imggen

Generate images from text prompts using OpenAI image APIs and extract OCR text from images.

Updated Dec 16, 2025

Search Tags:#OpenAI #image generation #CLI #OCR #DALL-E #imggen

Ready to run

npx skills add https://github.com/manashmandal/imggen --skill imggen

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: imggen
Source: https://github.com/manashmandal/imggen/tree/main/.
Command: npx skills add https://github.com/manashmandal/imggen --skill imggen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates two powerful tasks in one place: generating images from text prompts using OpenAI's image APIs (gpt-image-1, dall-e-3, dall-e-2) and extracting text from images via OCR. It saves you time and reduces the complexity of running multiple tools.

Core Features & Use Cases

Image generation: Produce AI-generated art, logos, or illustrations from text prompts.
OCR extraction: Pull text from images with optional structured output.
Use Case: Create a marketing asset by generating an image and extracting any embedded text for branding notes from a single streamlined workflow.

Quick Start

Use the imggen CLI to generate an image from a prompt and then perform OCR on an image:

Basic: imggen "sunset over mountains"
Then: imggen ocr output.png