Repository Showcase
A curated collection of interesting GitHub repositories
NVlabs/OmniVinci
LLM for vision, audio, and language
Related repos
- 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
- AI wearable for transcriptions and actions
- homelab configs, scripts, and docs for IT setups
- open-source platform for building LLM apps and AI workflows
- Edit videos in your browser with this open source tool—no accounts or uploads needed
- Open-source toolkit for training and generating videos from text or other data inputs
- Open-source models getting closer to GPT-5 for handling images and text together
- VILA: Visual language models for AI tasks
