#introduction

I’m Marcelo, a first year CS PhD student at TTI Chicago. I am currently working on American Sign Language translation using Computer Vision.

In my free time, I enjoy working on Film projects, photography, strategy games, and overly analysing the movies and TV shows I consume.

Scalable Diffusion Models with Transformers (DiT)

DiT-XL/2 models outperform all prior diffusion models on the class-conditional ImageNet 512×512 and 256×256 benchmarks

Try out the @[email protected] Demo on @[email protected] Spaces

demo: https://huggingface.co/spaces/wpeebles/DiT