image-gen

Generate images, infographics, and diagrams from natural-language prompts via Gemini 3 Pro Image.

5|Updated Nov 18, 2025
One-click install
npx skills add https://github.com/krishagel/geoffrey --skill image-gen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image-gen
Source: https://github.com/krishagel/geoffrey/tree/main/skills/image-gen
Command: npx skills add https://github.com/krishagel/geoffrey --skill image-gen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, pillow, python-dotenv, and includes scripts (resource) components.

What problem does it solve?

Generate professional images, infographics, and diagrams quickly using Gemini 3 Pro Image with workflow-driven prompts.

Core Features & Use Cases

  • Text-to-image generation, editing, and multi-image composition
  • Workflow-based prompts ensuring visuals align with narrative
  • Supports up to 14 reference images for style transfer and composition
  • Output in multiple resolutions and aspect ratios (1:1, 16:9, etc.)

Quick Start

uv run generate.py "A sleek dashboard" dashboard.png 16:9 2K

Frequently Asked Questions about image-gen

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

FAQPage Schema
How do I generate professional images from text prompts using AI?

Text-to-image generation creates visuals from natural-language prompts using Gemini 3 Pro Image. This Skill accepts a prompt, optional reference images, and outputs a professional image in your chosen resolution and aspect ratio—useful for marketing materials, infographics, and technical diagrams without design software.

Can I use reference images to control the style and composition of generated visuals?

Yes, this Skill supports up to 14 reference images for style transfer and composition guidance. Upload reference images alongside your prompt to influence the output's visual direction, ensuring generated content aligns with your brand or design system.

What image resolutions and aspect ratios does AI image generation support?

AI image generation supports aspect ratios of 1:1, 2:3, 3:2, 4:3, 16:9, and 21:9 at three resolutions: 1K, 2K, and 4K. Choose the format that matches your use case—square for social media, 16:9 for presentations, or 21:9 for panoramic content.

How do I create diagrams and infographics without hiring a designer?

Workflow-driven prompts enable you to describe diagram structure and content in plain language. The Skill generates professional diagrams and infographics from your description, supporting data storytelling and technical documentation without design expertise.

What setup do I need to start generating images with Gemini?

You need a GEMINI_API_KEY environment variable configured. The Skill handles dependencies (google-genai, pillow, python-dotenv) automatically, so you can generate images immediately after providing your API key.

Can I refine and iterate on generated images?

Yes, the Skill supports iterative refinement through workflow-based prompts and optional text responses. Adjust your prompt description or reference images and regenerate until the output matches your vision.