Awesome Open Source
Awesome Open Source

Anime-InPainting: An application Tool based on Edge-Connect

Version Status Platform PyTorch License

English | 中文版介绍


2019.3.27 Update:
Our latest drawing method PI-REC is more powerful.
Take a look on it, and I'm sure it won't disappoint you.

Tool show time 🏳️‍🌈


Tool operation


This is an optimized application tool which has a frontend based on Opencv, whose backend used Edge-Connect. Make sure you have read their awesome work and license thoroughly. Compared with the original work, this project has such improvements :

  • Add tool application modes
  • Optimize the training phase
    • Auto-save and auto-load latest weights files
    • Add a fast training phase combined with origin phase 2 and 3
  • bugs fixed (most of them are merged into the original work)
  • Add utility files
  • Add configs in config.yml
    • DEVICE : cpu or gpu
  • ... ...

You can do the amazing Anime inpainting conveniently here.

And detailed training manual is released. You may train your own dataset smoothly now.


  • Python 3
  • PyTorch 1.0 (0.4 is not supported)


  • Clone this repo
  • Install PyTorch and dependencies from
  • Install python requirements:
pip install -r requirements.txt

Run the Tool

I want to run the tool! Calm down and follow such step:

Info: The following weights files are trained on anime face dataset which performs not good on a large whole anime character.

  1. Download the well trained model weights file --> Google Drive | Baidu
  2. Unzip the .7z and put it under your root directory. So make sure your path now is: ./model/getchu/<xxxxx.pth>
  3. Complete the above Prerequisites and Installation
  4. (Optional) Check and edit the ./model/getchu/config.yml config file as you wish
  5. Run the cooool tool:

Default Tool:

python --path model/getchu/

Tool with edge window:

python --edge --path model/getchu/

Args help

python -h

PS. You can run any well trained model, not only above one. You can download more model weights files from the original work Edge-Connect. Then you can run the Tool as above. Only one thing to be careful: The config.yml in this project has some additional options than the config from the Edge-Connect.

Tool operation

For detailed manual, refer to your terminal prints or the __doc__ in

Below is the simplified tool operation manual:

Key description
Mouse Left To draw out the defective area in window input and to draw the edge in window edge
Mouse Right To erase edge in window edge
Key [ To make the brush thickness smaller
Key ] To make the brush thickness larger
Key 0 Todo
Key 1 Todo
Key n To patch the black part of image, just use input image
Key e To patch the black part of image, use the input image and edit edge (only work under edge window opened)
Key r To reset the setup
Key s To save the output
Key q To quit

Training manual

Click here --> Training manual by yourself



2019.3.27 更新:
我们的最新模型 PI-REC 更强大.


Tool效果看上面👆 | Bilibili视频教程:TO DO

这是图像修补方向最新研究成果Edge-Connect阿姆斯特朗氮气加速魔改(优化)版。 用Opencv写了个前端部分,后端是Edge-Connect,方便当作工具使用。 此工具可以用来自动图像修补,去马赛克……同样优化了模型训练的过程。具体优化内容请看英文版Improvements



  • Python 3
  • PyTorch 1.0 (0.4 会报错)
  • NVIDIA GPU + CUDA cuDNN (当前版本已可选cpu,请修改config.yml中的DEVICE


  • Clone this repo
  • 安装PyTorch和torchvision -->
  • 安装 python requirements:
pip install -r requirements.txt




  1. 下训练好的模型文件 --> Google Drive | Baidu
  2. 解压 .7z 放到你的根目录下. 确保你的目录现在是这样: ./model/getchu/<xxxxx.pth>
  3. 完成上面的基础环境和第三方库安装步骤
  4. (可选) 检查并编辑 ./model/getchu/config.yml 配置文件
  5. 使用以下命令运行:


python --path model/getchu/


python --edge --path model/getchu/


python -h

PS. 你也能用tool跑别的任何模型,在这里下载原作更多模型Edge-Connect. 文件组织方式参考上面,其余运行命令都一样。唯一注意的是这个项目的 config.yml 比原作的多了几个选项,报错了的话注意修改。



按键 说明
鼠标左键 Input窗口:画出瑕疵区域的遮盖,Edge窗口:手动画边缘
鼠标右键 Edge窗口:橡皮擦
按键 [ 笔刷变细 (控制台打印粗细大小)
按键 ] 笔刷变粗
按键 0 Todo
按键 1 Todo
按键 n 修补黑色涂抹区域,只使用一张输入图片
按键 e 修补黑色涂抹区域,使用输入图片和边缘图片(仅当edge窗口启动时有效)
按键 r 全部重置
按键 s 保存输出图片
按键 q 退出


训练指南 --> 阅读


Licensed under a Creative Commons Attribution-NonCommercial 4.0 International.

Except where otherwise noted, this content is published under a CC BY-NC license, which means that you can copy, remix, transform and build upon the content as long as you do not use the material for commercial purposes and give appropriate credit and provide a link to the license.


If you use this code for your research, please cite our paper EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning:

  title={EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning},
  author={Nazeri, Kamyar and Ng, Eric and Joseph, Tony and Qureshi, Faisal and Ebrahimi, Mehran},
  journal={arXiv preprint},
Related Awesome Lists
Top Programming Languages
Top Projects

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (795,861
Deep Learning (35,987
Pytorch (20,745
Neural Network (15,414
Opencv (13,274
Connect (8,730
Computer Vision (8,646
Edge (7,582
Gan (5,128
Generative Adversarial Network (5,128
Manual (4,336
Cv (4,279
Anime (2,885
Mosaic (841
Inpainting (112