As part of ongoing promotions for the book, The Digital Visual Effects Studio: The Artists and Their Work Revealed, Mayur hosted webinars on December 6 and 7, 2009. In the sessions, Mayur made the case for artist-centric pipelines, as opposed to data-centric pipelines and he shared some insight as to why production pipelines fail to be fast, light and powerful. We are pleased to make available a recording of one of the sessions, with a run-time of 56m30s.
Stable Diffusion is a latent diffusion model that generates AI images from text. Instead of operating in the high-dimensional image space, it first compresses the image into the latent space.
Stable Diffusion belongs to a class of deep learning models called diffusion models. They are generative models, meaning they are designed to generate new data similar to what they have seen in training. In the case of Stable Diffusion, the data are images.
Why is it called the diffusion model? Because its math looks very much like diffusion in physics. Let’s go through the idea.
