openai/CLIP

connects images and text for zero-shot predictions

View on index · View in 3D Map

Related repos

• open source CLIP models for image-text tasks
• Trains agents to act from videos
• Tracks any point in a video
• open source AI model for generating videos from text prompts
• MobileCLIP brings fast image-text AI models to mobile devices
• AI video clipper with speech and text recognition
• Community .NET library for OpenAI API
• Extracts text from images locally in the browser
• Web interface for creating AI images and videos
• turn a photo and audio into a talking video with AI