ContraD
pix2pixHD
Our great sponsors
ContraD | pix2pixHD | |
---|---|---|
1 | 6 | |
186 | 6,498 | |
- | 0.8% | |
0.0 | 0.0 | |
over 2 years ago | 10 months ago | |
Python | Python | |
MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ContraD
-
[D] What is the smallest dataset you styleGAN2 trained?
Well, I've been trying to train a 1024 GAN from scratch on stylegan2-ada-pytorch with a small dataset 300 samples of not so diversity in images of painting faces. Fact is that on first try FID went as low as 71 and started deteriorating. Now I x-flip augmented the dataset (700 images) and at 900kimg FID went 64 but I doubt it will get lower. I lowered the learning rate to 0.0001 as they say it might help... Recently found this way of dataset augmentation... probably will use this https://github.com/jh-jeong/ContraD
pix2pixHD
-
Image to hand drawn
Sources: U2Net, ArtLine, Pix2PixHD, APDrawingGAN
-
[P] I made FaceShop! Instance segmentation + CGAN for editing faces (badly)
Pix2PixHD (from DeepSIM)
Uses a mix of instance segmentation (BiSeNet) and conditional GAN, and is heavily inspired by the Pix2PixHD and DeepSIM papers. Will have more details when I wake up!
What are some alternatives?
pytorch-CycleGAN-and-pix2pix - Image-to-Image Translation in PyTorch
awesome-colab-notebooks - Collection of google colaboratory notebooks for fast and easy experiments
sofgan - [TOG 2022] SofGAN: A Portrait Image Generator with Dynamic Styling
face-parsing.PyTorch - Using modified BiSeNet for face parsing in PyTorch
generative-inpainting-pytorch - A PyTorch reimplementation for paper Generative Image Inpainting with Contextual Attention (https://arxiv.org/abs/1801.07892)
contrastive-unpaired-translation - Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
CycleGAN - Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
StyleSwin - [CVPR 2022] StyleSwin: Transformer-based GAN for High-resolution Image Generation
Im2Vec - [CVPR 2021 Oral] Im2Vec Synthesizing Vector Graphics without Vector Supervision
DeblurGANv2 - [ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
ArtGAN - ArtGAN + WikiArt: This work presents a series of new approaches to improve GAN for conditional image synthesis and we name the proposed model as “ArtGAN”.
gaussian-splatting - Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"