Training deep models using anime, illustration images.

Last update: Dec 25, 2022

Overview

animeface

deep models for anime images.

Datasets

anime-face-dataset Anime faces collected from Getchu.com. Based on Mckinsey666's dataset. 63.6K images.
Tagged Anime Illustrations A subset of the Danbooru2017, and the moeimouto face dataset. 337K Danbooru images, 17.4K moeimouto face images.
Danbooru2019 Portraits [1] Portraits of anime characters collected from Danbooru2019. 302K portraits.

Models

"code" is indicated when only an official implementation exists.

Generative Adversarial Networks (GANs)

Method	paper	code
Alias Free GAN (StyleGAN3)	arxiv	github
Augmented-Self Reference and Dense Semantic Correspondence (SCFT)	arxiv	-
auxiliary classifier GAN (ACGAN)	arxiv	-
big GAN (BigGAN)	arxiv	github
conditional GAN (cGAN)	arxiv	-
Contrastive Discriminator (ContraD)	openreview	github
deep convolutional GAN (DCGAN)	arxiv	-
deep regret analytic GAN (DRAGAN)	arxiv	github
Enhanced super resolution GAN (ESRGAN)	arxiv	github
Fourier Features	arxiv	github
GANILLA	arxiv	github
generative adversarial networks (GAN)	arxiv	-
Image-to-image Translation via Hierarchical Style Disentanglement (HiSD)	arxiv	github
Improved Transformer for High-Resolution GANs (HiT)	arxiv	-
Hologram(?) GAN (HoloGAN)	arxiv	github
Position Encoding as Spatial Inductive Bias	arxiv	github
progressive growing of GANs (PGGAN)	arxiv	github
pix2ix	arxiv	github
pix2pix HD	arxiv	github
single GAN (SinGAN)	arxiv	github
Spatially-Adaptive Normalization (SPADE)	arxiv	github
style-based GAN (StyleGAN)	arxiv	github
style-based GAN 2 (StyleGAN2)	arxiv	github
Super resolution GAN (SRGAN)	arxiv	-
Transformer-based GAN (TransGAN)	arxiv	github
unsupervised GAN with adaptive layer-instance normalization (UGATIT)	arxiv	github
Wasserstein GAN (WGAN)	arxiv	-
WGAN with gradient penalty (WGAN_gp)	arxiv	-
zero-centered gradient penalty	arxiv	-
simplified zero-centered gradient penality	arxiv	github

Auto Encoders

Method	paper	code
Auto Encoder (AE)	tronto	-
Variational Auto Encoder (VAE)	arxiv	-

Other

Method	paper	code
AdaBelief optimizer	arxiv	github
Adaptive Discriminator Augmentation (ADA)	arxiv	github
differentiable augmentation (DiffAugment)	arxiv	github
pixel shuffle	arxiv	-

Weights

See weights.md

Reference

[1] Gwern Branwen, Anonymous, & The Danbooru Community;
    “Danbooru2019 Portraits: A Large-Scale Anime Head Illustration Dataset”,
    2019-03-12. Web. Accessed 2020/09/17,
    https://www.gwern.net/Crops#danbooru2019-portraits

Author

Tomoya Sawada

Training deep models using anime, illustration images.

Related tags

Overview

animeface

Datasets

Models

Generative Adversarial Networks (GANs)

Auto Encoders

Other

Weights

Reference

Author

Owner

Tomoya Sawada

Code for Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation (CVPR 2021)

Music Source Separation; Train & Eval & Inference piplines and pretrained models we used for 2021 ISMIR MDX Challenge.

Pretrained models for Jax/Haiku; MobileNet, ResNet, VGG, Xception.

A lightweight deep network for fast and accurate optical flow estimation.

Pytorch implementation of AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks

Face Mask Detection on Image and Video using tensorflow and keras

Convert dog pictures into various painting styles. Try LimnPet

LoL Runes Recommender With Python

Speech recognition tool to convert audio to text transcripts, for Linux and Raspberry Pi.

Scalable machine learning based time series forecasting

Equivariant layers for RC-complement symmetry in DNA sequence data

A code implementation of AC-GC: Activation Compression with Guaranteed Convergence, in NeurIPS 2021.

PyTorch implementation of Asymmetric Siamese (https://arxiv.org/abs/2204.00613)

WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose

PyTorch implementation of Weak-shot Fine-grained Classification via Similarity Transfer

DGN pymarl - Implementation of DGN on Pymarl, which could be trained by VDN or QMIX

Implementation of CVPR'2022:Surface Reconstruction from Point Clouds by Learning Predictive Context Priors

Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.

Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".

Official PyTorch code of Holistic 3D Scene Understanding from a Single Image with Implicit Representation (CVPR 2021)