Layer Video Direction
Overview
One shot, directed well. A generated shot goes wrong in predictable ways: the camera drifts when it
should hold, two moves fight each other, the action is crammed into the first second or spread so
thin nothing happens. Direction is choosing, before generating, what the camera does, what the
subject does, and how long each takes.
The generation loop and the spend gate are in the
skill; anchoring on a still, loops and
drafts are in
. Holding a character and set across several shots is
.
If a sibling skill named here is missing from your available skills, ask the user to install it
(
npx skills add layerai/skills --skill <name>
); unattended, proceed from tool schemas and flag the
gap.
Quick reference
| Want | Route |
|---|
| A standard camera move | video_effects: [{type, weight}]
|
| A camera that must not move | video_effects: [{type: "STATIC"}]
|
| A named cinematic technique | with , passed as |
| An exact clip length | , on a model filtered with capabilities: {fixed_duration: true}
|
| Models that take structured camera moves | with capabilities: {video_effects: true}
|
types are uppercase:
,
,
,
,
,
,
,
,
,
,
,
,
,
. Support is per model, so read
before choosing one.
runs 0 to
100; leave it unset for the model's default strength and lower it when the move overwhelms the
subject.
One move per shot
A shot carries one camera idea. A push in while orbiting while tilting reads as a malfunction, and
models handle a single clear move far better than a compound one. If the scene needs two, it is two
shots.
Prefer the structured effect over prose for the same move: the effect is the input the model takes
for it. Where the model offers no effect for the move, describe it in the prompt in camera terms
("slow push in toward her face", "the camera cranes up to reveal the city") and keep the rest of the
prompt about the subject.
Choose the move for what it says, not for energy:
- Push in (dolly in): rising tension, attention narrowing to a detail or a face.
- Pull out (dolly out): reveal of scale or isolation.
- Orbit: showcase of a hero, a weapon, a product; it reads as display, not drama.
- Crane up: arrival or ending; crane down settles into a scene.
- Handheld: urgency and presence; wrong for calm or for anything that has to read precisely.
- Static: performance and comedy; lets the action carry the shot.
A dolly zoom (vertigo) is a push in with a counter-zoom, not
; use a
set for it, or describe both halves in the prompt.
Lens, framing and light
Name these in the prompt in production terms, once, and keep them across a scene:
- Framing: extreme wide, wide, medium, close-up, extreme close-up; eye level, low angle, high
angle, top down.
- Lens: wide-angle for space and distortion near the edges, long lens for compressed depth and a
soft background.
- Light: the key's direction and quality (hard noon sun from the left, soft overcast, low warm
backlight), and the time of day. A shot with no stated light gets an even, flat default.
Technique presets
Layer ships technique reference sets that package a camera move, angle, framing, lens, lighting,
composition, atmosphere, genre look, optical or visual effect, timing or performance. Discover them
with
and
set to one of
,
,
,
,
,
,
,
,
,
,
or
; add
for the technique the user named. Pass the chosen set as
reference_sets: [{set_id}]
. Never hard-code a set: the catalogue differs by workspace.
Read
reference_set_contributions
on the estimate. A camera set attached to an image model comes
back
skipped_irrelevant_category
, and any set can be degraded on a model that cannot apply it.
When
is true, say which set did not apply and why; never report it as
applied.
Pacing to the clip
Clips are short, so time the action to the length. Say when things happen: "holds still for the
first second, then turns sharply toward the camera, and the rest of the clip is the reaction".
Without timing the model spreads the action evenly, which reads as slow motion, or front-loads it and
leaves dead frames.
Set
from the beat, not the maximum. Filter for
when the length
matters; models without it choose their own length and ignore the request without an error.
For a performance, give the beat a cause and a reaction: "she hears the door, freezes, then slowly
turns". Emotion words alone ("she looks scared") produce a held expression, not a performance.
Worked example
"A 5-second hero shot of our mech for the trailer: slow, imposing, a dolly zoom feel."
- The approved mech still has a . No upload.
- with
filter.use_case: "image_to_video"
filter.capabilities: {fixed_duration: true}
- with
filter.category: "camera_movement"
- Prompt: "Low angle, wide lens. The mech stands still for the first second, then its head turns
slowly toward the camera and its visor lights up. Hard low backlight, dust in the air."
- with the still as
{file_id, type: "first_frame"}
reference_sets: [{set_id}]
- Execute, poll at , and report whether the set applied.
Common mistakes
- Two or three camera moves in one shot.
- Describing a move in prose when the model takes it as a type.
- Passing as a list of strings instead of objects.
- Leaving the camera unstated and accepting the drift the model adds.
- Hard-coding a technique set id or name from another workspace.
- Reporting a technique set as applied without reading the contribution report.
- Emotion words instead of a timed beat.
- Asking for an exact length on a model without .