跳到正文
cccskills
免费在 GitHub 公开

imgen

Azure OpenAI画像生成CLIツール (gpt-image-1.5 / gpt-5.1)。テキストから画像生成、画像のAI編集、画像の内容説明を行う。

Use when the user wants to (1) generate images using Azure OpenAI, (2) edit existing images with AI, (3) explain image contents. Triggers on "画像を生成", "画像を編集", "画像の説明", "generate an image", "edit this image", "describe this image", "imgenで".

中文简介正在准备中。当前显示原文说明。

集成工具AzureOpenAI
查看安装方法

包含的文件(1)

  • SKILL.md5.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

imgen - Azure OpenAI Image Generation CLI

How to Run

imgen is NOT globally installed. Use one of these methods:

# 開発モード(ソースから直接実行、.envを自動読み込み)
npm run dev --prefix /Volumes/Data/dev/imgen -- <command>

# npx でソースから実行(.envは自動読み込みされない)
npx tsx /Volumes/Data/dev/imgen/src/index.ts <command>

# npm パッケージとして実行(npm install -g @nogataka/imgen 済みの場合)
imgen <command>

以下の例では imgen と表記するが、実際は上記いずれかの方法で実行すること。

Quick Reference

imgen image gen "<prompt>" -q <quality> -s <size>    # 画像生成
imgen image edit <file> "<instruction>"               # 画像編集
imgen image explain <file> -l <lang>                  # 画像説明

Setup

環境変数または .env ファイルで Azure OpenAI の認証情報を設定する。

# 環境変数(最優先)
export AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com"
export AZURE_OPENAI_API_KEY="your-api-key"
export AZURE_OPENAI_DEPLOYMENT_NAME="gpt-5.1"
export AZURE_OPENAI_DEPLOYMENT_NAME_IMAGE="gpt-image-1.5"

.env ファイル探索順: cwd/.env → ~/.imgen/.env

VariableDescriptionDefault
AZURE_OPENAI_ENDPOINTAzure OpenAI resource endpoint(required)
AZURE_OPENAI_API_KEYAzure OpenAI API key(required)
AZURE_OPENAI_DEPLOYMENT_NAMEChat model deployment(required)
AZURE_OPENAI_DEPLOYMENT_NAME_IMAGEImage model deployment(required)
AZURE_OPENAI_API_VERSIONChat API version2024-02-15-preview
AZURE_OPENAI_IMAGE_API_VERSIONImage API version2025-04-01-preview

Image Generation

imgen image gen [options] <theme>
OptionValuesDefault
-s, --size1024x1024, 1536x1024, 1024x15361024x1024
-q, --qualitylow, medium, highhigh
-f, --formatpng, jpg, webppng
-p, --presetbuiltin preset name-
-c, --contextcontext file path (.md/.txt)-
-o, --outputoutput path (file or directory)auto
-d, --debugenable debug loggingfalse
--jsonJSON output formatfalse
--dry-runpreview settings without API callfalse

Recommended Settings

Use CaseQualitySize
Product photo, landscapehigh1536x1024
Illustration, icon, mascothigh1024x1024
Quick draft, prototypelow1024x1024
Portrait, verticalhigh1024x1536

Examples

imgen image gen "夕日の海辺の風景" -q high -s 1536x1024
imgen image gen "可愛い猫のマスコット" -p builtin:square
imgen image gen "ミニマルなロゴデザイン" -o logo.png
imgen image gen "complex scene" --dry-run

Image Editing

imgen image edit [options] <file> <prompt>

Edit instructions in natural language:

  • Background change: "背景を青空に変更"
  • Style transfer: "水彩画風に変換"
  • Object modification: "色を鮮やかに"

Supported input formats: .jpg, .jpeg, .png, .gif, .webp

OptionValuesDefault
-s, --size1024x1024, 1536x1024, 1024x15361024x1024
-f, --formatpng, jpg, webppng
-o, --outputoutput pathauto
--jsonJSON output formatfalse
--dry-runpreview settings without API callfalse

Examples

imgen image edit photo.jpg "背景を青空に変更"
imgen image edit portrait.png "アニメスタイルに変換" -s 1536x1024
imgen image edit photo.png "edit" --dry-run

Image Explanation

imgen image explain [options] <file>
OptionValuesDefault
-l, --langja, en, zh, ko, es, fr, de, it, ru, vija
-f, --formatmarkdown, jsonmarkdown
-c, --contextcontext info (text or .md/.txt file path)-
-o, --outputoutput file pathstdout

Examples

imgen image explain screenshot.png
imgen image explain photo.jpg -l en
imgen image explain chart.png -c "Q4 sales report" -f json

Builtin Presets

-p オプションで指定可能:

NameSizeQuality
builtin:square1024x1024high
builtin:landscape1536x1024high
builtin:portrait1024x1536high
builtin:draft1024x1024low
builtin:photo1536x1024high

Option Priority

CLI options > Preset values (-p) > Default values

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

pptx

免费

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

中文简介正在准备中。当前显示原文说明。

nogataka/SlideKit302026年3月19日 更新

Generate HTML slide presentations (1 slide = 1 HTML file, 1280x720px) using Tailwind CSS, Font Awesome, and Google Fonts. Use when the user asks to create a new presentation deck or slide HTML files. Covers design guidelines, 43 layout patterns, component library, and PPTX conversion compatibility rules. Supports style selection (creative, elegant, modern, professional, minimalist) and theme selection (marketing, portfolio, business, technology, education).

中文简介正在准备中。当前显示原文说明。

nogataka/SlideKit302026年3月19日 更新

Convert PDF presentations to HTML slide templates using a visual reproduction approach. Pipeline: PDF → slide screenshots → Claude writes HTML matching each screenshot. Use when the user wants to convert a PDF to HTML slide templates, reproduce a presentation as HTML, or create reusable templates from existing decks. Triggers: 'pdf to html', 'convert pdf to template', 'reproduce this deck as html', 'create template from pdf'.

中文简介正在准备中。当前显示原文说明。

nogataka/SlideKit302026年3月19日 更新

查看 nogataka 的全部技能

报告此技能的问题