video-edit

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Video Edit — Pro Pack on RunComfy

RunComfy 视频编辑专业包

runcomfy.com · Wan 2.7 Edit-Video · Kling Motion-Control Pro · Lucy Edit Restyle · GitHub

Video edit, intent-routed. This skill doesn't lock you to one model — it picks the right video-edit model in the RunComfy catalog based on what the user actually wants: general restyle, motion transfer from a reference clip, or lightweight identity-stable outfit / background swap.

bash

npx skills add agentspace-so/runcomfy-skills --skill video-edit -g

runcomfy.com · Wan 2.7 Edit-Video · Kling Motion-Control Pro · Lucy Edit Restyle · GitHub

视频编辑，意图路由。该Skill不会局限于单一模型——它会根据用户的实际需求，从RunComfy模型库中挑选合适的视频编辑模型：通用风格重塑、参考片段动作迁移，或是轻量级身份稳定的服装/背景替换。

bash

npx skills add agentspace-so/runcomfy-skills --skill video-edit -g

Pick the right model for the user's intent

根据用户意图选择合适的模型

User intent	Model	Why
Restyle a talking-head video — preserve face / pose / lip movement	Wan 2.7 Edit-Video	Strong identity + motion preservation; supports up to 1080p
Swap product background, keep camera motion	Wan 2.7 Edit-Video	Camera motion preserved; one-direction edit honored
Replace packaging design using a reference image	Wan 2.7 Edit-Video + `reference_image`	Reference-conditioned design transfer
Apply cinematic color grade / commercial polish	Wan 2.7 Edit-Video	Good at single-direction global look changes
Transfer precise motion from a reference video to a target character	Kling 2.6 Pro Motion Control	Designed for motion mapping with identity hold
Lip-sync motion of a target character to source video's lip movement	Kling 2.6 Pro Motion Control	Built for tight temporal coherence
Lightweight outfit / costume swap with identity preservation	Lucy Edit Restyle	Core strength is localized identity-stable edits
Identity-stable restyle ("astronaut in desert", "warm golden-hour lighting")	Lucy Edit Restyle	Specializes in temporal consistency for restyle
Default if unspecified	Wan 2.7 Edit-Video	Most versatile, highest resolution

The agent reads this table, classifies the user's intent, and picks the matching subsection below.

用户意图	模型	选择理由
重塑对话头部视频风格——保留面部/姿态/唇部动作	Wan 2.7 Edit-Video	身份与动作保留能力强；支持最高1080p分辨率
替换产品背景，保留镜头运动	Wan 2.7 Edit-Video	可保留镜头运动；支持单向编辑需求
使用参考图替换包装设计	Wan 2.7 Edit-Video + `reference_image`	基于参考图的设计迁移能力
应用电影级调色/商业级优化	Wan 2.7 Edit-Video	擅长单向全局风格调整
将参考视频的精准动作迁移到目标角色	Kling 2.6 Pro Motion Control	专为带身份保留的动作映射设计
将目标角色的唇部动作与源视频唇部动作同步	Kling 2.6 Pro Motion Control	具备极强的时间连贯性
轻量级服装替换，保留身份特征	Lucy Edit Restyle	核心优势是本地化身份稳定编辑
身份稳定风格重塑（如“沙漠中的宇航员”“温暖的黄金时段光线”）	Lucy Edit Restyle	专注于风格重塑的时间一致性
用户未明确指定时的默认选择	Wan 2.7 Edit-Video	功能最全面，支持最高分辨率

Agent会读取此表格，对用户意图进行分类，并选择匹配的下方路径。

Prerequisites

前置条件

RunComfy CLI —
```
npm i -g @runcomfy/cli
```
RunComfy account —
```
runcomfy login
```
.
CI / containers — set
```
RUNCOMFY_TOKEN=<token>
```
.
A source video URL — formats and limits depend on the chosen route.

RunComfy CLI —
```
npm i -g @runcomfy/cli
```
RunComfy账号 —
```
runcomfy login
```
。
CI/容器环境 — 设置环境变量
```
RUNCOMFY_TOKEN=<token>
```
。
源视频URL — 格式与限制取决于所选路径。

Route 1: Wan 2.7 Edit-Video — default for restyle / background / packaging

路径1：Wan 2.7 Edit-Video — 风格重塑/背景/包装替换默认模型

Model:

wan-ai/wan-2-7/edit-video

模型：

wan-ai/wan-2-7/edit-video

Schema

数据结构

Field	Type	Required	Default	Notes
`prompt`	string	yes	—	Lead with preservation. One edit direction per call.
`video`	string	yes	—	MP4/MOV URL, 2–10s, ≤100MB.
`reference_image`	string	no	—	URL — use for direct design / appearance transfer only.
`resolution`	enum	no	(input)	`720p` or `1080p` .
`aspect_ratio`	enum	no	(input)	W:H. Defaults to input.
`duration`	int	no	0	`0` = match input; `2–10` = truncate from start.
`audio_setting`	enum	no	`auto`	`auto` or `origin` (preserve source audio).
`seed`	int	no	—	Reproducibility.

字段	类型	是否必填	默认值	说明
`prompt`	string	是	—	先说明保留需求，每次调用仅指定一种编辑方向。
`video`	string	是	—	MP4/MOV格式URL，时长2–10秒，大小≤100MB。
`reference_image`	string	否	—	URL — 仅用于直接的设计/外观迁移场景。
`resolution`	enum	否	(输入视频分辨率)	`720p` 或 `1080p` 。
`aspect_ratio`	enum	否	(输入视频比例)	宽:高，默认与输入视频一致。
`duration`	int	否	0	`0` = 匹配输入视频时长； `2–10` = 从开头截取对应时长。
`audio_setting`	enum	否	`auto`	`auto` 或 `origin` （保留源视频音频）。
`seed`	int	否	—	用于结果复现。

Invoke

调用示例

Background swap, identity preserved, audio kept:

bash

runcomfy run wan-ai/wan-2-7/edit-video \
  --input '{
    "prompt": "Preserve the speaker'\''s face, pose, and lip movement; change the background to a modern office with neutral lighting.",
    "video": "https://.../speaker.mp4",
    "audio_setting": "origin"
  }' \
  --output-dir <absolute/path>

Packaging swap with reference image:

bash

runcomfy run wan-ai/wan-2-7/edit-video \
  --input '{
    "prompt": "Maintain the original framing and hand movement; replace the packaging design using the reference image.",
    "video": "https://.../hand-holding-package.mp4",
    "reference_image": "https://.../new-packaging.png",
    "audio_setting": "origin"
  }' \
  --output-dir <absolute/path>

背景替换，保留身份与音频：

bash

runcomfy run wan-ai/wan-2-7/edit-video \
  --input '{
    "prompt": "Preserve the speaker'\''s face, pose, and lip movement; change the background to a modern office with neutral lighting.",
    "video": "https://.../speaker.mp4",
    "audio_setting": "origin"
  }' \
  --output-dir <absolute/path>

使用参考图替换包装：

bash

runcomfy run wan-ai/wan-2-7/edit-video \
  --input '{
    "prompt": "Maintain the original framing and hand movement; replace the packaging design using the reference image.",
    "video": "https://.../hand-holding-package.mp4",
    "reference_image": "https://.../new-packaging.png",
    "audio_setting": "origin"
  }' \
  --output-dir <absolute/path>

Prompting tips

提示技巧

Preservation goals first:

"Preserve [face / pose / motion / framing / lip movement]; [then state the change]"

One edit direction per call. Compound edits drift on motion.
reference_image
only when justified (packaging swap, costume swap with target visual). Don't pass refs for general restyle.
audio_setting: "origin"
for talking-head where you don't want soundtrack regenerated.
Source video constraints: 2–10s, ≤100MB.

先明确保留目标：

"Preserve [面部 / 姿态 / 动作 / 构图 / 唇部动作]; [再说明修改需求]"

。

每次调用仅指定一种编辑方向。复合编辑会导致动作偏移。
仅在必要时使用
reference_image
（包装替换、带目标视觉的服装替换）。通用风格重塑场景无需传入参考图。
对话头部视频使用
audio_setting: "origin"
，避免重新生成音轨。
源视频限制：时长2–10秒，大小≤100MB。

Route 2: Kling 2.6 Pro Motion Control — when motion FROM a reference clip is the point

路径2：Kling 2.6 Pro Motion Control — 需从参考片段迁移动作时使用

Model:

kling/kling-2-6/motion-control-pro

Use when the user wants to transfer the motion of a reference video onto a target character (driven by an image OR another video). This isn't restyle — it's motion mapping with identity hold.

模型：

kling/kling-2-6/motion-control-pro

当用户需要将参考视频的动作迁移到目标角色（由图片或另一视频驱动）时使用。这不是风格重塑，而是带身份保留的动作映射。

Schema

数据结构

Field	Type	Required	Notes
`prompt`	string	yes	Describe target motion / style.
`image`	string	yes (image orientation)	Reference for character / background consistency.
`video`	string	yes	Motion reference. 10–30s depending on orientation.
`keep_original_sound`	bool	no	Preserve audio from reference video.
`character_orientation`	enum	yes	`image` (max 10s output) or `video` (max 30s output).

字段	类型	是否必填	说明
`prompt`	string	是	描述目标动作/风格。
`image`	string	是（图片模式）	用于保持角色/背景一致性的参考图。
`video`	string	是	动作参考视频。时长限制取决于模式，10–30秒不等。
`keep_original_sound`	bool	否	保留参考视频的音频。
`character_orientation`	enum	是	`image` （输出最长10秒）或 `video` （输出最长30秒）。

Invoke

调用示例

bash

runcomfy run kling/kling-2-6/motion-control-pro \
  --input '{
    "prompt": "A young american woman dancing",
    "image": "https://.../target-character.jpg",
    "video": "https://.../motion-reference-dance.mp4",
    "character_orientation": "image",
    "keep_original_sound": true
  }' \
  --output-dir <absolute/path>

bash

runcomfy run kling/kling-2-6/motion-control-pro \
  --input '{
    "prompt": "A young american woman dancing",
    "image": "https://.../target-character.jpg",
    "video": "https://.../motion-reference-dance.mp4",
    "character_orientation": "image",
    "keep_original_sound": true
  }' \
  --output-dir <absolute/path>

Prompting tips

提示技巧

Subject must be > 5% of frame in the image reference for clean identity hold.

Spatial constraints help:

"character on left side, background motion right"

Simplify if results drift between iterations — drop adjectives, keep core motion description.
character_orientation: "image"
caps output at 10s;
```
"video"
```
allows 30s.

图片参考中的主体需占画面的5%以上，才能确保清晰的身份保留。
添加空间约束有助于提升效果：
```
"角色在左侧，背景动效在右侧"
```
。
若结果出现偏移，简化提示——去掉修饰词，保留核心动作描述。
character_orientation: "image"
输出时长上限为10秒；
```
"video"
```
允许最长30秒输出。

Route 3: Lucy Edit Restyle — lightweight identity-stable restyle / outfit swap

路径3：Lucy Edit Restyle — 轻量级身份稳定风格重塑/服装替换

Model:

decart/lucy-edit/restyle

Use when the edit is localized style modification — outfit swap, scene relight, atmospheric restyle — and identity preservation is critical. Lighter-weight than Wan 2.7 Edit; capped at 720p.

模型：

decart/lucy-edit/restyle

当编辑需求为本地化风格修改——服装替换、场景重新打光、氛围风格重塑——且身份保留至关重要时使用。比Wan 2.7 Edit更轻量化，分辨率上限为720p。

Schema

数据结构

Field	Type	Required	Default	Notes
`prompt`	string	yes	—	Natural-language edit instruction.
`video_url`	string	yes	—	MP4/MOV/WEBM/GIF.
`resolution`	enum	no	`720p`	`720p` only on this tier.

字段	类型	是否必填	默认值	说明
`prompt`	string	是	—	自然语言编辑指令。
`video_url`	string	是	—	MP4/MOV/WEBM/GIF格式。
`resolution`	enum	否	`720p`	此模型仅支持 `720p` 分辨率。

Invoke

调用示例

Outfit swap:

bash

runcomfy run decart/lucy-edit/restyle \
  --input '{
    "prompt": "Change outfit to professional business attire; preserve face and motion.",
    "video_url": "https://.../subject-walking.mp4"
  }' \
  --output-dir <absolute/path>

Atmospheric restyle:

bash

runcomfy run decart/lucy-edit/restyle \
  --input '{
    "prompt": "Make lighting warm and golden hour; preserve face, pose, and motion.",
    "video_url": "https://.../subject-portrait.mp4"
  }' \
  --output-dir <absolute/path>

服装替换：

bash

runcomfy run decart/lucy-edit/restyle \
  --input '{
    "prompt": "Change outfit to professional business attire; preserve face and motion.",
    "video_url": "https://.../subject-walking.mp4"
  }' \
  --output-dir <absolute/path>

氛围风格重塑：

bash

runcomfy run decart/lucy-edit/restyle \
  --input '{
    "prompt": "Make lighting warm and golden hour; preserve face, pose, and motion.",
    "video_url": "https://.../subject-portrait.mp4"
  }' \
  --output-dir <absolute/path>

Prompting tips

提示技巧

Localized change phrasing wins. "Outfit", "lighting", "background" — pick one bucket.
Preserve identity goals —
```
"preserve face and motion"
```
is enough; don't over-specify.
Avoid total replacement ("astronaut in space" works; "swap subject for a different person" doesn't). Lucy is built for localized style mods, not full character swap.
No aspect ratio control — output matches input. Cropping happens server-side if you don't pre-match.

使用本地化修改表述效果更佳。明确“服装”“光线”“背景”——选择一个类别。
明确身份保留目标——
```
"preserve face and motion"
```
即可，无需过度指定。
避免完全替换主体（“太空里的宇航员”可行；“将主体换成另一个人”不可行）。Lucy专为本地化风格修改设计，不支持完整角色替换。
不支持比例控制——输出比例与输入一致。若未预先匹配，服务器端会自动裁剪。

Limitations

限制条件

Each route inherits its model's limits. Wan 2.7 Edit: 2–10s, 1080p ceiling. Kling: 10s (image orientation) or 30s (video orientation). Lucy: 720p ceiling, no aspect control.
No multi-route blending. This skill picks one model per call.
Brand-specific overrides — if the user named a specific model, route to the corresponding brand skill (
```
wan-2-7
```
) for fuller treatment.

每条路径继承对应模型的限制。Wan 2.7 Edit：时长2–10秒，分辨率上限1080p。Kling：图片模式最长10秒，视频模式最长30秒。Lucy：分辨率上限720p，无比例控制。
不支持多路径混合。每次调用该Skill仅选择一个模型。
品牌特定覆盖——若用户指定了特定模型，需路由到对应品牌Skill（如
```
wan-2-7
```
）以获得更完整的处理。

Exit codes

退出码

code	meaning
0	success
64	bad CLI args
65	bad input JSON / schema mismatch
69	upstream 5xx
75	retryable: timeout / 429
77	not signed in or token rejected

Full reference: docs.runcomfy.com/cli/troubleshooting.

代码	含义
0	成功
64	CLI参数错误
65	输入JSON错误/数据结构不匹配
69	上游服务5xx错误
75	可重试：超时/429请求过多
77	未登录或令牌被拒绝

完整参考：docs.runcomfy.com/cli/troubleshooting。

How it works

工作原理

The skill picks one of Wan 2.7 Edit-Video / Kling 2.6 Pro Motion Control / Lucy Edit Restyle based on user intent and invokes

runcomfy run <model_id>

with the matching JSON body. The CLI POSTs to the Model API, polls the request, fetches the result, and downloads any

.runcomfy.net

.runcomfy.com

URL into

--output-dir

Ctrl-C

cancels the remote request before exit.

该Skill会根据用户意图选择Wan 2.7 Edit-Video/Kling 2.6 Pro Motion Control/Lucy Edit Restyle中的一个模型，并使用匹配的JSON参数调用

runcomfy run <model_id>

命令。CLI会向Model API发送POST请求，轮询请求状态，获取结果，并将

.runcomfy.net

.runcomfy.com

域名下的生成文件下载到

--output-dir

指定路径。按

Ctrl-C

会在退出前取消远程请求。

Security & Privacy

安全与隐私

Token storage:
```
runcomfy login
```
writes the API token to
```
~/.config/runcomfy/token.json
```
with mode 0600 (owner-only read/write). Set
```
RUNCOMFY_TOKEN
```
env var to bypass the file entirely in CI / containers.
Input boundary: the user prompt is passed as a JSON string to the CLI via
```
--input
```
. The CLI does NOT shell-expand the prompt; it transmits the JSON body directly to the Model API over HTTPS. No shell injection surface from prompt content.
Third-party content: image / mask / video URLs you pass are fetched by the RunComfy model server, not by the CLI on your machine. Treat external URLs as untrusted; image-based prompt injection is a known risk for any image-edit / video-edit model.
Outbound endpoints: only
```
model-api.runcomfy.net
```
(request submission) and
```
*.runcomfy.net
```
/
```
*.runcomfy.com
```
(download whitelist for generated outputs). No telemetry, no callbacks.
Generated-file size cap: the CLI aborts any single download > 2 GiB to prevent disk-fill from a malicious or runaway model output.

令牌存储：
```
runcomfy login
```
会将API令牌写入
```
~/.config/runcomfy/token.json
```
，权限为0600（仅所有者可读写）。在CI/容器环境中，可设置环境变量
```
RUNCOMFY_TOKEN
```
来绕过文件存储。
输入边界：用户提示会作为JSON字符串通过
```
--input
```
参数传递给CLI。CLI不会对提示内容进行shell展开，而是直接通过HTTPS将JSON主体传输给Model API。提示内容不存在shell注入风险。
第三方内容：你传入的图片/遮罩/视频URL由RunComfy模型服务器获取，而非本地CLI。请将外部URL视为不可信内容；基于图片的提示注入是所有图片/视频编辑模型的已知风险。
出站端点：仅允许访问
```
model-api.runcomfy.net
```
（请求提交）和
```
*.runcomfy.net
```
/
```
*.runcomfy.com
```
（生成文件下载白名单）。无遥测数据，无回调。
生成文件大小限制：CLI会终止任何超过2 GiB的单个下载，防止恶意或失控模型输出占满磁盘。