This is the official U-DiT model from our work "U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers". The model is trained for 400K iterations on the ImageNet 256x256 dataset.
Model Details
Model Name
FLOPs (G)
Training Iters
FID
U-DiT-S
6.04
400K
31.51
U-DiT-B
22.22
400K
16.64
U-DiT-L
85.00
400K
10.08
U-DiT-B
22.22
1M
12.87
U-DiT-L
85.00
1M
7.54
Citation
If you find this model useful, please cite:
@misc{tian2024udits,
title={U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers},
author={Yuchuan Tian and Zhijun Tu and Hanting Chen and Jie Hu and Chao Xu and Yunhe Wang},
year={2024},
eprint={2405.02730},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
U-DiT huggingface.co is an AI model on huggingface.co that provides U-DiT's model effect (), which can be used instantly with this yuchuantian U-DiT model. huggingface.co supports a free trial of the U-DiT model, and also provides paid use of the U-DiT. Support call U-DiT model through api, including Node.js, Python, http.
U-DiT huggingface.co is an online trial and call api platform, which integrates U-DiT's modeling effects, including api services, and provides a free online trial of U-DiT, you can try U-DiT online for free by clicking the link below.
yuchuantian U-DiT online free url in huggingface.co:
U-DiT is an open source model from GitHub that offers a free installation service, and any user can find U-DiT on GitHub to install. At the same time, huggingface.co provides the effect of U-DiT install, users can directly use U-DiT installed effect in huggingface.co for debugging and trial. It also supports api for free installation.