Vladimir Bok

Image Generation Models

Image Generation Models explores the inner workings of the generative AI models behind modern computer vision. You’ll start by developing a simple autoencoder and extending it into a variational autoencoder for image generation. Next, you’ll dive deep into GANs and discover how to upgrade their performance with next-generation techniques like Wasserstein GAN. Create your own denoising diffusion probabilistic models that can generate original imagery, and even implement a simplified text-to-image model! Plus, you’ll explore hybrid models that benefit from the strengths of multiple approaches, and even video-based generative AI. Throughout, real-world case studies demonstrate how these models can be put into action.

GANs in Action

GANs in Action teaches you to build and train your own Generative Adversarial Networks. You'll start by creating simple generator and discriminator networks that are the foundation of GAN architecture. Then, following numerous hands-on examples, you'll train GANs to generate high-resolution images, image-to-image translation, and targeted data generation. Along the way, you'll find pro tips for making your system smart, effective, and fast.