image-edit

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Image Edit — Pro Pack on RunComfy

RunComfy 图像编辑专业套件

runcomfy.com · Nano Banana Edit · GPT Image 2 Edit · Flux Kontext · Z-Image Inpaint · GitHub

Image edit, intent-routed. This skill doesn't lock you to one model — it picks the right edit model in the RunComfy catalog based on what the user actually wants: batch identity-preservation, multilingual text rewrite, single-shot precise edit, or mask-driven region replacement.

bash

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

runcomfy.com · Nano Banana Edit · GPT Image 2 Edit · Flux Kontext · Z-Image Inpaint · GitHub

基于意图路由的图像编辑。该技能不会限制你使用单一模型——它会根据用户的实际需求，从RunComfy模型库中挑选合适的编辑模型：批量保留主体特征、多语言文字改写、单指令精准编辑或基于蒙版的区域替换。

bash

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

Pick the right model for the user's intent

根据用户意图选择合适模型

User intent	Model	Why
Batch edit 1–20 images consistently (SKU gallery, A/B variants)	Nano Banana Edit	Up to 20 input images per call; locked aspect/resolution for series
Swap background, preserve subject identity	Nano Banana Edit	Strong identity preservation under "keep X unchanged" prompts
Localized object removal / addition with spatial language ("the left object", "upper-right corner")	Nano Banana Edit	Honors directional spatial scope
Multilingual / non-Latin in-image text rewrite (Japanese kana, Cyrillic, Arabic)	GPT Image 2 Edit	Strongest in class for multilingual typography
Multi-reference composition (subject from img1, scene from img2, palette from img3)	GPT Image 2 Edit	Numbered refs route cues correctly
Layout-precise repositioning ("move headline from top-right to bottom-center")	GPT Image 2 Edit	Directional language honored at layout level
Identity preservation across translated headline variants	GPT Image 2 Edit	Same source asset → many language variants, identity stable
Single-shot precise local edit ("she's now holding an orange umbrella")	Flux Kontext Pro	Single-ref single-instruction, high-fidelity preservation
Mask-driven object removal (cables, watermarks, distractions)	Z-Image Turbo Inpaint	Mask-required, strength-tunable, edge-consistent
Mask-driven region replacement (full background swap with mask)	Z-Image Turbo Inpaint	High strength + clean mask = clean replacement
Default if unspecified	Nano Banana Edit	Most flexible, supports both single and batch

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
批量编辑1-20张图片并保持一致性（SKU图库、A/B测试变体）	Nano Banana Edit	每次调用最多支持20张输入图片；可锁定宽高比/分辨率以保证系列一致性
替换背景，保留主体特征	Nano Banana Edit	在“保持X不变”的提示下，主体特征保留能力出色
使用空间语言进行局部物体移除/添加（“左侧物体”“右上角”）	Nano Banana Edit	可识别并遵循方向性空间范围
多语言/非拉丁语系图像内文字改写（日文假名、西里尔字母、阿拉伯语）	GPT Image 2 Edit	多语言排版能力业内领先
多参考图合成（主体来自图1，场景来自图2，调色来自图3）	GPT Image 2 Edit	可通过编号参考图正确传递线索
布局精准重定位（“将标题从右上角移至底部中央”）	GPT Image 2 Edit	可在布局层面遵循方向性语言指令
翻译标题变体时保留主体特征	GPT Image 2 Edit	同一源素材生成多语言变体，主体特征保持稳定
单指令精准局部编辑（“她现在手持一把橙色雨伞”）	Flux Kontext Pro	单参考图单指令，高保真保留原有特征
基于蒙版的物体移除（线缆、水印、干扰元素）	Z-Image Turbo Inpaint	需配合蒙版使用，强度可调，边缘过渡自然
基于蒙版的区域替换（通过蒙版完全替换背景）	Z-Image Turbo Inpaint	高强度蒙版可实现干净的替换效果
用户未指定时的默认选择	Nano Banana Edit	灵活性最高，支持单张和批量编辑

智能代理会读取此表格，对用户意图进行分类，并选择对应的操作路径。

Prerequisites

前置条件

RunComfy CLI —
```
npm i -g @runcomfy/cli
```
RunComfy account —
```
runcomfy login
```
.
CI / containers — set
```
RUNCOMFY_TOKEN=<token>
```
.

RunComfy CLI —
```
npm i -g @runcomfy/cli
```
RunComfy账户 —
```
runcomfy login
```
CI/容器环境 — 设置环境变量
```
RUNCOMFY_TOKEN=<token>
```

Route 1: Nano Banana Edit — default for general edit + batch

路径1：Nano Banana Edit — 通用编辑和批量编辑默认选择

Model:

google/nano-banana-2/edit

模型：

google/nano-banana-2/edit

Schema

参数 schema

Field	Type	Required	Default	Notes
`prompt`	string	yes	—	Lead with preservation goals, end with the change.
`image_urls`	array	yes	—	1–20 publicly-fetchable HTTPS URLs.
`number_of_images`	int	no	1	1–4 outputs per call.
`aspect_ratio`	enum	no	`auto`	`auto` follows input; lock for batch consistency.
`resolution`	enum	no	`1K`	`0.5K` / `1K` / `2K` / `4K` .
`output_format`	enum	no	`png`	`png` / `jpeg` / `webp` .
`seed`	int	no	—	Reproducibility.
`enable_web_search`	bool	no	false	Web-grounded edits (extra latency).

字段	类型	是否必填	默认值	说明
`prompt`	字符串	是	—	先说明需要保留的内容，再描述修改需求
`image_urls`	数组	是	—	1-20个可公开访问的HTTPS图片链接
`number_of_images`	整数	否	1	每次调用可生成1-4张输出图片
`aspect_ratio`	枚举值	否	`auto`	`auto` 跟随输入图片；批量编辑时锁定可保证一致性
`resolution`	枚举值	否	`1K`	`0.5K` / `1K` / `2K` / `4K`
`output_format`	枚举值	否	`png`	`png` / `jpeg` / `webp`
`seed`	整数	否	—	用于生成结果可复现
`enable_web_search`	布尔值	否	false	基于网络搜索的编辑（会增加延迟）

Invoke

调用示例

bash

runcomfy run google/nano-banana-2/edit \
  --input '{
    "prompt": "Keep the subject identity, pose, and clothing unchanged. Convert the background into a rainy neon cyberpunk street.",
    "image_urls": ["https://.../portrait.jpg"]
  }' \
  --output-dir <absolute/path>

Batch (lock aspect + resolution):

bash

runcomfy run google/nano-banana-2/edit \
  --input '{
    "prompt": "Replace the watermark in the bottom-right with the text \"AURA\" in clean white sans-serif. Keep everything else exactly as in the input.",
    "image_urls": ["https://.../sku-1.jpg", "https://.../sku-2.jpg", "https://.../sku-3.jpg"],
    "aspect_ratio": "1:1",
    "resolution": "1K"
  }' \
  --output-dir <absolute/path>

bash

runcomfy run google/nano-banana-2/edit \
  --input '{
    "prompt": "保留主体身份、姿势和服装不变。将背景改为雨夜霓虹赛博朋克街道。",
    "image_urls": ["https://.../portrait.jpg"]
  }' \
  --output-dir <absolute/path>

批量编辑（锁定宽高比和分辨率）：

bash

runcomfy run google/nano-banana-2/edit \
  --input '{
    "prompt": "将右下角的水印替换为干净的白色无衬线字体\"AURA\"。其他内容完全保持与输入一致。",
    "image_urls": ["https://.../sku-1.jpg", "https://.../sku-2.jpg", "https://.../sku-3.jpg"],
    "aspect_ratio": "1:1",
    "resolution": "1K"
  }' \
  --output-dir <absolute/path>

Prompting tips

提示技巧

Preservation first:

"Keep [identity / pose / brand / framing] unchanged."

Then state the change.

Spatial scope: "background only", "the left object", "upper-right quadrant" — concrete locations honored.
Batch consistency: lock
```
aspect_ratio
```
and
```
resolution
```
across the batch.
Iterate small: split compound edits into multiple shorter passes.

先提保留需求：

"保持[身份/姿势/品牌/构图]不变。"

再说明修改内容

明确空间范围：“仅背景”“左侧物体”“右上象限”——具体位置指令会被遵循
批量一致性：批量编辑时锁定
```
aspect_ratio
```
和
```
resolution
```
分步修改：将复杂编辑拆分为多个简短步骤

Route 2: GPT Image 2 Edit — multilingual text + multi-ref composition

路径2：GPT Image 2 Edit — 多语言文字+多参考图合成

Model:

openai/gpt-image-2/edit

模型：

openai/gpt-image-2/edit

Schema

参数 schema

Field	Type	Required	Default	Notes
`prompt`	string	yes	—	Edit instruction; lead with preservation.
`images`	string[]	yes	—	Up to 10 HTTPS URLs. First is primary; rest are auxiliary.
`size`	enum	no	`auto`	`auto` , `1024_1024` , `1024_1536` , `1536_1024` . Only these.

字段	类型	是否必填	默认值	说明
`prompt`	字符串	是	—	编辑指令；先说明需要保留的内容
`images`	字符串数组	是	—	最多10个HTTPS链接。第一个是主图；其余为辅助参考图
`size`	枚举值	否	`auto`	`auto` , `1024_1024` , `1024_1536` , `1536_1024` 。仅支持这些选项

Invoke

调用示例

Multilingual text rewrite:

bash

runcomfy run openai/gpt-image-2/edit \
  --input '{
    "prompt": "Keep the photograph, layout, and brand mark exactly as in the input. Replace only the in-image headline. The new headline reads \"今日のおすすめ\" in bold Japanese kana, same position and font weight.",
    "images": ["https://.../poster-en.jpg"]
  }' \
  --output-dir <absolute/path>

Multi-ref composition:

bash

runcomfy run openai/gpt-image-2/edit \
  --input '{
    "prompt": "Compose subject from image 1 into the room from image 2. Match the lighting and color palette of image 2. Keep image 1 subject identity unchanged.",
    "images": ["https://.../subject.jpg", "https://.../room.jpg"]
  }' \
  --output-dir <absolute/path>

多语言文字改写：

bash

runcomfy run openai/gpt-image-2/edit \
  --input '{
    "prompt": "完全保留照片、布局和品牌标识。仅替换图像内的标题。新标题为粗体日文假名\"今日のおすすめ\"，位置和字重与原标题一致。",
    "images": ["https://.../poster-en.jpg"]
  }' \
  --output-dir <absolute/path>

多参考图合成：

bash

runcomfy run openai/gpt-image-2/edit \
  --input '{
    "prompt": "将图1中的主体合成到图2的房间中。匹配图2的光线和调色板。保持图1主体身份不变。",
    "images": ["https://.../subject.jpg", "https://.../room.jpg"]
  }' \
  --output-dir <absolute/path>

Prompting tips

提示技巧

Quote in-image text exactly. Name the script for non-Latin:
```
"Japanese kana"
```
,
```
"Cyrillic"
```
,
```
"Arabic right-to-left"
```
.

Number multi-refs:

"subject from image 1, lighting from image 2"

Directional layout language:

"move the headline from top-right to bottom-center"

"replace the watermark in the bottom-right"

size: "auto"
preserves input ratio — recommended unless the edit changes framing.

准确引用图像内文字：非拉丁语系需注明文字类型：
```
"日文假名"
```
、
```
"西里尔字母"
```
、
```
"阿拉伯语从右到左"
```
给参考图编号：
```
"图1的主体，图2的光线"
```

使用方向性布局语言：

"将标题从右上角移至底部中央"

、

"替换右下角的水印"

推荐使用
size: "auto"
：保留输入图片的比例——除非编辑需要改变构图

Route 3: Flux Kontext Pro — single-shot precise local edit

路径3：Flux Kontext Pro — 单指令精准局部编辑

Model:

blackforestlabs/flux-1-kontext/pro/edit

模型：

blackforestlabs/flux-1-kontext/pro/edit

Schema (minimal)

极简参数 schema

Field	Type	Required	Notes
`prompt`	string	yes	One declarative edit instruction.
`image`	string	yes	Single source image URL.
`aspect_ratio`	enum	no	Pick from supported W:H values.
`seed`	int	no	Reproducibility.

Single image only — no array. For multi-image flows, use Route 1 (Nano Banana Edit).

字段	类型	是否必填	说明
`prompt`	字符串	是	一条陈述式编辑指令
`image`	字符串	是	单个源图片链接
`aspect_ratio`	枚举值	否	从支持的宽高比选项中选择
`seed`	整数	否	用于生成结果可复现

仅支持单张图片——不支持数组。多图片流程请使用路径1（Nano Banana Edit）。

Invoke

调用示例

bash

runcomfy run blackforestlabs/flux-1-kontext/pro/edit \
  --input '{
    "prompt": "Keep the person'\''s face, pose, and clothing unchanged. Add an orange umbrella in her left hand and a slight smile.",
    "image": "https://.../portrait.jpg"
  }' \
  --output-dir <absolute/path>

bash

runcomfy run blackforestlabs/flux-1-kontext/pro/edit \
  --input '{
    "prompt": "保持人物的面部、姿势和服装不变。在她的左手添加一把橙色雨伞，并让她面带微笑。",
    "image": "https://.../portrait.jpg"
  }' \
  --output-dir <absolute/path>

Prompting tips

提示技巧

One declarative instruction. "She is now holding an orange umbrella and smiling" — imperative, single change.
Preservation first. Lead with
```
"Keep [unchanged elements]"
```
then state the change.
Iterate small. Compound edits drift on a single pass; split into sequential passes.

使用单条陈述式指令：“她现在手持一把橙色雨伞并面带微笑”——简洁的祈使句，单一修改需求
先提保留需求：以
```
"保持[不变元素]"
```
开头，再说明修改内容
分步修改：单次复杂编辑容易出现偏差；拆分为多次连续操作

Route 4: Z-Image Turbo Inpaint — mask-driven precise region edit

路径4：Z-Image Turbo Inpaint — 基于蒙版的精准区域编辑

Model:

tongyi-mai/z-image/turbo/inpainting

模型：

tongyi-mai/z-image/turbo/inpainting

Schema

参数 schema

Field	Type	Required	Notes
`prompt`	string	yes	What to fill / replace; preservation constraints for the unmasked surround.
`image`	string	yes	Source image URL.
`mask_image`	string	yes	Grayscale mask URL (white = inpaint, black = preserve).
`strength`	float	no	0.3–0.6 retouching, 0.7–1.0 full replacement.
`control_scale`	float	no	0.6–0.9 typical.
`aspect_ratio`	enum	no	W:H output ratio.
`seed`	int	no	Reproducibility.

字段	类型	是否必填	说明
`prompt`	字符串	是	填充/替换内容；需说明蒙版外区域的保留约束
`image`	字符串	是	源图片链接
`mask_image`	字符串	是	灰度蒙版链接（白色=需要修复的区域，黑色=需要保留的区域）
`strength`	浮点数	否	0.3–0.6用于润色，0.7–1.0用于完全替换
`control_scale`	浮点数	否	通常设置为0.6–0.9
`aspect_ratio`	枚举值	否	输出图片的宽高比
`seed`	整数	否	用于生成结果可复现

Invoke

调用示例

Object removal (low strength):

bash

runcomfy run tongyi-mai/z-image/turbo/inpainting \
  --input '{
    "prompt": "Remove overhead cables; preserve rooflines and sky gradient; thin clean sky.",
    "image": "https://.../street.jpg",
    "mask_image": "https://.../cables-mask.png",
    "strength": 0.5,
    "control_scale": 0.8
  }' \
  --output-dir <absolute/path>

Region replacement (high strength):

bash

runcomfy run tongyi-mai/z-image/turbo/inpainting \
  --input '{
    "prompt": "Replace busy backdrop with smooth light gray studio paper; mask background only.",
    "image": "https://.../product.jpg",
    "mask_image": "https://.../bg-mask.png",
    "strength": 0.9
  }' \
  --output-dir <absolute/path>

物体移除（低强度）：

bash

runcomfy run tongyi-mai/z-image/turbo/inpainting \
  --input '{
    "prompt": "移除架空线缆；保留屋顶轮廓和天空渐变；生成干净的浅色天空。",
    "image": "https://.../street.jpg",
    "mask_image": "https://.../cables-mask.png",
    "strength": 0.5,
    "control_scale": 0.8
  }' \
  --output-dir <absolute/path>

区域替换（高强度）：

bash

runcomfy run tongyi-mai/z-image/turbo/inpainting \
  --input '{
    "prompt": "将杂乱背景替换为光滑的浅灰色摄影棚背景纸；仅蒙版背景区域。",
    "image": "https://.../product.jpg",
    "mask_image": "https://.../bg-mask.png",
    "strength": 0.9
  }' \
  --output-dir <absolute/path>

Prompting tips

提示技巧

A mask URL is required — grayscale, white = inpaint region, black = preserve. Slight blur on mask edges (1–3px) blends better than sharp binary.
Strength by intent:
```
0.3–0.5
```
for retouching / cleanup,
```
0.6–0.7
```
for object replacement with style match,
```
0.8–1.0
```
for full-region replacement.

Name what stays outside the mask in the prompt:

"preserve rooflines and sky gradient"

"match brick pattern and mortar tone"

Spatial labels still help even though the mask defines the region:
```
"the left shelf"
```
,
```
"upper-right quadrant"
```
.

必须提供蒙版链接——灰度图，白色=修复区域，黑色=保留区域。蒙版边缘轻微模糊（1-3像素）比尖锐的黑白边界融合效果更好
根据意图设置强度：
```
0.3–0.5
```
用于润色/清理，
```
0.6–0.7
```
用于风格匹配的物体替换，
```
0.8–1.0
```
用于全区域替换

在提示中明确蒙版外保留内容：

"保留屋顶轮廓和天空渐变"

、

"匹配砖块图案和砂浆色调"

即使有蒙版，空间标签仍有帮助：
```
"左侧架子"
```
、
```
"右上象限"
```

Limitations

局限性

Each route inherits its model's limits. Nano Banana: 1–20 inputs, 1–4 outputs. GPT Image 2 Edit: up to 10 refs, 4 fixed sizes. Flux Kontext: single ref. Z-Image Inpaint: mask required.
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 (
```
gpt-image-edit
```
,
```
flux-kontext
```
,
```
nano-banana-edit
```
) for fuller treatment.

各路径继承对应模型的限制。Nano Banana：1-20张输入，1-4张输出。GPT Image 2 Edit：最多10个参考图，4种固定尺寸。Flux Kontext：仅支持单参考图。Z-Image Inpaint：必须使用蒙版。
不支持多路径混合。该技能每次调用仅选择一个模型。
品牌特定覆盖——如果用户指定了特定模型，请使用对应品牌的技能（
```
gpt-image-edit
```
、
```
flux-kontext
```
、
```
nano-banana-edit
```
）以获得更完整的功能。

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/ schema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 Nano Banana Edit / GPT Image 2 Edit / Flux Kontext Pro / Z-Image Turbo Inpaint 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.

该技能会根据用户意图从Nano Banana Edit / GPT Image 2 Edit / Flux Kontext Pro / Z-Image Turbo Inpaint中选择一个模型，并调用

runcomfy run <model_id>

命令及匹配的JSON参数。CLI会向Model API发送POST请求，轮询请求状态，获取结果，并将所有

.runcomfy.net

.runcomfy.com

链接的内容下载到

--output-dir

指定的目录。按下

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
```
RUNCOMFY_TOKEN
```
环境变量以绕过文件存储。
输入边界：用户提示通过
```
--input
```
以JSON字符串形式传递给CLI。CLI不会对提示内容进行shell扩展；会直接通过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/蒙版/视频链接会由RunComfy模型服务器获取，而非本地CLI。请将外部链接视为不可信；图像提示注入是所有图像编辑/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
```
（生成结果下载白名单）。无遥测，无回调。
生成文件大小限制：CLI会中止任何超过2 GiB的单个文件下载，以防止恶意或异常模型输出占满磁盘。