MobileCLIP2 Collection MobileCLIP2: Mobile-friendly image-text models with SOTA zero-shot capabilities trained on DFNDR-2B • 37 items • Updated 3 days ago • 50
FastVLM Collection Efficient Vision Encoding for Vision Language Models • 9 items • Updated 13 days ago • 96
Running on A10G 25 25 Segment Anything 2 Video Tracking 👀 Segment any objects and track them through a video with SAM2
ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing Paper • 2508.10881 • Published Aug 14 • 52