Event box

Part 2 of 2: Generative AI with diffusion models

Part 2 of 2: Generative AI with diffusion models

This three-part workshop will dive deeper into denoising diffusion models, which are a popular choice for text-to-image pipelines.

Applications of this technology include creative content generation, data augmentation, simulation and planning, anomaly detection, drug discovery, personalized recommendations, and more. Each session is roughly divided into 3 hours of interactive teaching and 1 hour of extra Q&A.

Three components below will spread over the two sessions:

  • U-Net architecture and training a model to remove noise from an image. 
  • Autoencoders and variational autoencoders and then go toward diffusion models.
  • Diffusion models and how to train them.

At the end of course, you can obtain a NVIDIA Certificate if you pass the assessment.

Important

This is a two-part course. Make sure you can attend both sessions before you register through session 1
A laptop is required to participate. Students can borrow a laptop through the library’s Tech Lending program. 

Prerequisites: 

Date:
Monday, April 14, 2025
Time:
1:00pm - 5:00pm
Location:
The Catalyst (Parks 199)
Audience:
  Faculty     Grad students & postdocs     ISU staff     Undergrads  
Categories:
  Workshop > The Catalyst  

This workshop is part of a collaboration between Transitional AI Center (TrAC) and University Library to bring classes from the NVIDIA Deep Learning Institute to Iowa State. Questions about the program can be sent to trac@iastate.edu