HiT / README.md
Nicholas0228's picture
Model card: remove the unconditional task tag
160ad7f verified
|
Raw History Blame Contribute Delete
1.05 kB
metadata
license: mit
tags:
  - image-generation
  - text-to-image
  - class-conditional
  - imagenet
  - diffusion
  - pixel-space

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