nipponjo/deepfillv2-pytorch
🖼️🎨 A PyTorch reimplementation of the paper Free-Form Image Inpainting with Gated Convolution (DeepFill v2) (https://arxiv.org/abs/1806.03589)
This project helps graphic designers, photographers, or marketers seamlessly remove unwanted objects or fill damaged areas in images. You provide an image with a masked region (indicating what to remove), and it outputs a new image with that region intelligently filled in, making the removal appear natural. This is ideal for anyone needing to clean up or restore visual content.
215 stars. No commits in the last 6 months.
Use this if you need to erase distracting elements, repair old photos, or complete partial images, and want a sophisticated tool to intelligently reconstruct the missing parts.
Not ideal if you need simple photo cropping, color correction, or only basic, geometric shape removal without complex content synthesis.
Stars
215
Forks
45
Language
Python
License
—
Category
Last pushed
Aug 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nipponjo/deepfillv2-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pathak22/context-encoder
[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs
knazeri/edge-connect
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019...
shepnerd/inpainting_gmcnn
Image Inpainting via Generative Multi-column Convolutional Neural Networks, NeurIPS2018
youyuge34/Anime-InPainting
An application tool of edge-connect, which can do anime inpainting and drawing. 动漫人物图片自动修复，去马赛克，填补，去瑕疵
otenim/GLCIC-PyTorch
A High-Quality PyTorch Implementation of "Globally and Locally Consistent Image Completion".