scenario-video-editing

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Scenario Video Editing

Scenario 视频编辑

Overview

概述

Every image post-processing effect has a video twin, and each is a

model_run

on a tool model: one clip in, a few numbers, one clip out. Generating or restyling footage, lipsync, dubbing and upscaling are

scenario-video

; concatenating, compositing and captioning a cut are

scenario-video-assembly

; the still-image side is

scenario-image-editing

. Connection and the core loop:

scenario

. If a sibling skill named here is missing from your available skills, ask the user to install it (

npx skills add scenario-labs/skills --skill <name>

); unattended, proceed from tool schemas and flag the gap.

每个图像后处理效果都有对应的视频版本，且每个效果都是工具模型上的一次

model_run

：输入一个视频片段，调整若干参数，输出一个视频片段。生成或重制素材风格、口型同步、配音和超分辨率属于

scenario-video

范畴；拼接、合成和为剪辑添加字幕属于

scenario-video-assembly

范畴；静态图像编辑则对应

scenario-image-editing

。连接与核心循环：

scenario

。如果你的可用技能中缺少此处提到的同类技能，请让用户安装（命令：

npx skills add scenario-labs/skills --skill <name>

）；若处于无人值守模式，则从工具schema开始执行并标记缺失项。

The twin rule

孪生规则

A video effect's id is the image id with

-video

appended, its file field is

video

rather than

image

, and the knobs are identical:

model_scenario-postprocessing-lut-video

takes the same

lutStyle

enum and

lutIntensity

model_scenario-postprocessing-lut

. All eighteen have twins, from blur and color correction through oilify, posterize and vignette.

One twin differs: Dissolve (Video) blends the clip with a still

dissolveImage

, not a second clip; crossfading two clips is a concat transition.

视频效果的ID是对应图像效果ID后追加

-video

，其文件字段为

video

而非

image

，且可调参数完全一致：

model_scenario-postprocessing-lut-video

与

model_scenario-postprocessing-lut

使用相同的

lutStyle

枚举值和

lutIntensity

参数。从模糊、色彩校正到油画效果、色调分离、暗角，全部18种效果都有对应的视频版本。

有一个孪生效果是例外：Dissolve（视频版）是将片段与静态的

dissolveImage

混合，而非与另一个片段混合；两个片段的交叉淡入淡出属于拼接转场效果。

Quick reference

快速参考

Need	Model or query
Grade or stylize	`filters={"tags": ["Post Processing"]}` , plus the effect name as `query`
Trim to a range	`model_scenario-video-cut` ( `startTime` , `endTime` )
Cut into segments	`model_scenario-video-split` ( `cutPoints` ; N points give N+1 clips)
Rescale or re-encode	`model_scenario-resize-video`
Play a clip backwards	`model_reverse-video`
Frames out, frames in	`model_scenario-video-to-image-seq` , `model_scenario-image-seq-to-video`
Subjects as layers	`model_scenario-video-layers-extractor`
Masks, cutouts	`recommend` with the need in the user's own words
Pull the audio track	`model_scenario-audio-extract`

Extracted frames carry no index and share one

createdAt

, so their order exists only in the job row's

assetIds

, and that list has come back out of time order (a confirmed defect at authoring time). The extractor takes a scalar

video

; every frame is

extractAllFrames: true

, and

frameInterval

(default 24 at authoring time, about one frame a second on a 24 fps clip) applies only when that flag is off. Check that the row holds exactly the clip's

nbFrames

ids (

asset_get

reports it beside

frameRate

; a short row is a dropped frame, which no reordering fixes), then, before reassembling with

model_scenario-image-seq-to-video

or handing frames on, lay the returned ids into

model_scenario-grid-maker

in that order (a fixed first-party id: Scenario's single grid tool; its

images

field takes an array of 1 to 100 ids and ignores a bare id while the run still succeeds, so past 100 frames sheet in batches or raise

frameInterval

; set

columns

, default 3 and up to 20, so a batch reads as a near-square sheet) and read the sheet against the clip's free

firstFrame

and

lastFrame

and its motion; a frame that breaks continuity is out of place, and the corrected order travels as your own id list from then on. Never rebuild order from listings or timestamps, and a preview that runs backwards on a clean sheet is the assembler's

pingpong

flag, not the order.

A cutout with transparency never ships as mp4: at authoring time the removal models carried alpha only as WebM or ProRes 4444 MOV, so read the output-format enum off

model_schema_get

and agree the container with the user before pricing the run.

Effect lookups go through

search

target="models"

public=true

. The

model_scenario-

ids are constants: each is Scenario's single deterministic tool for its operation, so discovery would only re-derive it.

model_reverse-video

sits outside that set and is an authoring-time hit: re-discover it by name (

search

query="video reverse"

需求	模型或查询
调色或风格化	`filters={"tags": ["Post Processing"]}` ，并将效果名称作为 `query` 参数
裁剪到指定时间范围	`model_scenario-video-cut` （参数： `startTime` 、 `endTime` ）
切割为多段	`model_scenario-video-split` （参数： `cutPoints` ；N个切割点会生成N+1个片段）
缩放或重新编码	`model_scenario-resize-video`
倒放片段	`model_reverse-video`
帧提取与帧合成	`model_scenario-video-to-image-seq` 、 `model_scenario-image-seq-to-video`
将主体作为图层	`model_scenario-video-layers-extractor`
蒙版、抠图	使用 `recommend` 并以用户自己的语言描述需求
提取音轨	`model_scenario-audio-extract`

提取的帧没有索引，且共享同一个

createdAt

时间戳，因此它们的顺序仅存在于任务行的

assetIds

中，而该列表返回时并非按时间顺序排列（这是编写本文时已确认的缺陷）。提取器接收一个标量

video

参数；当

extractAllFrames: true

时会提取所有帧，而

frameInterval

（编写本文时默认值为24，对于24fps的片段约为每秒一帧）仅在该标志为关闭状态时生效。

请检查任务行中的ID数量是否与片段的

nbFrames

完全一致（

asset_get

会在

frameRate

旁返回该值；如果行长度不足说明有丢帧，这是重排无法解决的问题）。然后，在使用

model_scenario-image-seq-to-video

重新合成或交付帧之前，将返回的ID按顺序传入

model_scenario-grid-maker

（这是一个固定的官方ID：Scenario唯一的网格工具；其

images

字段接收1到100个ID组成的数组，若传入单个裸ID会被忽略但任务仍会成功，因此超过100帧时需要分批处理或增大

frameInterval

；设置

columns

参数，默认值为3，最大为20，这样一批帧会以接近正方形的网格形式呈现），并结合片段的

firstFrame

、

lastFrame

及其运动规律来核对网格中的帧；如果某一帧破坏了连续性，说明它的位置不对，之后就使用你自己整理好的正确ID顺序。绝对不要通过列表或时间戳重建顺序，另外，如果在正确排列的网格上预览出现倒放的情况，是合成器的

pingpong

标志导致的，而非顺序问题。

带透明度的抠图结果绝对不会以mp4格式输出：编写本文时，抠图模型仅支持WebM或ProRes 4444 MOV格式携带alpha通道，因此请通过

model_schema_get

读取输出格式枚举值，并在为任务定价前与用户确认容器格式。

效果查询通过

search

接口进行，参数为

target="models"

、

public=true

。以

model_scenario-

开头的ID都是常量：每个ID对应Scenario中执行该操作的唯一确定性工具，因此发现操作只会重新推导出相同的ID。

model_reverse-video

不在这个集合中，是编写本文时的热门工具：可通过名称重新发现它（

search

的

query="video reverse"

）。

Cost follows the clip, so trim first

成本由片段决定，因此先裁剪

On the video twins the

video

input carries

cost_impact: true

, which the image versions do not: price tracks the footage rather than the settings. Trim to the frames that ship, then grade;

dry_run=true

prices a payload before it runs. Video tools also outlast

model_run

's wait window, so launch with

wait=false

and follow with

jobs_wait

, re-calling it with the returned

pending_job_ids

. A client-side timeout on

jobs_wait

is as harmless as the server's own: re-call it with the same ids rather than treating the job as lost.

Checking costs nothing:

asset_get

returns

firstFrame

and

lastFrame

as their own asset ids, so

asset_display

one to confirm a grade before chaining another billable run onto it.

在视频孪生效果中，

video

输入带有

cost_impact: true

属性（图像版本则没有）：价格由素材时长而非设置决定。先裁剪到最终需要的帧范围，再进行调色；设置

dry_run=true

可在运行前计算任务的价格。视频工具的运行时间也会超过

model_run

的等待窗口，因此请使用

wait=false

启动任务，然后调用

jobs_wait

，传入返回的

pending_job_ids

进行轮询。

jobs_wait

的客户端超时和服务端超时一样都不会造成问题：使用相同的ID重新调用即可，不要认为任务已经丢失。

检查是免费的：

asset_get

会将

firstFrame

和

lastFrame

作为独立的资产ID返回，因此可以用

asset_display

查看其中一帧来确认调色效果，然后再串联下一个付费任务。

Field names drift between neighbors

相邻工具的字段名差异

Video Cut and the effect twins take a scalar
```
video
```
. Resize Video takes
```
video
```
as an
```
array: true
```
field capped at one item, where a bare id is dropped silently; its size is
```
width
```
and
```
height
```
in pixels, both optional, and one alone keeps the aspect ratio.
The output format field is
```
outputFormat
```
on cut and split,
```
videoOutputFormat
```
on resize.
```
preserveAudio
```
defaults to true on cut, split and resize; the effects expose no audio field and pass the track through.
Enum values are copied, not retyped: one
```
lutStyle
```
string contains a space.
```
asset_download
```
takes no
```
format
```
for a video: it converts image formats only. A GIF from the sequence tool is an image asset and takes
```
format: "gif"
```
; the
```
png
```
default flattens it to one frame.

视频裁剪（Video Cut）和效果孪生工具接收标量
```
video
```
参数。视频缩放（Resize Video）的
```
video
```
字段是
```
array: true
```
类型，最多包含1个元素，若传入单个裸ID会被静默丢弃；其尺寸参数为像素单位的
```
width
```
和
```
height
```
，两者都是可选的，仅设置一个时会保持宽高比。
输出格式字段在裁剪和分割工具中是
```
outputFormat
```
，在缩放工具中是
```
videoOutputFormat
```
。
```
preserveAudio
```
在裁剪、分割和缩放工具中默认值为true；效果类工具不提供音频相关字段，会直接透传音轨。
枚举值是直接复制的，而非重新定义：有一个
```
lutStyle
```
的字符串值包含空格。
```
asset_download
```
对于视频不接受
```
format
```
参数：它仅支持转换图像格式。序列工具生成的GIF属于图像资产，可使用
```
format: "gif"
```
参数；默认的
```
png
```
格式会将其扁平化为单帧。

Resizing is not reframing

缩放不等于重构图

No tool model repaints a video's canvas. Resize Video takes

fit

contain

(default) fits the clip inside the target,

stretch

forces the size and distorts,

cover

fills the target and center-crops the rest.

cover

is the cheap way to an exact ratio when losing the edges is acceptable, but none of them gives a 16:9 clip a vertical frame with the whole picture kept, so that brief needs a decision before any spend, between two routes an order of magnitude apart in price.

Generative reframe (
```
query="reframe"
```
, Luma Ray 3.2 Reframe and Wan 2.2 Reframe,
```
scenario-video
```
territory) outpaints past the frame and keeps the whole picture, at by far the highest price in such a job. Resolution ceilings bite: a schema can allow a vertical ratio and its top resolution tier separately yet reject the pair at run time.
Compositor (Video Studio, cropping or pillarboxing onto a vertical canvas) is cheap but throws away width or adds bars, and its layer geometry is
```
scenario-video-assembly
```
's contract rather than a one-line setting.

dry_run

prices a payload without validating it, so either route can bill for a run that fails outright or returns a mis-composed frame at exactly the right dimensions.

没有任何工具模型会重绘视频的画布。视频缩放工具支持

fit

参数：

contain

（默认值）将片段适配到目标尺寸内，

stretch

强制拉伸到目标尺寸（会导致变形），

cover

填充目标尺寸并对超出部分进行中心裁剪。如果可以接受边缘被裁剪，

cover

是获得精确比例的低成本方式，但这三种模式都无法在保留完整画面的前提下将16:9的片段转为竖屏格式，因此这类需求在产生任何费用前需要先确定方案，两种可选方案的价格相差一个数量级。

生成式重构图（
```
query="reframe"
```
，包括Luma Ray 3.2 Reframe和Wan 2.2 Reframe，属于
```
scenario-video
```
范畴）通过外绘扩展画面边界，保留完整画面，是这类任务中价格最高的方案。分辨率上限会带来限制：schema可能单独允许竖屏比例和最高分辨率档位，但在运行时会拒绝两者的组合。
合成器（Video Studio，在竖屏画布上裁剪或添加上下黑边）成本较低，但会损失画面宽度或添加黑边，其图层几何设置属于
```
scenario-video-assembly
```
的约定内容，而非单行参数设置。

dry_run

仅计算任务价格而不进行验证，因此无论选择哪种方案，都有可能出现任务完全失败、或者返回尺寸正确但构图错误的帧却仍被收费的情况。

Worked example: a graded cutdown

示例：带调色的精简剪辑

Launch every

model_run

below with

wait=false

and retire it with

jobs_wait

before the next step reads its asset.

```
asset_get
```
the master and read
```
properties.duration
```
before choosing times.
Trim:
```
model_scenario-video-cut
```
with
```
startTime
```
and
```
endTime
```
in seconds. Going first is what makes every later step cheaper.
Reshape:
```
model_scenario-resize-video
```
,
```
video
```
as a one-item array,
```
width
```
and
```
height
```
at the delivery size,
```
videoOutputFormat: "mp4"
```
.
```
fit
```
settles the shape at this step rather than later:
```
cover
```
lands an exact ratio once the edges are spendable, and a shape that has to keep the whole picture is the reframe decision above.
Grade:
```
model_schema_get
```
, then the LUT twin with
```
lutIntensity
```
near 0.6.
Texture:
```
model_schema_get
```
, then the Grain twin with
```
grainProfile
```
(a 22-value enum, default
```
kodak_portra_400
```
at authoring time) on that output, last, so its grain is sized for the delivered frame rather than resampled by a later resize.
```
asset_display
```
the result's
```
firstFrame
```
to confirm the look, then
```
asset_download
```
with no
```
format
```
.

以下所有

model_run

都使用

wait=false

启动，并在下一步读取其资产前通过

jobs_wait

等待任务完成。

调用
```
asset_get
```
获取主素材信息，读取
```
properties.duration
```
后再选择时间范围。
裁剪：使用
```
model_scenario-video-cut
```
，参数为秒级的
```
startTime
```
和
```
endTime
```
。先做裁剪能降低后续所有步骤的成本。
调整尺寸：使用
```
model_scenario-resize-video
```
，
```
video
```
参数为单元素数组，
```
width
```
和
```
height
```
设置为交付尺寸，
```
videoOutputFormat: "mp4"
```
。
```
fit
```
参数在这一步就确定了画面形状，而非后续步骤：如果可以接受边缘被裁剪，
```
cover
```
可以得到精确的比例；如果必须保留完整画面，则需要采用上文提到的重构图方案。
调色：调用
```
model_schema_get
```
，然后使用LUT的视频孪生版本，
```
lutIntensity
```
设置在0.6左右。
添加质感：调用
```
model_schema_get
```
，然后在调色后的输出上使用Grain（胶片颗粒）的视频孪生版本，参数为
```
grainProfile
```
（一个有22个值的枚举，编写本文时默认值为
```
kodak_portra_400
```
）。这一步放在最后，这样颗粒的大小是适配最终交付帧的，而不会被后续的缩放重新采样。
用
```
asset_display
```
查看结果的
```
firstFrame
```
确认效果，然后使用不带
```
format
```
参数的
```
asset_download
```
下载。

Common mistakes

常见错误

Grading each source clip and then concatenating: grade the finished master once, or the shots drift apart.
Reaching for local ffmpeg, or for an MCP tool named
```
video_edit
```
: the surface is
```
model_run
```
on tool models.
Polling
```
job_get
```
in a loop instead of
```
jobs_wait
```
, whose timeout is not an error.
Trusting a Grain profile to add grain: the 22 profiles are looks, not intensities, and some soften the picture instead. Compare a frame against the input.

先对每个源片段调色再拼接：应该对最终的完整素材只做一次调色，否则不同镜头的色调会不一致。
试图使用本地ffmpeg，或者名为
```
video_edit
```
的MCP工具：实际操作入口是工具模型上的
```
model_run
```
。
循环调用
```
job_get
```
轮询而非使用
```
jobs_wait
```
：
```
jobs_wait
```
的超时并不是错误。
误以为Grain配置文件只是添加颗粒：这22个配置文件是不同的风格效果，而非不同的颗粒强度，有些反而会让画面变柔和。请将输出帧与输入帧对比确认。