AI Agent Skills

Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic…

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications