NVlabs/describe-anything

Generates localized descriptions for images and videos

View on index · View in 3D Map

Related repos

• LLM for vision, audio, and language
• multimodal data annotation for images, video, audio
• multilingual text generation and editing for images
• open source tool for labeling images, text, audio, video, and more
• VILA: Visual language models for AI tasks
• Extracts document content for generative applications
• Multimodal foundation models for video understanding
• Reframes image editing as video generation
• part-level 3D object generation from single images
• Generates videos for education via code