Hierarchical Diffusion Transformer for End-to-End Image Generation
Paper โข 2611.22962 โข Published
This repository hosts the official PyTorch checkpoints of HiT. HiT is a pixel-space diffusion Transformer that learns to group related image patches into a visual hierarchy and runs most of its blocks on the compact groups.
| Checkpoint | Model | Should reproduce |
|---|---|---|
ImageNet256/HiT-XL16_ep600/model.safetensors |
HiT-XL/16, ImageNet 256ร256, 600 epochs | FID-50K 1.48 |
T2I512/HiT-B16_sft40k/model.safetensors |
HiT-B/16, text-to-image 512ร512, 40k fine-tuning updates | GenEval 87.78, DPG 85.33, PRISM 58.62, CoRe 45.22, Spatial 52.68 |
Text-to-image training inputs: Nicholas0228/minit2i-frozen-inputs-v1.