#381 · Primary category: Computer Vision
Anime-InPainting
An application tool of edge-connect, which can do anime inpainting and drawing.
Project last updated:03/27/19
GitHub Stars
1.1K
Forks
150
Contributors
1
License
Other
Why we included this project
Anime-InPainting takes the Edge-Connect inpainting GAN and packages it as an OpenCV-based desktop app, so you don't have to wire the algorithm together yourself. You open a small window, paint over the damaged, mosaic-covered, or missing part of an illustration with your mouse, and the network fills it back in, with an optional edge view to guide the reconstruction. The authors also streamlined the original training pipeline, adding auto-save and auto-load of weights plus a faster combined training phase, and shipped a detailed manual so you can retrain on your own anime dataset. It's a solid starting point for hobbyists and artists cleaning up character faces, though the pretrained weights are tuned for heads rather than full bodies. Keep the noncommercial license in mind if you plan to use it beyond personal or research work.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)