01Analyze single images from a URL to get descriptions or answers to prompts
02Compare and analyze up to 8 images simultaneously for combined insights
03Extract all visible text from images using OCR-focused capabilities
04Compatible with any local OpenAI-API vision server (e.g., llama.cpp, Ollama, vLLM)
05Integrates with gimmick-search-mcp for live preview of analysis results
062 GitHub stars