Ever Seen an Astronaut Riding a Horse? - Understanding and Applying Text to Image Generation Models

Explore the fascinating world of text-to-image generation models in this 45-minute Devoxx conference talk. Delve into the architecture and theory behind cutting-edge models like DallE-2, ImageGen, and StableDiffusion, which can create photorealistic images from text prompts with unprecedented accuracy. Discover advanced applications of these models and learn how to generate your own images using KerasCV, the most optimized implementation of StableDiffusion available. Presented by Luke Wood, a Machine Learning Specialist and Software Engineering Generalist working at Google on the Keras team, this talk offers valuable insights into the potential and practical applications of text-to-image technology.