Gemini Image Generation

About

Empowers Claude to create and manipulate images directly within the development workflow using Google's Gemini API. This skill provides specialized CLI scripts for generating new images from text, editing existing files through conversational instructions, and composing complex scenes from multiple reference images. With support for resolutions up to 4K, customizable aspect ratios, and advanced features like Google Search grounding for real-time visual data, it is an essential tool for rapid prototyping of UI elements, logos, and photorealistic product mockups.

Key Features

• Conversational image editing and multi-turn refinement for iterative design cycles.
• Granular control over aspect ratios including wide-screen, portrait, and cinematic formats.
• High-resolution image generation from text prompts up to 4K quality.
• Real-time visual grounding using Google Search integration.
• Multi-image composition support using up to 14 reference sources.
• 0 GitHub stars

Use Cases

• Creating high-fidelity product mockups and photorealistic visualizations for documentation and presentations.
• Performing complex image manipulations and style transfers on existing project assets.
• Generating UI assets, logos, and stickers directly from text descriptions during development.