Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
GPT Image 2/2.5 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
| Date | Stars |
|---|---|
| 2026-07-24 | 3934 |
| 2026-07-25 | 3951 |
| 2026-07-28 | 3951 |
| 2026-07-30 | 3951 |
| 2026-07-31 | 4052 |
| 2026-08-07 | 4205 |
| 2026-08-16 | 4606 |
| 2026-08-18 | 4711 |
| 2026-08-19 | 4734 |
| 2026-08-20 | 4773 |
| 2026-08-21 | 4797 |
| 2026-08-22 | 4812 |
| 2026-08-23 | 4830 |
| 2026-08-24 | 4848 |
| 2026-08-25 | 4870 |
| 2026-08-26 | 4913 |
| 2026-08-27 | 4939 |
| 2026-08-28 | 4969 |
| 2026-08-29 | 4982 |
| 2026-08-30 | 4996 |
| 2026-08-31 | 5013 |
| 2026-09-01 | 5025 |
| 2026-09-02 | 5047 |
| 2026-09-03 | 5101 |
| 2026-09-04 | 5139 |
| 2026-09-05 | 5156 |
| 2026-09-06 | 5179 |
| 2026-09-07 | 5200 |
| 2026-09-08 | 5219 |
| 2026-09-09 | 5234 |
| 2026-09-10 | 5281 |
| 2026-09-11 | 5312 |
| 2026-09-12 | 5334 |
| 2026-09-13 | 5339 |
| 2026-09-14 | 5368 |
| 2026-09-15 | 5393 |
| 2026-09-16 | 5404 |
| 2026-09-17 | 5433 |
| 2026-09-18 | 5446 |
| 2026-09-19 | 5459 |
| 2026-09-20 | 5475 |
Today
+16 stars today
This week
+136 stars this week
This month
+678 stars this month
Momentum
205.0
growth rate 2.55%/day
<h1 align="center">GPT Image 2/2.5 Prompt Gallery + Agent Skills + CLI</h1>
<p align="center"><em>Prompts, reference images, two agent skills and a CLI for GPT Image 2 and 2.5.</em></p>
<p align="center">
<a href="README.md"><strong>English</strong></a> · <a href="README.zh.md">中文</a>
</p>
<p align="center">
<a href="https://github.com/wuyoscar/gpt_image_2_skill/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-green.svg" alt="License: MIT"/></a>
<a href="https://github.com/wuyoscar/gpt_image_2_skill/pulls"><img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg" alt="PRs Welcome"/></a>
<img src="https://img.shields.io/badge/models-GPT%20Image%202%20%2F%202.5-purple.svg" alt="Models: GPT Image 2 / 2.5"/>
<img src="https://img.shields.io/badge/python-%E2%89%A53.11-blue.svg" alt="Python ≥ 3.11"/>
</p>
<p align="center">
<a href="docs/assets/gptimage2skill-banner.png"><img src="docs/assets/gptimage2skill-banner.png" alt="GPTImage2Skill banner" width="100%"/></a>
</p>
<p align="center">
<a href="#overview">Overview</a> · <a href="#sunburst-samples">2.5 samples</a> · <a href="#image-example">Example</a> · <a href="#quickstart">Quick start</a> · <a href="#install">Install</a> · <a href="#cli-reference">CLI reference</a> · <a href="#guides">Guides</a> · <a href="#gallery-index">Gallery</a> · <a href="#community">Contribute</a>
</p>
<a id="overview"></a>
## 🧭 What about this report
<table border="1" cellspacing="0" cellpadding="6">
<tr>
<th align="left">Item</th>
<th align="left">Value</th>
</tr>
<tr>
<td>Gallery size</td>
<td><strong>163 numbered entries</strong> across 31 categories, with selected images below</td>
</tr>
<tr>
<td>Surfaces</td>
<td><strong>2 Agent Skills + CLI</strong>: Claude Code / Codex, OpenClaw, Hermes Agent and other skill-capable agent runtimes</td>
</tr>
<tr>
<td>Last update</td>
<td><strong>2026-09-10</strong></td>
</tr>
<tr>
<td>Docs</td>
<td><strong>English + 中文</strong></td>
</tr>
</table>
The repo keeps the GPT Image 2 prompt collection and gallery alongside 2.5 API support, [reading material](#image-25-reading) and task-specific references. The two skills handle image generation/editing and image-to-prompt extraction.
> TBH, GPT Image 2.5 feels seriously capable. I prefer giving it a clear reference: a shape, a sketch or an image. Sometimes showing a layout from a PDF is more useful than describing it at length. It's how I like to work with GPT-6, too: **minimize the prompt; make the reference clear.**
>
> I collect prompts, useful building blocks and references here to help you find a workflow that suits the job. Thanks for all the love this little gallery has received 🫶.
For the CLI, export the relevant PDF pages as PNG, WebP or JPG, then attach them with `-i`. See the [supported image-reference formats](https://developers.openai.com/api/reference/python/resources/images/methods/edit). Keep required text and edit constraints explicit.
For PPT work, try vector-style diagrams, icons and slide layouts. The [Image API outputs PNG, JPEG or WebP](https://developers.openai.com/api/docs/guides/image-generation#output-format); editable SVG or PowerPoint shapes need a separate authoring step.
<a id="sunburst-samples"></a>
## ✨ Made with GPT Image 2.5
Two 2K samples: an exploded watch assembly with detailed callouts, and a multi-storey cafe cutaway built from a reference image. Both use `gpt-image-2.5-sunburst`, `2048x2048` and `high`.
<table>
<tr>
<td width="50%" align="center" valign="top">
<a href="docs/technical-illustration/meridian8-sunburst.png"><img src="docs/technical-illustration/meridian8-sunburst.png" width="100%" alt="Sunburst exploded mechanical watch with numbered component callouts"/></a>
<sub>A · Meridian 8 exploded assembly<br/>2048x2048 · high · Curated</sub>
</td>
<td width="50%" align="center" valign="top">
<a href="docs/isometric/cafe-cutExcerpt of 225,014 characters
Read on GitHub
Oscar Wu · Australia
60
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6c5855132e8010e1, topic:image-generation, topic:text-to-image, desc:image generation