apple/ml-mobileclip

MobileCLIP brings fast image-text AI models to mobile devices

View on index · View in 3D Map

Related repos

• fast vision-language model for on-device AI
• Framework for mobile agents with model and benchmark
• Android AI agent that understands your screen and acts on voice or text commands
• AI video clipper with speech and text recognition
• Multimodal LLM inference engine for mobile devices
• control your phone with natural language commands
• open source CLIP models for image-text tasks
• multimodal model for images, video, and text on your phone
• Extracts text from images using Apple Vision framework
• AI agent that taps and types on your iPhone across apps