gpt-image-2

Generate typography-focused images and edit them with AI using voice commands.

62|14|Updated Apr 22, 2026
One-click install
npx skills add https://github.com/robonuggets/gpt-image-2-skill --skill gpt-image-2-robonuggets
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gpt-image-2
Source: https://github.com/robonuggets/gpt-image-2-skill/tree/main
Command: npx skills add https://github.com/robonuggets/gpt-image-2-skill --skill gpt-image-2-robonuggets

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Most image generation models fail to produce legible, accurate text inside generated images, making it extremely difficult to create assets like signs, posters, menus, and UI mockups that rely on clear typography. This Skill solves that gap by wiring OpenAI's GPT Image 2 (via Fal AI) directly into your workflow, delivering industry-leading text fidelity for all typography-focused image tasks.

Core Features & Use Cases

  • Text-to-image generation: Create typography-heavy assets including chalkboards, store signs, hand-lettered posters, menu boards, packaging mockups, magazine covers, UI screenshots, and social cards with perfectly legible text.
  • Image editing: Modify existing reference images with optional region masks for surgical edits, such as swapping text, changing backgrounds, or adjusting specific elements while preserving the rest of the scene.
  • Community prompt library access: Integrated pointer to a 700+ curated prompt library (CC BY 4.0) for style and use case inspiration, covering categories from vintage typography to modern UI mockups.
  • Sync API with no polling: Single POST request returns image URLs immediately, with support for up to 4 output variants per call and custom dimensions up to 3840×2160.

Quick Start

Use this skill to generate a vintage diner chalkboard sign that reads "TODAY SPECIAL — Lobster Roll $24" with clear, hand-lettered typography.

Frequently Asked Questions about gpt-image-2

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images with legible typography and text inside them?

To generate images with legible typography, this Skill uses OpenAI's GPT Image 2 model via the Fal AI API to create high-fidelity text directly on assets like posters, menus, and packaging mockups. You provide a text prompt and it returns URLs for the generated images.

What are the output limitations for GPT Image 2 image generation via Fal AI?

The image generation process supports up to 4 output variants per single POST request and allows custom dimensions up to 3840×2160. It returns image URLs synchronously without requiring polling.

How do I find style inspiration for typography-focused image generation?

For style inspiration, the Skill integrates with a curated community prompt library containing over 700 prompts. This covers various categories from vintage typography to modern UI mockups to help guide your text-to-image generation.

Can I generate UI mockups and packaging designs with accurate text using image generation?

Yes, you can generate UI screenshots and packaging mockups with perfectly legible text. The Skill is specifically designed to solve the problem of inaccurate text rendering in typography-heavy image generation tasks.