AIbase
EN
Home
Metaclip L14 400m
M

Metaclip L14 400m

Developed by facebook
MetaCLIP is a vision-language model trained on CommonCrawl data for constructing shared image-text embedding spaces.
Text-to-Image
Transformers
#Zero-shot image classification#Cross-modal retrieval#Large-scale pre-training
Downloads 325
Release Time : 10/9/2023

Model Overview

This model builds a shared embedding space for images and texts by analyzing CLIP training data filtering methods, supporting various cross-modal tasks.

Model Features

Large-scale data training
Trained on 400 million data points from CommonCrawl
Cross-modal understanding
Constructs shared embedding spaces for images and texts
Zero-shot capability
Supports zero-shot classification without task-specific training

Model Capabilities

Image classification
Text-to-image retrieval
Image-to-text retrieval
Cross-modal understanding

Use Cases

Content retrieval
Text-based image search
Retrieve relevant images using natural language descriptions
Content classification
Zero-shot image classification
Classify images of new categories without training
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase