What is Contrastive Language-Image Pre-training (CLIP)?

Contrastive Language-Image Pre-training (CLIP)

Contrastive Language-Image Pre-training (CLIP): A model trained to match images with their text descriptions, widely used to steer and to evaluate image generators.

Related terms

Carbon footprint of training
Compute-optimal training
Contrastive learning
Distributed training
Fair use (AI training)
GPT (generative pre-trained transformer)
Holistic Evaluation of Language Models (HELM)
Image captioning

Browse the full glossary →