Generative AI with Diffusion Models

Generative AI with Diffusion Models

Issued by University of Florida

Advanced learners take a deeper dive on denoising diffusion models, which are a popular choice for text-to-image pipelines, disrupting several industries. Generative AI will gain significant importance due to its various applications such as Creative Content Generation, Data Augmentation, Simulation and Planning, Anomaly Detection, Drug Discovery, and Personalized Recommendations, all essential for advanced learners who already have a good understanding of PyTorch and deep learning.

Skills

Earning Criteria

  • By the end of this workshop, you’ll learn: build a U-Net to generate images from pure noise, improve the quality of generated images with the Denoising Diffusion process, compare Denoising Diffusion Probabilistic Models (DDPMs) with Denoising Diffusion Implicit Models (DDIMs), control the image output with context embeddings and generate images from English text-prompts using Contrastive Language–Image Pre-training (CLIP).