Dolly In — AI camera move prompt
Dolly In is a camera movement you can name directly in the prompt. Here is the phrase to use, what it changes, and which models render it reliably.
The prompt phrase
Dolly In
smooth cinematic dolly-in pushing toward the subjectWithout an explicit move, video models fall back on a vague floating drift that reads as artificial. Naming the move gives the model something deliberate to execute.
A worked example
An astronaut floating beside a station window, smooth cinematic dolly-in pushing toward the subject, 35mm lensYour subject comes first, then the technique, then anything else. Models weight the front of a prompt most heavily, so keep the subject there and let the camera move modify it.
Models that render it
| Model | Credits | What it is for |
|---|---|---|
| Veo 3.1 Lite | 6 | Google quality on a budget, sound included |
| Veo 3.1 Fast | 12 | Google quality at half the price |
| Wan 2.6 | 14 | realistic physics and fine detail |
| Veo 3.1 | 22 | best realism, native sound, start and end frames |
| Hailuo 02 | 8 | expressive people and faces |
| Kling 1.6 | 8 | reliable motion, older generation |
| LTX 2 Fast | 9 | quickest way to test an idea |
| LTX 2 | 10 | sharp drafts at a low price |
Related camera moves
- Dolly Out Dolly
- Truck Left Dolly
- Truck Right Dolly
- Tracking Shot Dolly
- Leading Follow Dolly
- Dolly Zoom Dolly
- Static Static
- Slow Push In Static
- Slow Pull Out Static
- Breathing Static
- Pan Left Pan
- Pan Right Pan
Common questions
What exactly do I put in the prompt?
The phrase above, word for word: "smooth cinematic dolly-in pushing toward the subject". Put it after your subject, separated by a comma.
Which models handle this best?
The 8 models in the table all support it. Veo 3.1 Lite is the cheapest way to test it at 6 credits, then move up a tier once the shot works.
Can I combine it with other camera moves?
Yes. Stacking two or three related instructions is normal; stacking six competing ones is where results start to fall apart.