NVlabs/OmniVinci

LLM for vision, audio, and language

View on index · View in 3D Map

Related repos

• Distills vision foundation models into one
• Open-source library for communication systems research
• Wearable for transcription and summaries
• Generates localized descriptions for images and videos
• audio-driven avatar video generation with prompt-based control and full-body animation
• multimodal data annotation for images, video, audio
• homelab configs, scripts, and docs for IT setups
• Visual editor for Open Graph images
• open-source platform for building LLM apps and AI workflows
• Curated list of computer vision papers and code