Transformers are a type of neural network architecture introduced in the paper "Attention is All You Need" by Vaswani et al. in 2017. They have since become a fundamental building block in many state-of-the-art natural language processing (NLP) and other machine learning models. The "transformers" library, is used for performing deep learning tasks. It provides pre-trained models and various utilities for working with transformer-based architectures. The library has become a go-to resource for researchers, developers, and practitioners working on a wide range of Deep Learning applications. The "transformers.js" library was released with the goal of being functionally equivalent to the Python version and can perform tasks in the Natural Language Processing, Computer Vision, Audio and Multimodal domains. In this talk we will learn about transformers, how they work and their used to power AI technologies like ChatGPT and Stable Diffusion. We will learn how to use "transformers.js" to perform inference in real-time using pre-trained models that have been trained by us or large tech companies to recognize and create images, translate foreign languages and even write code!