
moonshotai/Kimi-VL-A3B-Thinking-2506
Image-Text-to-Text
•
16B
•
Updated
•
25.4k
•
288
LightGlue demo
nanonets ocr / monkey ocr / typhoon ocr / smoldocling
Run V-JEPA 2 on a video stream for Video Classification
OmniGen2: Unified Image Understanding and Generation.
Real-time video generation
Streamlit template space
Image-to-3D Generation