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


Upon successful completion of the assessment, you will receive an NVIDIA certificate.