QwenLM/Qwen-MM-Plugins

Qwen-MM-Plugins is a modular collection of native multimodal capabilities designed to enhance Qwen models. It enables AI agents to process images, video, audio, and 3D files natively, while also offering tools for hardware control, web search, and long-video memory. The project supports various Qwen model families, providing a standardized way to bridge the gap between LLMs and the physical world.