🧪🧪 Edge#221: What are Diffusion Models

+ Google's Imagen; +MindsEye

In this issue:

• we explain what Diffusion Models are; 

• we discuss Imagen, Google’s massive diffusion model for photorealistic text-to-image generation; 

• we explore MindsEye, which allows you to run multiple generative art models in a single interface.

Enjoy the learning!  

---

💡 ML Concept of the Day: What are Diffusion Models  

As the first deep dive of our series about text-to-image models, we would like to discuss the recent diffusion techniques that have revolutionized the space. Even though to start with discussing more traditional methods like GANs or autoregressive models might have been a better idea, we think diffusion methods are having such an impact on text-to-image models that they deserve a lot of space in this series.