Generative AI with Diffusion Models
This two-part workshop builds on Fundamentals of Deep Learning and will introduce techniques used in generative AI.
Denoising diffusion models 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 active learning and 1 hour of extra Q&A. You will work with Python code in a Jupyter notebook environment.
Learning objectives:
- Build a U-Net to generate images from pure noise
- Improve the quality of generated images with the denoising diffusion process
- Control the image output with context embeddings
- Generate images from English text prompts using the Contrastive Language—Image Pretraining (CLIP) neural network
- Date:
- Monday, October 5, 2026 Show more dates
- Time:
- 1:00pm - 5:00pm
- Audience:
- Faculty Grad students & postdocs ISU staff Undergrads
- Categories:
- Workshop > The Catalyst
Important
-
This workshop is in-person only and will not be recorded.
-
This is a two-part course. Make sure you can attend both sessions before you register.
-
A laptop is required to participate. Students can borrow a laptop through the library’s Tech Lending program.
-
Prerequisites: A basic understanding of Deep Learning Concepts or participation of the Fundamentals of Deep Learning series (hyperlink to the Fund of DL series libCal).