Which AI video models take camera moves as plain words?
12 of the 24 models: Google Veo, Grok Imagine, HunyuanVideo 1.5, Kling AI, LTX, Pika, Runway, SceneMixer, SkyReels, Sora, Step-Video-TI2V and Wan. The other 12 do not, in the docs read. As of 2026-10-13.
| Model | Camera moves | What the docs say |
|---|---|---|
| Google Veo | Words in the prompt | Camera moves are prompt words, each defined with an example: static, pan, tilt, dolly and more |
| Grok Imagine | Words in the prompt | Camera moves are written in the prompt, as in its example of panning out |
| HunyuanVideo 1.5 | Words in the prompt | Camera movement is written into the prompt; the demo prompts circle, tilt and zoom the camera |
| Kling AI | Words in the prompt | Camera moves are written into each shot of the prompt, as in its tracking-shot examples |
| LTX | Words in the prompt | Camera movement is a step of the prompt: how and when the camera moves, relative to the subject |
| Pika | Words in the prompt | Camera shots are keywords in the prompt, such as bullet time, vertigo or dolly down |
| Runway | Words in the prompt | Camera motion is one of the prompt ingredients, added after the subject's motion works |
| SceneMixer | Words in the prompt | Camera moves are written into each shot's text: fixed, handheld, tracking or a slow push in |
| SkyReels | Words in the prompt | Camera moves are written in the prompt, as in its example of following a bird upward |
| Sora | Words in the prompt | Camera motion is described in plain words, one clear move per shot |
| Step-Video-TI2V | Words in the prompt | A table of supported camera movements, from a fixed camera to orbit shots and rack focus, asked for in the prompt |
| Wan | Words in the prompt | Camera moves are prompt words, each tied to an intent: push-in, pull-out, tracking, orbit, fixed |
Inclusion rule. Models whose own docs meet the condition in the question. Order. Alphabetical by model name.
1Why it matters
Most models have no command syntax for the camera: the move is written into the prompt in ordinary words, and the model reads it the way it reads the rest of the description. That makes the wording the control, so a docs page that shows which words it responds to is worth more than a feature list.
2From the docs
Pan (left/right) : the camera rotates horizontally left or right from a fixed position.
Google Cloud, Veo video prompt guide
Make the water crash down and slowly pan out the camera
xAI, Grok Imagine documentation
3The rest of the register
Not matching: Adobe Firefly, Higgsfield, Leonardo Motion 2.0, LTX Studio, Luma Dream Machine, Midjourney, MiniMax Hailuo, Moonvalley Marey, Open-Sora 2.0, PixVerse, Seedance and Vidu.
- Camera motionCamera moves are prompt words, each defined with an example: static, pan, tilt, dolly and more
- Example requestCamera moves are written in the prompt, as in its example of panning out
- Demo promptsCamera movement is written into the prompt; the demo prompts circle, tilt and zoom the camera
- Multi-shot examplesCamera moves are written into each shot of the prompt, as in its tracking-shot examples
- Key elementsCamera movement is a step of the prompt: how and when the camera moves, relative to the subject
- Camera shotsCamera shots are keywords in the prompt, such as bullet time, vertigo or dolly down
- Example promptCamera motion is one of the prompt ingredients, added after the subject's motion works
- Framing and cameraCamera moves are written into each shot's text: fixed, handheld, tracking or a slow push in
- Example promptCamera moves are written in the prompt, as in its example of following a bird upward
- Camera directionCamera motion is described in plain words, one clear move per shot
- Camera controlA table of supported camera movements, from a fixed camera to orbit shots and rack focus, asked for in the prompt
- Formula elementsCamera moves are prompt words, each tied to an intent: push-in, pull-out, tracking, orbit, fixed