awesome-gpt-image-2-API-and-Prompts

This repository is a curated collection of prompts and API usage examples for GPT-Image-2, which is OpenAI's image generation and editing model available through the OpenAI API and integrated into ChatGPT. The repository is not a piece of software to install; it is a reference document with examples and guides for people who want to generate images using that model.

The core content is a gallery of over 500 prompt examples organized into seven categories: portrait and photography, poster and illustration, UI and social media mockups, e-commerce product shots, ad creative, character design, and comparison cases. Each entry in the gallery shows the prompt text used alongside the actual image the model produced, giving readers a concrete before/after view of what different prompt styles achieve.

The README explains what GPT-Image-2 can do: generate images from text descriptions, edit existing images with text instructions, render text accurately within images, and maintain a consistent character appearance across multiple generations. It also covers how to call the model through the OpenAI API, including which endpoint to use and how to request different image sizes or batch outputs.

The repository is updated regularly, with new prompt cases added in daily batches curated by the maintainers. As of the portion of the README available, it had grown from an initial release in April 2026 to over 500 cases in roughly a month. Documentation is available in 11 languages, including Spanish, Japanese, Korean, German, and Chinese.

Companion repositories linked from this one provide a callable skill for automating image generation and a workflow that pairs GPT-Image-2 with a video generation model. The full README is longer than what was shown.