GPT Image 1.5 图像生成与编辑技能 - 基于OpenAI的AI图像处理工具

gpt-image-1-5 by intellectronica/agent-skills

200 周安装量

228 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/intellectronica/agent-skills --skill gpt-image-1-5

AI/机器学习内容创作图像处理

🇨🇳中文介绍

GPT Image 1.5 - 图像生成与编辑

使用 OpenAI 的 GPT Image 1.5 模型生成新图像或编辑现有图像。

生成 : 使用带有 image_generation 工具的 Responses API
编辑 : 使用 Image API 进行可靠的基于遮罩的修复

使用方法

使用绝对路径运行脚本（请勿先切换到技能目录）：

生成新图像：

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--quality low|medium|high] [--size 1024x1024|1024x1536|1536x1024|auto] [--background transparent|opaque|auto] [--api-key KEY]

编辑现有图像（无遮罩 - 全图编辑）：

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "editing instructions" --filename "output-name.png" --input-image "path/to/input.png" [--size 1024x1024|1024x1536|1536x1024|auto] [--api-key KEY]

编辑现有图像（带遮罩 - 精确修复）：

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "what to put in masked area" --filename "output-name.png" --input-image "path/to/input.png" --mask "path/to/mask.png" [--size 1024x1024|1024x1536|1536x1024|auto] [--api-key KEY]

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

背景选项（仅限生成）

auto (默认) - 模型决定
transparent - 透明背景（PNG/WebP 输出）
opaque - 实心背景

脚本按以下顺序检查 API 密钥：

--api-key 参数（如果用户在聊天中提供了密钥则使用）
OPENAI_API_KEY 环境变量

如果两者都不可用，脚本将退出并显示错误消息。

使用以下模式生成文件名：yyyy-mm-dd-hh-mm-ss-name.png

格式： {timestamp}-{descriptive-name}.png

时间戳：当前日期/时间，格式为 yyyy-mm-dd-hh-mm-ss（24 小时制）
名称：描述性小写文本，用连字符连接
保持描述部分简洁（通常为 1-5 个单词）
使用用户提示或对话的上下文
如果不明确，使用随机标识符（例如 x9k2、a7b3）

提示 "A serene Japanese garden" -> 2025-12-17-14-23-05-japanese-garden.png
提示 "sunset over mountains" -> 2025-12-17-15-30-12-sunset-mountains.png
提示 "create an image of a robot" -> 2025-12-17-16-45-33-robot.png
上下文不明确 -> 2025-12-17-17-12-48-x9k2.png

两种编辑模式都使用 Image API（images.edit 端点）和 gpt-image-1.5 以获得可靠的结果。

无遮罩（全图编辑）

当用户想要修改现有图像但未指定确切区域时：

使用 --input-image 参数指定图像路径
提示应包含编辑指令（例如，"make the sky more dramatic"、"change to cartoon style"）
自动生成完全透明的遮罩，允许模型编辑整个图像

带遮罩（精确修复）

当用户想要编辑特定区域时：

使用 --input-image 参数指定图像路径
使用 --mask 参数指定 PNG 遮罩文件
遮罩应在需要编辑的区域具有透明区域（alpha=0）
提示描述遮罩区域应出现的内容

常见的编辑任务：添加/移除元素、更改样式、调整颜色、替换背景等。

对于生成： 将用户的图像描述原样传递给 --prompt。仅在明显不足时进行修改。

对于编辑： 将编辑指令传递给 --prompt（例如，"add a rainbow in the sky"、"make it look like a watercolor painting"）

在两种情况下都应保留用户的创作意图。

将 PNG 保存到当前目录（如果文件名包含目录，则保存到指定路径）
脚本输出生成图像的完整路径
不要读回图像 - 只需告知用户保存的路径

生成新图像：

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "A serene Japanese garden with cherry blossoms" --filename "2025-12-17-14-23-05-japanese-garden.png" --quality high --size 1536x1024

生成透明背景图像：

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "A cute cartoon cat mascot" --filename "2025-12-17-14-25-30-cat-mascot.png" --background transparent --quality high

编辑现有图像（全图）：

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "make the sky more dramatic with storm clouds" --filename "2025-12-17-14-27-00-dramatic-sky.png" --input-image "original-photo.jpg"

使用遮罩编辑（修复）：

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "a flamingo swimming" --filename "2025-12-17-14-30-00-lounge-flamingo.png" --input-image "lounge.png" --mask "mask.png"

🇺🇸English

GPT Image 1.5 - Image Generation & Editing

Generate new images or edit existing ones using OpenAI's GPT Image 1.5 model.

Generation : Uses the Responses API with image_generation tool
Editing : Uses the Image API for reliable mask-based inpainting

Usage

Run the script using absolute path (do NOT cd to skill directory first):

Generate new image:

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--quality low|medium|high] [--size 1024x1024|1024x1536|1536x1024|auto] [--background transparent|opaque|auto] [--api-key KEY]

Edit existing image (without mask - full image edit):

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "editing instructions" --filename "output-name.png" --input-image "path/to/input.png" [--size 1024x1024|1024x1536|1536x1024|auto] [--api-key KEY]

Edit existing image (with mask - precise inpainting):

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "what to put in masked area" --filename "output-name.png" --input-image "path/to/input.png" --mask "path/to/mask.png" [--size 1024x1024|1024x1536|1536x1024|auto] [--api-key KEY]

Important: Always run from the user's current working directory so images are saved where the user is working, not in the skill directory.

Parameters

Quality Options

low - Fastest generation, lower quality
medium (default) - Balanced quality and speed
high - Best quality, slower generation

Map user requests:

No mention of quality -> medium
"quick", "fast", "draft" -> low
"high quality", "best", "detailed", "high-res" -> high

Size Options

1024x1024 (default) - Square format
1024x1536 - Portrait format
1536x1024 - Landscape format
auto - Let the model decide based on prompt

Map user requests:

No mention of size -> 1024x1024
"square" -> 1024x1024
"portrait", "vertical", "tall" -> 1024x1536
"landscape", "horizontal", "wide" -> 1536x1024

Background Options (generation only)

auto (default) - Model decides
transparent - Transparent background (PNG/WebP output)
opaque - Solid background

API Key

The script checks for API key in this order:

--api-key argument (use if user provided key in chat)
OPENAI_API_KEY environment variable

If neither is available, the script exits with an error message.

Filename Generation

Generate filenames with the pattern: yyyy-mm-dd-hh-mm-ss-name.png

Format: {timestamp}-{descriptive-name}.png

Timestamp: Current date/time in format yyyy-mm-dd-hh-mm-ss (24-hour format)
Name: Descriptive lowercase text with hyphens
Keep the descriptive part concise (1-5 words typically)
Use context from user's prompt or conversation
If unclear, use random identifier (e.g., x9k2, a7b3)

Examples:

Prompt "A serene Japanese garden" -> 2025-12-17-14-23-05-japanese-garden.png
Prompt "sunset over mountains" -> 2025-12-17-15-30-12-sunset-mountains.png
Prompt "create an image of a robot" -> 2025-12-17-16-45-33-robot.png
Unclear context -> 2025-12-17-17-12-48-x9k2.png

Image Editing

Both editing modes use the Image API (images.edit endpoint) with gpt-image-1.5 for reliable results.

Without Mask (Full Image Edit)

When the user wants to modify an existing image without specifying exact regions:

Use --input-image parameter with the path to the image
The prompt should contain editing instructions (e.g., "make the sky more dramatic", "change to cartoon style")
A fully transparent mask is auto-generated, allowing the model to edit the entire image

With Mask (Precise Inpainting)

When the user wants to edit specific regions:

Use --input-image parameter with the path to the image
Use --mask parameter with a PNG mask file
The mask should have transparent areas (alpha=0) where edits should occur
The prompt describes what should appear in the masked region

Common editing tasks: add/remove elements, change style, adjust colors, replace backgrounds, etc.

Prompt Handling

For generation: Pass user's image description as-is to --prompt. Only rework if clearly insufficient.

For editing: Pass editing instructions in --prompt (e.g., "add a rainbow in the sky", "make it look like a watercolor painting")

Preserve user's creative intent in both cases.

Output

Saves PNG to current directory (or specified path if filename includes directory)
Script outputs the full path to the generated image
Do not read the image back - just inform the user of the saved path

Examples

Generate new image:

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "A serene Japanese garden with cherry blossoms" --filename "2025-12-17-14-23-05-japanese-garden.png" --quality high --size 1536x1024

Generate with transparent background:

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "A cute cartoon cat mascot" --filename "2025-12-17-14-25-30-cat-mascot.png" --background transparent --quality high

Edit existing image (full image):

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "make the sky more dramatic with storm clouds" --filename "2025-12-17-14-27-00-dramatic-sky.png" --input-image "original-photo.jpg"

Edit with mask (inpainting):

uv run ~/.claude/skills/gpt-image-1-5/scripts/generate_image.py --prompt "a flamingo swimming" --filename "2025-12-17-14-30-00-lounge-flamingo.png" --input-image "lounge.png" --mask "mask.png"

Weekly Installs

200

Repository

intellectronica…t-skills

GitHub Stars

228

First Seen

Jan 20, 2026

Security Audits

Gen Agent Trust HubFail SocketPass SnykFail

Installed on

opencode165

gemini-cli162

codex162

claude-code157

cursor148

github-copilot137

超能力技能使用指南：AI助手技能调用优先级与工作流程详解

45,100 周安装