For implementation details, please refer to our Github Repo
ImageNet pretrained checkpoints
model
FID
IS
LEGO-L-PG
2.16
78.7
LEGO-L-PR
2.29
78.7
LEGO-XL-U
2.59
338.08
BibTex
Please cite our work if you find it is helpful. Thank you!
@inproceedings{
zheng2024learning,
title={Learning Stackable and Skippable {LEGO} Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling},
author={Huangjie Zheng and Zhendong Wang and Jianbo Yuan and Guanghan Ning and Pengcheng He and Quanzeng You and Hongxia Yang and Mingyuan Zhou},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=qmXedvwrT1}
}
