Back to Details

layer-video-continuity

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Layer Video Continuity

Layer 视频连续性

Overview

概述

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 
layer-video
and 
layer-video-direction
; cutting the finished shots together is 
layer-video-timeline
; the storyboard comes from 
layer-art-direction
.
Three things carry continuity, strongest first:
  1. The last frame of the previous shot as the first frame of the next.
  2. Character elements: reference images or a clip of the character, attached to every shot.
  3. 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.
单个镜头自身具有连续性。序列则不然：每次生成都会重新创造角色的脸部、服装、光线和场景，除非有某种内容将这些要素跨越剪辑保留下来。本 skill 关注的就是由什么来承载这些要素。单个镜头的动作和摄影机运镜属于 
layer-video
和 
layer-video-direction
；将完成的镜头剪辑在一起属于 
layer-video-timeline
；分镜板来自 
layer-art-direction
。
三种机制可以维持连续性，按强度从高到低排列：
  1. 上一个镜头的最后一帧，作为下一个镜头的第一帧。
  2. 角色 elements：将角色参考图或片段附加到每个镜头。
  3. 一张所有镜头均据此生成的已批准静帧。
如果此处提到的同级 skill 不在可用 skill 中，请让用户安装（
npx skills add layerai/skills --skill <name>
）；在无人值守模式下，根据工具 schema 继续执行并标记该缺口。

Quick reference

快速参考

NeedRoute
Shot N+1 starts where shot N endedShot N's video 
file_id
in the 
first_frame
slot with 
video_frame: "last"
A frame at an exact time
video_frame_seconds
on the same guidance entry; it overrides 
video_frame
Same character in every shot
element_frontal_image
, 
element_reference_image
or 
element_video
guidance files
Match the motion of an existing clip
reference_video
Models that accept all of the above
list_base_models
with 
filter.guidance_file_types
listing every type the sequence will use
What a slot accepts, and its limits
get_base_model
on the chosen model
Explore the whole sequence cheaply
draft: true
on every shot, complete only the keepers
A guidance entry is 
{file_id, type}
plus optional 
video_frame
, 
video_frame_seconds
and 
weight
. A video placed in an image slot (
first_frame
, 
last_frame
, 
reference_image
, 
init_image
) contributes one frame: its first frame by default, its last for 
last_frame
. So to start a shot on the previous shot's ending you must say so: 
video_frame: "last"
.
需求处理路径
镜头 N+1 从镜头 N 的结束处开始镜头 N 视频的 
file_id
，置于 
first_frame
槽位并设置 
video_frame: "last"
获取某个精确时间点的帧在同一个 guidance 条目上使用 
video_frame_seconds
；它会覆盖 
video_frame
每个镜头中保持同一角色
element_frontal_image
、
element_reference_image
或 
element_video
guidance 文件
匹配现有片段的动作
reference_video
接受上述所有输入的模型使用 
list_base_models
，通过 
filter.guidance_file_types
列出序列将使用的每一种类型
某个槽位接受的内容及其限制对所选模型调用 
get_base_model
低成本探索整个序列每个镜头都使用 
draft: true
，只完成最终保留的镜头
guidance 条目由 
{file_id, type}
构成，另含可选的 
video_frame
、
video_frame_seconds
和 
weight
。放入图像槽位（
first_frame
、
last_frame
、
reference_image
、
init_image
）的视频只会提供一帧：默认使用第一帧，而 
last_frame
使用最后一帧。因此，要让一个镜头以上一段视频的结尾开始，必须明确指定：
video_frame: "last"
。

Pick a model by what it accepts

按模型支持项选择模型

Continuity is a capability question before it is a prompt question. Ask 
list_base_models
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 
get_base_model
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.
在考虑提示词之前，连续性首先是一个能力问题。调用 
list_base_models
，设置 
filter.use_case: "image_to_video"
，并将 
filter.guidance_file_types
设为序列所需的每个槽位，例如 
["first_frame", "element_frontal_image"]
。所列的每一种类型都必须被支持，因此结果为空意味着这组要求过高：应删除最不重要的槽位，而不是臆造一个模型。Seedance、Kling 或 Veo 等模型系列支持的输入各不相同，因此应根据筛选条件，而不是系列名称来决定模型。
随后对第一个结果调用 
get_base_model
。它会给出每个槽位的文件与长度限制，以及该系列自己的提示词指南，后者正是该模型适用的措辞。整段序列使用同一个模型：不同系列渲染同一 element 的方式不同，剪辑处会暴露差异。

Elements hold the character

用 elements 保持角色一致

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 (
layer-game-assets
for a character sheet) and reuse their 
file_id
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.
将同一组 element 文件原样附加到每个出现该角色的镜头中。使用正面图固定脸部，使用其他角度的参考图固定服装，并在模型支持时使用 element 视频。根据已批准的设计一次性生成这些文件（角色设定图使用 
layer-game-assets
），然后复用其 
file_id
值：绝不要在序列中途重新生成 element。
elements 负责保持身份一致性，但不负责位置。提示词仍需说明角色在哪里、做什么以及面向哪一边。

Write the sequence as a shot list

将序列写成镜头表

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.
根据分镜板，在生成任何内容之前，每个镜头先写一行：
  • 每个镜头只安排一个动作。 需要同时呈现开门、反应和拔剑的镜头，无法把这些动作都做好。应拆分为多个镜头。
  • 画面方向。 如果主角从画面右侧退出，他们应从下一个镜头的左侧入画。在两个提示词中都明确写出。
  • 视线与光线。 明确一次光线方向，并在该场景的每个镜头中逐字重复。
  • 剪辑类型。 连续动作可基于最后一帧衔接。切换到新角度时不能这样衔接：应从已批准静帧或 elements 开始，否则新角度会继承旧构图。

Draft the whole sequence first

先为整个序列制作草稿

Where 
get_base_model
reports 
capabilities.draft
, render every shot with 
draft: true
, review the sequence as a cut, then complete only the shots you keep. A completion is a second 
execute_forge
with 
base_model_id
set to the draft's 
draft.completion_base_model_id
, 
batch_size: 1
, and the draft's 
file_id
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 
duration_seconds
. Drafts can expire (
draft.status
, 
expires_at
), 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 
duration_seconds
.
如果 
get_base_model
报告 
capabilities.draft
，则使用 
draft: true
渲染每个镜头，把序列作为一段剪辑进行审阅，然后只完成要保留的镜头。完成操作是对 
execute_forge
的第二次调用：将 
base_model_id
设置为草稿的 
draft.completion_base_model_id
，设置 
batch_size: 1
，并将草稿的 
file_id
作为类型为 
draft.completion_guidance_type
的 guidance 文件传入，不提供提示词：这会保留草稿的提示词、运动和长度。使用 completion 模型和草稿的 
duration_seconds
估算完成操作。草稿可能会过期（
draft.status
、
expires_at
），因此应及时完成。
链式衔接草稿可以低成本预览剪辑效果，但完成操作会重新渲染整个镜头，因此其最后一帧可能与草稿发生偏移，衔接点也会随之移动。当衔接必须精确时，先完成镜头 N，再从已完成的拍摄结果生成镜头 N+1；需说明，这会让每个链式镜头额外运行一次。通过 
duration_seconds
设置长度。

Worked example

实例

"A 4-shot cutscene: our knight walks to the gate, pushes it open, a dragon looks up, the knight draws her sword."
  1. The approved knight design and front view already have 
    file_id
    values. No upload.
  2. list_base_models
    with 
    filter.use_case: "image_to_video"
    and 
    filter.guidance_file_types: ["first_frame", "element_frontal_image", "element_reference_image"]
    . Take the first result; 
    get_base_model
    for slot limits, durations, 
    capabilities.draft
    and the prompt guide.
  3. 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.
  4. 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.
  5. Draft all four, each with the knight elements as 
    {file_id, type: "element_frontal_image"}
    and 
    {file_id, type: "element_reference_image"}
    . Shot 2 adds 
    {file_id: <shot 1 video>, type: "first_frame", video_frame: "last"}
    .
  6. Poll each at 
    poll_interval_seconds
    . 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.
  7. Hand the completed 
    file_id
    values to 
    layer-video-timeline
    for the cut.
“ 一段 4 镜头 cutscene：我们的骑士走向城门，推开城门，一条龙抬头，骑士拔出她的剑。”
  1. 已批准的骑士设计和正面视图已有 
    file_id
    值。无需上传。
  2. 调用 
    list_base_models
    ，设置 
    filter.use_case: "image_to_video"
    和 
    filter.guidance_file_types: ["first_frame", "element_frontal_image", "element_reference_image"]
    。取第一个结果；调用 
    get_base_model
    获取槽位限制、时长、
    capabilities.draft
    和提示词指南。
  3. 镜头表：(1) 全景，骑士从左向右走向城门；(2) 连续镜头，她推开城门，链式衔接；(3) 新角度，龙抬起头，从已批准的龙静帧开始，不附加骑士 elements；(4) 中景，骑士拔剑，面向右侧，附加 elements。
  4. 为任务定价：每种类型估算一次（带 elements 的镜头、链式镜头、龙镜头），再按草稿时长估算四次完成操作。给出总价；超过 20 CU 时，等待用户明确同意。
  5. 为全部四个镜头制作草稿，每个镜头都使用骑士 elements：
    {file_id, type: "element_frontal_image"}
    和 
    {file_id, type: "element_reference_image"}
    。镜头 2 添加 
    {file_id: <shot 1 video>, type: "first_frame", video_frame: "last"}
    。
  6. 使用 
    poll_interval_seconds
    轮询每个任务。将四个镜头作为序列进行审阅；若某个镜头破坏画面方向，则重新制作草稿；随后完成保留的镜头，并从已完成的镜头 1 重新链式生成镜头 2。
  7. 将完成的 
    file_id
    值交给 
    layer-video-timeline
    进行剪辑。

Common mistakes

常见错误

  • Putting the previous clip in 
    first_frame
    without 
    video_frame: "last"
    , so the shot restarts at the beginning of the last one.
  • Choosing the model by family name instead of by 
    guidance_file_types
    .
  • 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.
  • 将上一段视频放入 
    first_frame
    ，却未设置 
    video_frame: "last"
    ，导致镜头从上一段的开头重新开始。
  • 按系列名称而不是 
    guidance_file_types
    选择模型。
  • 在序列中途更换模型。
  • 在镜头之间重新生成角色的 element 图像。
  • 跨切换到新角度的剪辑进行链式衔接，导致新镜头继承旧构图。
  • 在一个镜头中塞入多个动作。
  • 在将序列作为草稿审阅之前就为全质量版本付费。
  • 在必须精确衔接时，从草稿进行链式衔接。