Generates and edits high-quality images directly within Claude Code using Google's Gemini API.
The Gemini Image Coder skill empowers Claude to perform complex image generation and manipulation tasks using advanced Gemini models. It allows users to create visual assets from text prompts, perform semantic image editing, and utilize multi-turn refinement for precise creative control. With support for up to 14 reference images, custom aspect ratios at up to 4K resolution, and Google Search grounding for real-world context, this skill is a powerful addition for developers needing UI placeholders, marketing assets, or AI-driven creative workflows.
Key Features
01High-resolution image generation (1K, 2K, and 4K)
02Semantic image editing and multi-turn refinement
03Multi-reference image composition (up to 14 images)
04Ready-to-use CLI scripts for generation and editing
0513 GitHub stars
06Google Search grounding for contextually accurate visuals
Use Cases
01Automating batch image processing and artistic editing via CLI
02Generating production-ready UI assets and website placeholders
03Creating marketing materials or product mockups using reference styles
