gpt-image
结构化流程帮助生成高质量图像并处理参考图与修补场景。
可能生成版权争议或不当内容，使用时需内容审查与合规把关。
基于 GPT Image 2 的图像生成与编辑运行手册与提示库。
能把你的文字描述或参考图自动变成图片，支持从头生成、局部修图（inpainting）到多参考图混合。适合做海报、UI mockup、含中文排版或插画原型的时候，用内置的 reference gallery 和封装的 CLI 快速产图。特别之处是会优先匹配已有示例风格和提示库，省去你反复调参的痛苦。
▸ 展开 SKILL.md 英文原文
Use this skill whenever a user asks to generate, create, draw, render, or edit images with GPT Image 2 / gpt-image-2, text-to-image, reference-image editing, inpainting, posters, typography, Chinese text, UI mockups, diagrams, or gallery prompts. Analyze the user's prompt, search the bundled Reference Gallery/craft files for matching design patterns, confer on direction when useful, then call the packaged `gpt-image` CLI or bundled `scripts/generate.py`. Do not write new image-generation code unless explicitly asked to modify this repo.
帮我安装这个 skill：https://raw.githubusercontent.com/wuyoscar/GPT-Image2-Skill/main/skills/gpt-image/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/wuyoscar/GPT-Image2-Skill/main/skills/gpt-image/SKILL.md"# gpt-image Agent runbook for GPT Image 2 generation/editing. Use the prompt library + packaged CLI. Do not reimplement image API code. ## Operating loop 1. **Classify request**: `generate`, `edit`, `inpaint`, or `multi-reference`; identify asset type, exact text, aspect ratio, references, safety constraints, and budget/quality. 2. **Search references first**: open `references/gallery.md`; load/search the closest `references/gallery-<category>.md` file(s). Read actual `**Prompt**` text before choosing a pattern. 3. **Refine with craft**: load `references/craft.md` for dense text, diagrams, UI, data visualization, multi-panel layouts, weak prompts, or no close gallery match. 4. **Confer wh