Diffusion Transformers with Representation Autoencoders
Open paper
Benchmark
Model
Rank
Results
image-generation-on-imagenet-512x512
DiT^DH-XL (DINOv2-B)
#2
FID: 1.13
image-generation-on-imagenet-256x256
DiT^DH-XL (DINOv2-B)
#7
FID: 1.13
Rank counts only results with a code link.