Y
Prompt Workshop
Article · AI video

AI Video Lens Language

Shot size, camera motion, focal length and pacing are the four dimensions of cinematographic vocabulary. Mastering them dramatically improves AI video success.

Shot size

TermUse
extreme wide shotShow environment scale
wide shotSubject in environment
full shotFull body
medium shotWaist up
close-upHead and shoulders
extreme close-upEye / hand / detail

Camera motion

Term
locked-off / static
dolly in / push in
dolly out / pull back
tracking left / right
following shot
crane up / crane down
orbit / arc shot
handheld (not recommended for AI video)

Focal length

LengthLook
14–24mm ultra-wideExaggerated perspective, depth
35mm wideDocumentary feel
50mm standardClose to the eye
85mm portraitCompression, shallow DoF
135mm longHeavy compression, cinematic

Pacing

  • slow steady
  • real-time pacing
  • slow motion 120fps look
  • time-lapse

Frequently asked questions

Does AI video read handheld?

Yes but unstably — often becomes jitter. Prefer "gentle handheld feel".

Do models actually read focal lengths?

Runway, Sora, Kling respond to focal-length cues, affecting depth and compression.

Try this parameter live in the editor

The local editor includes Midjourney / SDXL / Flux templates with a visible, editable parameter panel.

Open the editor →
Yan · AI Prompt Workshop editorial team|Last updated on 2026-06-12。This site does not call any cloud model. Every prompt and parameter in this article was tested and refined locally by the editorial team.