Skip to content
AI’s

architectures

CLIP

Contrastive Language-Image Pre-training, a model by OpenAI that learns visual concepts from natural language descriptions. CLIP can match images and text in a shared embedding space, enabling zero-shot image classification without task-specific training data.

In practice

CLIP can classify images into arbitrary categories like 'a photo of a golden retriever' without being specifically trained on dog breeds.

In the index

Tools that mention CLIP

Matched on each tool’s own description and feature list, highest trust score first.