A comprehensive skill for image generation and editing using Google's Gemini model (gemini-3-pro-image-preview). Supports text-to-image generation with photorealistic and stylized outputs, image editing with element addition/removal, inpainting, style transfer, and multi-image composition. Features multiple resolutions (1K, 2K, 4K), various aspect ratios, Google Search grounding for real-time data, and multi-turn editing capabilities with up to 14 reference images.
npx skills add dair-ai/dair-academy-plugins --skill image-generatorwget https://github.com/dair-ai/dair-academy-plugins/archive/refs/heads/main.zip -O image-generator.zip