PyTorch Implementation of AnimeGANv2

Last update: Jan 07, 2023

Overview

PyTorch Implementation of AnimeGANv2

Updates

2021-10-17 Add weights for FacePortraitV2
2021-11-07 Thanks to ak92501, a web demo is integrated to Huggingface Spaces with Gradio.

See demo:
2021-11-07 Thanks to xhlulu, the torch.hub model is now available. See Torch Hub Usage.
2021-11-07 Add FacePortraitV2 style demo to a telegram bot. See @face2stickerbot by sxela

Basic Usage

Weight Conversion from the Original Repo (Requires TensorFlow 1.x)

git clone https://github.com/TachibanaYoshino/AnimeGANv2
python convert_weights.py

Inference

python test.py --input_dir [image_folder_path] --device [cpu/cuda]

Results from converted [Paprika] style model

(input image, original tensorflow result, pytorch result from left to right)

Note: Training code not included / Results from converted weights slightly different due to the bilinear upsample issue

Additional Model Weights

Webtoon Face [ckpt]

samples

Trained on 256x256 face images. Distilled from webtoon face model with L2 + VGG + GAN Loss and CelebA-HQ images. See test_faces.ipynb for details.

Face Portrait v1 [ckpt]

samples

Trained on 512x512 face images.

📺

Face Portrait v2 [ckpt]

samples

Trained on 512x512 face images. Compared to v1, 🔻beautify 🔺robustness

🦑 🎮 🔥

Torch Hub Usage

You can load Animegan v2 via torch.hub:

import torch
model = torch.hub.load('bryandlee/animegan2-pytorch', 'generator').eval()
# convert your image into tensor here
out = model(img_tensor)

You can load with various configs (more details in the torch docs):

model = torch.hub.load(
    "bryandlee/animegan2-pytorch:main",
    "generator",
    pretrained=True, # or give URL to a pretrained model
    device="cuda", # or "cpu" if you don't have a GPU
    progress=True, # show progress
)

Currently, the following pretrained shorthands are available:

model = torch.hub.load("bryandlee/animegan2-pytorch:main", "generator", pretrained="celeba_distill")
model = torch.hub.load("bryandlee/animegan2-pytorch:main", "generator", pretrained="face_paint_512_v1")
model = torch.hub.load("bryandlee/animegan2-pytorch:main", "generator", pretrained="face_paint_512_v2")
model = torch.hub.load("bryandlee/animegan2-pytorch:main", "generator", pretrained="paprika")

You can also load the face2paint util function. First, install dependencies:

pip install torchvision Pillow numpy

Then, import the function using torch.hub:

face2paint = torch.hub.load(
    'bryandlee/animegan2-pytorch:main', 'face2paint', 
    size=512, device="cpu"
)

img = Image.open(...).convert("RGB")
out = face2paint(model, img)

PyTorch Implementation of AnimeGANv2

Related tags

Overview

PyTorch Implementation of AnimeGANv2

Basic Usage

Additional Model Weights

Torch Hub Usage

Owner

A community run, 5-day PyTorch Deep Learning Bootcamp

🔪 Elimination based Lightweight Neural Net with Pretrained Weights

A simple python program that can be used to implement user authentication tokens into your program...

Code for generating the figures in the paper "Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?"

Python package for visualizing the loss landscape of parameterized quantum algorithms.

For storing the complete exploration of Visual Question Answering for our B.Tech Project

Politecnico of Turin Thesis: "Implementation and Evaluation of an Educational Chatbot based on NLP Techniques"

Minimisation of a negative log likelihood fit to extract the lifetime of the D^0 meson (MNLL2ELDM)

Code for Efficient Visual Pretraining with Contrastive Detection

Bagua is a flexible and performant distributed training algorithm development framework.

Implementation of CVPR'21: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

External Attention Network

NaturalCC is a sequence modeling toolkit that allows researchers and developers to train custom models

TensorFlow-based implementation of "Pyramid Scene Parsing Network".

Using python and scikit-learn to make stock predictions

Official implementation for: Blended Diffusion for Text-driven Editing of Natural Images.

The codes and related files to reproduce the results for Image Similarity Challenge Track 1.

Code for paper: "Spinning Language Models for Propaganda-As-A-Service"

Pseudo-rng-app - whos needs science to make a random number when you have pseudoscience?

Implementation of the GVP-Transformer, which was used in the paper "Learning inverse folding from millions of predicted structures" for de novo protein design alongside Alphafold2