Close-Up — AI shot size prompt
Close-Up is a framing you can specify instead of leaving it to chance. Here is the phrase to use, what it changes, and which models render it reliably.
The prompt phrase
Close-Up
close-up shot, tight on the subjectShot size controls how much context the viewer gets. Left unspecified, models tend to land on a generic medium shot every time.
A worked example
A child chasing a kite across an open field, close-up shot, tight on the subject
Your 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 shot size modify it.
Models that render it
| Model | Credits | What it is for |
|---|---|---|
| Flux Schnell | 1 | instant drafts, lowest cost |
| Flux Dev | 2 | good quality without the top price |
| Nano Banana | 2 | follows instructions most closely |
| Recraft v3 | 3 | logos, icons and clean vector art |
| Seedream 4.5 | 3 | photoreal, and gets text right |
| Flux 2 | 4 | newest model, most realistic results |
| Flux Pro | 4 | sharpest detail of the Flux family |
| Ideogram 3 | 4 | posters and anything with words in it |
In video
The same phrase works in video prompts. These models accept it alongside a camera move:
| Model | Credits | Native audio |
|---|---|---|
| Veo 3.1 Lite | 6 | Yes |
| Veo 3.1 Fast | 12 | Yes |
| Wan 2.6 | 14 | Yes |
| Veo 3.1 | 22 | Yes |
| Hailuo 02 | 8 | Yes |
Related shot sizes
- Extreme Close-Up shot size
- Medium Shot shot size
- Cowboy Shot shot size
- Wide Shot shot size
- Extreme Wide shot size
- Two Shot shot size
- Insert / Detail shot size
Common questions
What exactly do I put in the prompt?
The phrase above, word for word: "close-up shot, tight on 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. Flux Schnell is the cheapest way to test it at 1 credits, then move up a tier once the shot works.
Can I combine it with other shot sizes?
Yes. Stacking two or three related instructions is normal; stacking six competing ones is where results start to fall apart.