Mydra logo
Log in
>All courses>Artificial Intelligence
Artificial Intelligence
DeepLearning.AI logo

DeepLearning.AI

How Diffusion Models Work

  • up to 1 hour
  • Intermediate

In this course, you will gain a deep familiarity with the diffusion process and the models which carry it out. You will learn to build a diffusion model from scratch, train it, and implement algorithms to speed up sampling by 10x.

  • Diffusion process
  • Generative AI
  • Building diffusion models
  • Training diffusion models
  • Neural networks for noise prediction

Overview

In 'How Diffusion Models Work', you will explore the cutting-edge world of diffusion-based generative AI. This course will teach you to build a diffusion model from scratch, gain deep familiarity with the diffusion process, and acquire practical coding skills through labs on sampling, training diffusion models, building neural networks for noise prediction, and adding context for personalized image generation. By the end of the course, you will have a model that can serve as a starting point for your own exploration of diffusion models for your applications.

  • Web Streamline Icon: https://streamlinehq.com
    Online
    course location
  • Layers 1 Streamline Icon: https://streamlinehq.com
    English
    course language
  • Self-paced
    course format
  • Live classes
    delivered online

Who is this course for?

AI Enthusiasts

Individuals interested in understanding and building diffusion models from scratch.

Intermediate Developers

Developers with knowledge of Python, Tensorflow, or Pytorch looking to expand their skills in generative AI.

Data Scientists

Professionals aiming to enhance their capabilities in training and optimizing diffusion models.

This course will teach you to build, train, and optimize diffusion models, expanding your generative AI capabilities. Ideal for AI enthusiasts, intermediate developers, and data scientists, it provides practical coding skills and hands-on examples to help you achieve your goals and advance your career.

Pre-Requisites

1 / 2

  • Knowledge of Python

  • Familiarity with Tensorflow or Pytorch

What will you learn?

Introduction to Diffusion Models
Gain an understanding of what diffusion models are and their applications in generative AI.
Building a Diffusion Model
Learn to build a diffusion model from scratch, including the necessary coding and algorithms.
Training Diffusion Models
Acquire skills to train diffusion models effectively, including techniques to optimize performance.
Neural Networks for Noise Prediction
Understand how to build neural networks specifically for noise prediction in diffusion models.
Personalized Image Generation
Learn to add context for personalized image generation using diffusion models.
Speeding Up Sampling
Implement algorithms to speed up the sampling process by 10x.
Hands-on Labs
Work through practical labs on sampling, training, and building neural networks, with built-in Jupyter notebooks for seamless experimentation.

Meet your instructor

  • Sharon Zhou

    Cofounder & CEO (Lamini), CS Faculty (Stanford University), Lamini, Stanford University

    Sharon Zhou is a leader in the field of generative AI. She is the cofounder and CEO of Lamini, an LLM startup, and a CS faculty member at Stanford University. She has a PhD in CS from Stanford, where she led a research group of 50+ students and published award-winning research on generative AI.

Upcoming cohorts

  • Dates

    start now

Free