Tweeted By @_akhaliq
Scalable Diffusion Models with Transformers
— AK (@_akhaliq) December 20, 2022
abs: https://t.co/RlOulZLZ1U
largest DiT-XL/2 models outperform all prior diffusion models on the class conditional ImageNet 512×512 and 256×256 benchmarks, achieving a state-of-the-art FID of 2.27 on the latter pic.twitter.com/lGVFXn9keN