August 29, 2022
@KathrynECramer @Merzmensch In my experience, portrait/vertical images generated with Stable Diffusion have a huge chance of generating the same subject one on top of the other. As if it would simply generate multiple independent 512px squares stacked vertically.

This is one of the many thoughts I post on Twitter on daily basis. They span many disciplines, including art, artificial intelligence, automation, behavioral economics, cloud computing, cognitive psychology, enterprise management, finance, leadership, marketing, neuroscience, startups, and venture capital.

I archive all my tweets here.