Skip to main content

img-cli

命令行图片生成与编辑工具,基于 Python + uv 开发,封装 OpenAI 兼容的 Images API(文生图 generate 与图生图编辑 edit)。

img-cli Poster


特性

  • 🚀 简单易用:一行命令完成图片生成和图片编辑。
  • 🔑 灵活认证:支持 ~/.img_gen/auth.json 配置文件及环境变量。
  • 📝 审计日志:自动在 ~/.img_gen/img.log 记录每次请求详情(JSON Lines 格式)。
  • 🖼️ 格式与尺寸自适应:支持 PNG / JPEG / WEBP,自动进行 RGBA 蒙版和格式转换。
  • 🌐 网络与本地图片支持:编辑模式下原图和蒙版均支持本地路径(含 ~)及 HTTP/HTTPS URL。
  • 🤖 Agent 友好:清晰的标准输出与结构化错误码,便于自动化工作流接入。

安装与环境准备

通过 PyPI 安装

# 使用 uv 工具安装(推荐)
uv tool install img-cli

# 或通过 pip 安装
pip install img-cli

本地开发与运行

# 1. 运行测试 / 调试
uv run img-cli --help

# 2. 从源码安装 CLI
uv tool install .

认证配置

首次使用前,请创建配置文件 ~/.img_gen/auth.json

mkdir -p ~/.img_gen
echo '{"api_key":"sk-xxx","api_base":"https://api.openai.com/v1"}' > ~/.img_gen/auth.json

也可通过环境变量传入:

  • OPENAI_API_KEY(或 IMG_GEN_API_KEY
  • OPENAI_BASE_URL(或 OPENAI_API_BASE / IMG_GEN_API_BASE

快速使用

1. 文生图 (generate)

# 基础生成(默认模型 gpt-image-2,保存至当前目录)
img-cli generate "一只戴墨镜的猫坐在沙滩上"

# 指定模型、尺寸与输出目录
img-cli generate "a futuristic city at sunset" -m dall-e-3 -s 1792x1024 -q hd -o ~/Desktop

# 指定输出格式为 JPEG
img-cli generate "产品白底宣传图,极简风格" -m gpt-image-1 -q high --format jpeg -o ./output

2. 图片编辑 (edit)

# 本地图片全图编辑
img-cli edit "给猫戴上一顶红色圣诞帽" --image ./cat.png -o ./output

# 网络图片直接编辑
img-cli edit "替换背景为星空" --image https://example.com/photo.jpg -o ./output

# 带蒙版的局部编辑(蒙版透明区域为待修改区域)
img-cli edit "用一朵玫瑰替换这里" --image ./photo.png --mask ./mask.png -o ./output

命令参数参考

img-cli generate <prompt>

参数 默认值 说明
prompt 必填 提示词(支持中文与英文)
-m, --model gpt-image-2 模型名称(如 gpt-image-2, dall-e-3, gpt-image-1
-s, --size 1024x1024 尺寸(如 1024x1024, 1536x1024, 1024x1536, auto
-q, --quality 质量(low / medium / high / auto / standard / hd
-n, --n 1 生成张数
-o, --output . 图片输出目录
--format png 输出格式:png / jpeg / webp

img-cli edit <prompt>

参数 默认值 说明
prompt 必填 修改描述
-i, --image 必填 原图:本地路径或 HTTP/HTTPS URL
--mask 蒙版:本地路径或 URL(PNG 透明区域待修改)
-m, --model gpt-image-2 模型名称
-s, --size auto 尺寸
-q, --quality auto 质量
-n, --n 1 生成张数
-o, --output . 图片输出目录
--format png 输出格式:png / jpeg / webp

运行测试

uv run pytest -v

Release files for img-cli 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for img-cli 0.1.0
File Size Uploaded
img_cli-0.1.0.tar.gz 2.2 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for img-cli 0.1.0
File Interpreter ABI Platform
img_cli-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 2.2 MB

Release files / img_cli-0.1.0.tar.gz

Download URL img_cli-0.1.0.tar.gz
Size 2.2 MB
Tags Source
SHA-256 checksum
How to use checksums
a6fe72bb804d8f9257e005c4cc6b76cec20867401e2716d12b568c674a7daaac
BLAKE2b-256 checksum
How to use checksums
662035d91d67e7001f3e92770ca10dbaa0576f54a1dab1bb4063a68e5f922b6e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release files / img_cli-0.1.0-py3-none-any.whl

Download URL img_cli-0.1.0-py3-none-any.whl
Size 12.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
973a97dd68a1121e677dea7d6702d33469776feb034cda28070e037d5645448c
BLAKE2b-256 checksum
How to use checksums
e024d78602b987fe6a1090866d70bdb0870de23e7d7112a0ecf74810ad2e72a9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 29, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page