Skip to content
/ DiffiT Public

[ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation

Notifications You must be signed in to change notification settings

NVlabs/DiffiT

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 

Repository files navigation

DiffiT: Diffusion Vision Transformers for Image Generation

Official PyTorch implementation of DiffiT: Diffusion Vision Transformers for Image Generation.

Code and pretrained DiffiT models will be released soon !

Star on GitHub

DiffiT achieves a new SOTA FID score of 1.73 on ImageNet-256 dataset !

teaser

In addition, DiffiT sets a new SOTA FID score of 2.22 on FFHQ-64 dataset !

teaser

We introduce a new Time-dependent Multihead Self-Attention (TMSA) mechanism that jointly learns spatial and temporal dependencies and allows for attention conditioning with finegrained control.

teaser

πŸ’₯ News πŸ’₯

  • [12.04.2023] πŸ”₯ DiffiT manuscript is now available on arXiv !

Benchmarks

Latent Space

ImageNet-256

Model Dataset Resolution FID-50K Inception Score
Latent DiffiT ImageNet 256x256 1.73 276.49

ImageNet-512

Model Dataset Resolution FID-50K Inception Score
Latent DiffiT ImageNet 512x512 2.67 252.12

Image Space

Model Dataset Resolution FID-50K
DiffiT CIFAR-10 32x32 1.95
DiffiT FFHQ-64 64x64 2.22

About

[ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation

Resources

Stars

Watchers

Forks

Packages

No packages published