In this issue:

• we explore different types of diffusion;

• we discuss OpenAI’s GLIDE, a guided diffusion method for photorealistic image generation; 

• we explore the Hugging Face text-to-image catalog. 

Enjoy the learning!  

💡 ML Concept of the Day: Different Types of Diffusion  

In Edge#221, we introduced the concept of diffusion as one of the foundational methods of the new generation of text-to-image generation models. The essence of diffusion is introducing Gaussian noise into an input image and then training a model to reconstruct the original image from the noise. While the principles of diffusion techniques are relatively consistent, there are different variations that have been applied in modern text-to-image models. Let’s explore them:...