English日本語한국어

Statistics

AI video prompt corpus statistics

Direct answer: across 5,926 analysed AI video prompts from 1,196 authors, 89.5% specify camera language, 83% specify lighting, 98.9% carry a mood, and 52.6% state a duration. Tracking is the most common camera term (2,443 prompts) and 15 seconds is the dominant duration (71% of prompts that state one).

Computed 2026-09-11 from our own structured corpus (engine: deepseek-flash). Reproducible with pipeline/build_stats.py.

How many prompts specify each field?

FieldPromptsShare
camera5,30289.5%
lighting4,92183%
mood5,86398.9%
duration3,12052.6%
aspect ratio1,61427.2%
negative prompt3,90065.8%
consistency lock5,51293%

Camera and lighting are the most reliably specified fields: roughly 86% of prompts describe both. Aspect ratio is the least specified at 27.2% — creators rarely state it even though it changes the entire shot design.

Which camera movements are most common?

Camera termPromptsShare of corpus
tracking2,44341%
close-up2,34740%
wide shot1,54726%
handheld1,43424%
slow motion1,21521%
orbit80614%
push-in69812%
aerial/drone62911%
pull-out58510%
pan5509%
zoom5049%
static/fixed4848%
slow push-in4618%
POV4167%
tilt3967%
macro3346%
one-take2564%
dolly2204%
whip pan2144%
speed ramp1943%
crane1392%
match cut1192%
rack focus1062%

Which lighting terms are most common?

Lighting termPromptsShare of corpus
natural light1,68929%
volumetric1,36023%
soft light1,04118%
warm tone1,01817%
golden hour99817%
low-key98917%
backlight94816%
practical lights73512%
neon72312%
rim light57410%
silhouette4978%
cool tone4698%
hard light4488%
lens flare3907%
studio lighting2604%
moonlight1843%
high-key1182%
candlelight621%

What durations do AI video prompts target?

Of the 3,120 prompts that state a duration, 71% specify 15 seconds. That single value dominates the corpus far more than any other field, which suggests 15s is the de facto standard clip length for this generation of models.

DurationPromptsShare of stated
15s2,22271%
10s2789%
30s1244%
12s1104%
14s532%
8s451%
16s371%
13s361%
20s311%
45s171%
7s161%
9s150%

What aspect ratios are used?

Aspect ratioPromptsShare of stated
16:982051%
9:1663739%
1:1785%
4:3231%
2.39:1171%
2.35:1131%
3:4101%
21:980%
4:560%
2:310%
19:610%

Which categories are largest?

CategoryPromptsShare of corpus
cinematic-realistic2,71146%
sports-action1,60027%
cinematic-showcase1,51526%
person-character1,41224%
fantasy-magical1,39724%
short-film1,22821%
social-lifestyle1,00117%
brand-commercial93016%
cyberpunk-scifi64111%
anime60910%
3d-cartoon5529%
surreal-dreamlike4758%
animal-pet3897%
nature-landscape3626%
food-drink3586%

A prompt can carry up to three categories, so shares do not sum to 100%.

How was this measured?

Each prompt was ingested from its original public post and analysed into a fixed schema. Camera, lighting and aspect ratio were extracted with a controlled vocabulary; duration and the semantic fields (title, summary, subject, mood) were assigned by an LLM reading the full prompt text. Values outside the controlled vocabulary were rejected, so the term frequencies above reflect a closed list rather than free-text matching.

Corpus: 5,926 prompts, 1,196 authors, source posts from 2025-10-01 to 2026-09-10.