sofunny-image

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

sofunny-image

何时使用

When to Use

在以下场景使用本 skill：

用户要生成图片，而当前客户端主模型并不适合直接承担图片输出
用户要上传一张或多张参考图，再结合文本生成新图片
用户要通过
```
New-API
```
的 Gemini 原生接口出图，而不是直连 Google 官方 API
用户希望优先复用：
- 进程环境变量
- ```
~/.sofunny-image.env
```

如果只是普通文本问答、代码生成或工具调用，不要使用本 skill。

Use this skill in the following scenarios:

The user wants to generate images, but the current client's main model is not suitable for direct image output
The user wants to upload one or more reference images and generate new images combined with text
The user wants to generate images via New-API's native Gemini interface instead of directly connecting to Google's official API
The user prefers to reuse:
- Process environment variables
- ```
~/.sofunny-image.env
```

Do not use this skill for ordinary text Q&A, code generation, or tool calls.

配置来源

Configuration Sources

脚本按以下顺序读取配置：

```
~/.sofunny-image.env
```
当前 shell 的环境变量

命令行参数

--base-url

、

--api-key

、

--model

会覆盖以上配置。

如果没有检测到

~/.sofunny-image.env

，脚本会提示你创建该文件并写入所需变量模板。

优先使用这些变量：

```
SOFUNNY_BASE_URL
```
```
SOFUNNY_API_KEY
```
```
SOFUNNY_MODEL
```

默认期望值：

```
SOFUNNY_BASE_URL=http://127.0.0.1:3000
```

SOFUNNY_MODEL=gemini-3.1-flash-image-preview

The script reads configurations in the following order:

```
~/.sofunny-image.env
```
Current shell environment variables

Command-line parameters

--base-url

--api-key

--model

will override the above configurations.

~/.sofunny-image.env

is not detected, the script will prompt you to create the file and write the required variable template.

Prioritize using these variables:

```
SOFUNNY_BASE_URL
```
```
SOFUNNY_API_KEY
```
```
SOFUNNY_MODEL
```

Default expected values:

```
SOFUNNY_BASE_URL=http://127.0.0.1:3000
```

SOFUNNY_MODEL=gemini-3.1-flash-image-preview

安装与执行入口

Installation and Execution Entry

推荐将仓库目录软链接到：

${CLAUDE_PLUGIN_ROOT}/skills/sofunny-image

可执行脚本入口：

${CLAUDE_PLUGIN_ROOT}/skills/sofunny-image/scripts/sofunny-image.js

It is recommended to create a soft link of the repository directory to:
- ```
${CLAUDE_PLUGIN_ROOT}/skills/sofunny-image
```

Executable script entry:

${CLAUDE_PLUGIN_ROOT}/skills/sofunny-image/scripts/sofunny-image.js

快速用法

Quick Usage

文本生图：

bash

node ${CLAUDE_PLUGIN_ROOT}/skills/sofunny-image/scripts/sofunny-image.js \
  --prompt "生成一张 16:9 的极简香蕉海报，不要任何文字。"

参考图编辑：

bash

node ${CLAUDE_PLUGIN_ROOT}/skills/sofunny-image/scripts/sofunny-image.js \
  --prompt "保持主体不变，把背景改成晨雾中的山谷。" \
  --input /absolute/path/to/ref-1.png \
  --input /absolute/path/to/ref-2.jpg

指定输出、比例和分辨率：

bash

node ${CLAUDE_PLUGIN_ROOT}/skills/sofunny-image/scripts/sofunny-image.js \
  --prompt "生成一张赛博朋克风格香蕉图标。" \
  --aspect-ratio 1:1 \
  --image-size 2K \
  --output /tmp/banana-icon.png

Text-to-image generation:

bash

node ${CLAUDE_PLUGIN_ROOT}/skills/sofunny-image/scripts/sofunny-image.js \
  --prompt "Generate a minimalist 16:9 banana poster without any text."

Reference image editing:

bash

node ${CLAUDE_PLUGIN_ROOT}/skills/sofunny-image/scripts/sofunny-image.js \
  --prompt "Keep the subject unchanged and change the background to a valley in morning fog." \
  --input /absolute/path/to/ref-1.png \
  --input /absolute/path/to/ref-2.jpg

Specify output, aspect ratio, and resolution:

bash

node ${CLAUDE_PLUGIN_ROOT}/skills/sofunny-image/scripts/sofunny-image.js \
  --prompt "Generate a cyberpunk-style banana icon." \
  --aspect-ratio 1:1 \
  --image-size 2K \
  --output /tmp/banana-icon.png

参数说明

Parameter Description

```
--prompt
```
：必填，图片生成或编辑指令
```
--input
```
：可重复传入，一张或多张参考图
```
--output
```
：可选，输出文件路径
```
--aspect-ratio
```
：可选，默认
```
16:9
```
```
--image-size
```
：可选，默认
```
1K
```
```
--model
```
：可选，默认读取配置，兜底为
```
gemini-3.1-flash-image-preview
```
```
--base-url
```
：可选，覆盖配置中的 base URL
```
--api-key
```
：可选，覆盖配置中的 token

```
--prompt
```
: Required, instruction for image generation or editing
```
--input
```
: Can be passed repeatedly, one or more reference images
```
--output
```
: Optional, output file path
```
--aspect-ratio
```
: Optional, default is
```
16:9
```
```
--image-size
```
: Optional, default is
```
1K
```
```
--model
```
: Optional, defaults to reading configuration, fallback to
```
gemini-3.1-flash-image-preview
```
```
--base-url
```
: Optional, overrides the base URL in configuration
```
--api-key
```
: Optional, overrides the token in configuration

工作流

Workflow

收集用户的 prompt、参考图、输出路径和画幅要求。
运行
```
scripts/sofunny-image.js
```
。

脚本会直接调用：

{BASE_URL}/v1beta/models/{MODEL}:generateContent

脚本从响应中提取最后一个
```
inlineData.data
```
，并将其视为最终图片保存到本地。
把保存路径返回给用户。

Collect the user's prompt, reference images, output path, and aspect ratio requirements.
Run
```
scripts/sofunny-image.js
```
.

The script will directly call:

{BASE_URL}/v1beta/models/{MODEL}:generateContent

The script extracts the last
```
inlineData.data
```
from the response and saves it as the final image locally.
Return the save path to the user.

注意事项

Notes

本 skill 默认不附带
```
tools
```
和
```
thinking
```
，避免图片模型在工具模式下失败。
```
BASE_URL
```
应为服务根地址，不要手动带
```
/v1
```
。
若未指定输出路径，脚本默认保存到：
- 当前工作目录
```
~/.sofunny-image.env
```
中只应使用
```
SOFUNNY_*
```
变量，避免旧配置混入导致行为不一致。
如果 Gemini 在同一次响应中返回多张图片，脚本默认只保存最后一张，前面的图片视为中间产物。

This skill does not include
```
tools
```
and
```
thinking
```
by default to avoid failures of the image model in tool mode.
```
BASE_URL
```
should be the root address of the service, do not manually add
```
/v1
```
.
If no output path is specified, the script will save the image by default to:
- Current working directory
Only use
```
SOFUNNY_*
```
variables in
```
~/.sofunny-image.env
```
to avoid inconsistent behavior caused by mixing old configurations.
If Gemini returns multiple images in the same response, the script will only save the last one by default, and previous images are considered intermediate products.