About Dawid Stachowiak

In this blog post, we empirically investigated portrait generation using diffusion models. Imitating human evaluation, we objectively measured aspects usually left to subjective manual checks and arbitrary decisions.

This is the second post in our series “Diffusion models in practice”. In this article, we start our journey into the practical aspects of diffusion modeling, which we found even more exciting. First, we would like to address a fundamental question that arises when one begins to venture into the realm of generative models: Where to start?

The AI revolution continues, and there is no indication of it nearing the finish line. The last year has brought astonishing developments in two critical areas of generative modeling: large language models and diffusion models.