole camera sideways, parallel to the subject.
pan · tilt · truck · pedestal · push-in · pull-out · zoom · dolly zoom · orbit or arc · crane · tracking shot · handheld · static shot · aerial shot · whip pan · bullet time