Skip to content

ShijunJ/Anime_SR_Restoration

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Anime Super-Resolution and Restoration

This repository is a collection of existing Anime Super-Resolution and Restoration models for the convenience of researchers and engineers who want to restore anime images. This repo is a non-accelerated version of my Fast Anime VSR (https://github.com/Kiteretsu77/FAST_Anime_VSR/tree/main). This repo is continuously developing! Feel free to leave your suggestions!
⭐ If you like Anime_SR_Restoration, please help star this repo. Thanks! 🤗

📖Table Of Contents

Update

  • 2023.12.09: This repo is released.

Model supported now:

  1. Real-CUGAN: The original model weight provided by BiliBili (from https://github.com/bilibili/ailab/tree/main)
  2. Real-ESRGAN: Using Anime version RRDB with 6 Blocks (full model has 23 blocks) (from https://github.com/xinntao/Real-ESRGAN/blob/master/docs/model_zoo.md#for-anime-images--illustrations)
  3. VCISR: A model I trained with my paper using a private Anime training datasets (https://github.com/Kiteretsu77/VCISR-official)

Installation (Environment Preparation)

git clone [email protected]:Kiteretsu77/Anime_SR_Restoration.git
cd Anime_SR_Restoration

# Create conda env
conda create -n ASRR python=3.10
conda activate ASRR

# Install Pytorch we use:
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

# Install Other packages:
pip install -r requirements.txt

Inference:

  1. Setup opt.py for the input and output path
  2. Execute the following:
    python inferece.py

License

This project is released under the GPL 3.0 license.

Contact

If you have any questions, please feel free to contact with me at [email protected].

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 95.1%
  • Dockerfile 2.9%
  • Shell 2.0%