Is There a Limitation of Diffusion?

In many ways, it's similar to how an artist learns in life, it's just we learn slightly differently but not back differently than machines. The way these kind of lines work together, the way that the colors kind of are adjacent to each other, those kinds of things are what it starts to learn over time. And so it learns a lot of these kind of granular features. It doesn't necessarily learn them on this kind of huge scale. Learn some on sort of a smaller scale. We may have kind of like sub algorithms that we don't understand where we know certain types of pattern matching. Sometimes you see images where it hasn't quite learned that underlying sort of mangled geometry