Clarifai / main

Overview

This app holds great models and workflows built by Clarifai that you can use in your own apps. Feel free to explore all the different models! Here are a few of the workflow highlights it contains:

Visual Classifiers

• General, Travel, Food, Wedding, Demographics, Face sentiment

Moderation

• Image moderation, Text moderation

Visual Detectors

• General Detection, Face detection

General Classifier

Recognize over 11,000 different concepts including objects, themes, moods, and more, with outputs in 23 different languages. This model is a great all-purpose solution for most visual recognition needs. Simply pass in an image input with a publicly accessible URL or by directly sending image bytes, and the API returns a list of concepts (such as car, girl, and happiness) with corresponding probability scores on the likelihood that these concepts are present within the image.

General Detection

Similar to the General Classifier, but draws bounding boxes around identified objects

Food Classifier

Recognize more than 1,000 food items in images down to the ingredient level. This model is great for anyone building a health and wellness-related app.

Text Moderation

Analyze and return probability scores that text contains concepts such as toxic, insult, obscene and threat. Moderate content and ensure the exclusion of profanity, threatening language and other unwanted text.

Face Detection

Our state-of-the-art Face Detection Model can differentiate faces based on only a small number of sample images. Alignment and transformation technology allows you to automatically recognize faces from any angle.

Face Sentiment

Not only detect faces, but return the emotion conveyed in an image.

Image Captioning

Image captioning is a fundamental task in vision-language understanding, where the model predicts a textual informative caption to a given input image. It can be surprisingly accurate, even for nonsensical images.