BLIP2 Collection State-of-the-art vision-language model for image captioning and visual question answering (VQA) • 4 items • Updated 4 days ago
VideoPrism Collection VideoPrism is a family of foundational video-encoder models. • 4 items • Updated 5 days ago • 2
VideoPrism Collection VideoPrism is a family of foundational video-encoder models. • 4 items • Updated 5 days ago • 2