Hi-DiT: Hybrid Latent-Pixel Diffusion Transformer for Image Generation
Open paper
Benchmark
Model
Rank
Results
image-generation-on-imagenet-256x256
Hi-DiT (CFG=2.4)
–
FID: 1.06
image-generation-on-imagenet-512x512
Hi-DiT (CFG=4.6)
–
FID: 1.26
Inception score: 295.0
Rank counts only results with a code link.