This course covers advanced topics in stable diffusion, including issues with standard diffusion models, reconstruction loss, adversarial loss, conditioning, image generation, super-resolution, and real-world applications. The course aims to teach students how to address challenges in diffusion models and apply them to various tasks through hands-on experiments. The intended audience for this course is individuals interested in deep learning, generative models, and image processing.
Overview
Syllabus
Introduction
Issues with standard diffusion models
Visualizing the issue with data
Method - Reconstruction Loss
Method - Adversarial Loss
Method - Conditioning
Experiments
Image Generation with Unconditional Latent Diffusion
Super-Resolution with Latent Diffusion
A person crossing a busy intersection
Conclusion
Points For the Paper
Points Against the Paper
Taught by
UCF CRCV
Tags
Related Courses
-
Beyond Text - Giving Stable Diffusion New Abilities
-
Stable Diffusion and Friends - High-Resolution Image Synthesis via Two-Stage Generative Models
-
Generative Adversarial Networks and Stable Diffusion
-
Single Image Super Resolution Using SRGAN
-
Deep Generative Modeling
-
SRGAN Implementation From Scratch
Related articles
Reviews
4.0 rating, based on 2 Class Central reviews
-
David TrevesInteresting from a Mathematical standpoint, but I was expecting more of an applied approach to learning how to work with Stable Diffusion. -
Sanjay GuptaProvides good perspective of difference between GAN and LDM based approach. Examples are worth appreciating the effort put by authors.
