GitHub radar
Gathered Scenes Zine: Photo to Art with GPT Image 2
Two Codex skills that turn an ordinary photo into a handcrafted zine-style poster — either a real-photo collage or a fully new illustration distilled from the scene's mood and tension.
The Gathered Scenes Zine is a pair of Codex skills for creating art from images using GPT Image 2. It consists of two separate skills, Gathered Scenes ($scenes-gathered-zine-v1-3) and Scene Distillation ($scene-distillation-zine-v1-3). Gathered Scenes takes an input image and outputs a collage containing elements of the input image alongside some abstracted features extracted from the input image, one highly saturated color, and rough paper edges. Scene Distillation takes an input image and outputs a distilled version of the scene, capturing its essence, emotions, and metaphors, while also generating a new illustration in an editorial style. To install the skills, copy them to ~/.codex/skills/. You can run the skills inline by typing $scenes-gathered-zine-v1-3 [description]. See this archive of before and after examples to get a sense of what elements are retained from each scene. This was released about six weeks ago and already has over 4,000 stars! You’ll need OpenAI Codex and access to GPT Image 2.
Why a vibe-coder should care
These skills allow you to automate the process of converting photos into poster-worthy art pieces using OpenAI Codex, by letting Codex make the visual choices for you (i.e., which parts of the image to retain, what to abstract away, etc.).
How to install
Copy this and send it to your agent — Claude Code, Codex, any of them:
Install the zine poster skill from https://github.com/Zeejay0/gathered-scenes-zine-skill — clone the repo, copy skills/scenes-gathered-zine-v1-3 to ~/.codex/skills/, restart Codex, and show me how to use $scenes-gathered-zine-v1-3 on a test photo.
▌ More finds