Downloads · 30 days
18
3% of all-time downloads
NimaBoscarino/aot-gan-celebahq
aot-gan-celebahq is a machine learning model from NimaBoscarino. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
AOT-GAN is a model that can be used for image in-painting. The CelebA-HQ checkpoint is trained on synthetic human faces, which should make it suitable for touching up and restoring portraits.
Downloads · 30 days
18
3% of all-time downloads
All-time downloads
607
Public
Repo size
182 MB
Likes
1
Public
Click a slice to open those files.
.bin60.8 MB · 100%
From the Hugging Face model README
AOT-GAN is a model that can be used for image in-painting. The CelebA-HQ checkpoint is trained on synthetic human faces, which should make it suitable for touching up and restoring portraits.
This model was generated using AOT-GAN-for-Inpainting, cited as
@inproceedings{yan2021agg,
author = {Zeng, Yanhong and Fu, Jianlong and Chao, Hongyang and Guo, Baining},
title = {Aggregated Contextual Transformations for High-Resolution Image Inpainting},
booktitle = {Arxiv},
pages={-},
year = {2020}
}
The CelebA-HQ dataset was created with this codebase: https://github.com/tkarras/progressive_growing_of_gans, owned by NVidia and licensed under Creative Commons Attribution-NonCommercial 4.0 International.