Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting

Python

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models.

Python

Real-time webcam demo with SmolVLM and llama.cpp server.

JavaScript

Expressive Portrait Image Animation for Live Streaming

Python

Gas Town - multi-agent workspace manager

Python

LTX-Video is the first DiT-based video generation model that contains all core capabilities of modern video generation in one model.

Python