01Generate images from text prompts using Google Gemini models.
02Edit existing images with text-based instructions to achieve desired modifications.
03Supports a wide range of aspect ratios and resolutions (e.g., 1:1, 16:9, 1K, 4K).
04Flexible authentication via Google Gemini API Key or Google Service Account (Vertex AI).
05Offers both HTTP and stdio transport options for integration with various MCP hosts.
061 GitHub stars