Layer Video Continuity
Overview
A single shot holds its own continuity. A sequence does not: every generation re-invents the face,
the costume, the light and the set unless something carries them across the cut. This skill is about
what carries them. Single-shot motion and camera are
and
;
cutting the finished shots together is
; the storyboard comes from
.
Three things carry continuity, strongest first:
- The last frame of the previous shot as the first frame of the next.
- Character elements: reference images or a clip of the character, attached to every shot.
- One approved still that every shot is drawn from.
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
| Need | Route |
|---|
| Shot N+1 starts where shot N ended | Shot N's video in the slot with |
| A frame at an exact time | on the same guidance entry; it overrides |
| Same character in every shot | , or guidance files |
| Match the motion of an existing clip | |
| Models that accept all of the above | with filter.guidance_file_types
|
| What a slot accepts, and its limits | on the chosen model |
| Explore the whole sequence cheaply | on every shot, complete only the keepers |
A guidance entry is
plus optional
,
and
. A video placed in an image slot (
,
,
,
) contributes one frame: its first frame by default, its last for
. So to
start a shot on the previous shot's ending you must say so:
.
Pick a model by what it accepts
Continuity is a capability question before it is a prompt question. Ask
for
filter.use_case: "image_to_video"
and
filter.guidance_file_types
set to every slot the sequence
needs, for example
["first_frame", "element_frontal_image"]
. Every listed type must be accepted,
so an empty result means the combination is too ambitious: drop the least important slot rather than
inventing a model. Families such as Seedance, Kling or Veo differ in what they take, which is why the
filter, not the family name, decides.
Then
on the first result. It gives each slot's file and length limits and the
family's own prompt guide, which is the right phrasing for that model. Use one model for the whole
sequence: two families render the same element differently, and the cut shows it.
Elements hold the character
Attach the same element files to every shot that shows the character, unchanged. Use a frontal image for the face, reference images
for the costume from other sides, and an element video where the model accepts one. Produce these once from the approved design (
for a
character sheet) and reuse their
values: never regenerate an element mid-sequence.
Elements hold identity, not position. The prompt still states where the character is, what they do
and which way they face.
Write the sequence as a shot list
From the storyboard, write one line per shot before generating anything:
- One action per shot. A shot that has to show a door opening, a reaction and a sword draw will
do none of them well. Split it.
- Screen direction. If the hero exits frame right, they enter the next shot from frame left.
State it in both prompts.
- Eyeline and light. Name the light direction once and repeat it verbatim in every shot of the
scene.
- Cut type. A continuous action chains on the last frame. A cut to a new angle does not chain:
start it from the approved still or the elements, or the new angle inherits the old composition.
Draft the whole sequence first
Where
reports
, render every shot with
, review the
sequence as a cut, then complete only the shots you keep. A completion is a second
with
set to the draft's
draft.completion_base_model_id
,
, and the
draft's
as a guidance file of type
draft.completion_guidance_type
, with no prompt: it
keeps the draft's prompt, motion and length. Estimate a completion with the completion model and the
draft's
. Drafts can expire (
,
), so complete promptly.
Chaining drafts previews the cut cheaply, but a completion re-renders the whole shot, so its last
frame can drift from the draft's and the join shifts. When a join must be exact, complete shot N first
and generate shot N+1 from the completed take; say this costs a second run of each chained shot.
Set length with
.
Worked example
"A 4-shot cutscene: our knight walks to the gate, pushes it open, a dragon looks up, the knight draws
her sword."
- The approved knight design and front view already have values. No upload.
- with
filter.use_case: "image_to_video"
filter.guidance_file_types: ["first_frame", "element_frontal_image", "element_reference_image"]
- Shot list: (1) wide, knight walks left to right toward the gate; (2) continuous, she pushes it
open, chained; (3) new angle, the dragon lifts its head, from an approved dragon still, no knight
elements; (4) medium, knight draws sword, facing right, elements attached.
- Price the job: one estimate per kind (a shot with elements, a chained shot, the dragon shot), then
the four completions at the drafts' durations. Present the total; above 20 CUs wait for an
explicit yes.
- Draft all four, each with the knight elements as
{file_id, type: "element_frontal_image"}
{file_id, type: "element_reference_image"}
{file_id: <shot 1 video>, type: "first_frame", video_frame: "last"}
- Poll each at . Review the four as a sequence, redraft any shot that breaks
screen direction, then complete the keepers and re-chain shot 2 from the completed shot 1.
- Hand the completed values to for the cut.
Common mistakes
- Putting the previous clip in without , so the shot restarts at
the beginning of the last one.
- Choosing the model by family name instead of by .
- Changing models partway through a sequence.
- Regenerating the character's element images between shots.
- Chaining across a cut to a new angle, so the new shot inherits the old composition.
- Packing several actions into one shot.
- Paying for full-quality takes before the sequence has been reviewed as drafts.
- Chaining from a draft when the join must be exact.