HiT: Hierarchical Diffusion Transformer for End-to-End Image Generation

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 256ร—256, 600 epochs FID-50K 1.48
T2I512/HiT-B16_sft40k/model.safetensors HiT-B/16, text-to-image 512ร—512, 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.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Paper for Nicholas0228/HiT