CLIP ViT-Large/14

CLIP ViT-Large/14 is a vision-language model from OpenAI that encodes images and text into a shared embedding space, enabling zero-shot image classification, image-text similarity scoring, and cross-modal retrieval without task-specific training. It is the large-patch-14 variant of the CLIP family, widely used as a backbone for downstream vision-language research and applications. Source: supabase.