What it is
This skill lets your AI assistant generate and edit images with OpenAI's GPT Image 2 and 2.5 models, backed by a large gallery of proven prompts. It handles posters, typography-heavy graphics, product shots, diagrams, edits based on reference images, and touch-ups to specific areas of a picture. It helps you pick the right model and quality level for your budget and saves the finished images for you.
What it does
- Generates images from a text description in square, portrait, landscape, or wide formats
- Edits existing images using one or more reference pictures
- Repaints a selected area of an image while leaving the rest untouched
- Draws on a curated gallery of prompts for posters, typography, and visual styles
- Helps you choose the model and quality setting to balance cost and polish
Use it when
- You need a poster, social graphic, or product image with accurate text on it
- You want to edit or restyle an existing photo or design using a reference
- You're exploring visual directions for a campaign or presentation
Add this skill to your AI
Copy the source URL and ask your AI to add it. Most coding agents — Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Windsurf — will fetch and install it for you.
Try this prompt:
Add this skill to my project: https://github.com/wuyoscar/GPT-Image2-Skill/tree/main/skills/gpt-image