advimman/lama
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
This project helps graphic designers, photographers, or digital artists easily remove unwanted objects or imperfections from images. You provide an image with a highlighted area (mask) you want to remove, and it intelligently fills that area with realistic background content, even for high-resolution photos and complex patterns. It's designed for anyone needing to clean up visual content without complex editing.
9,765 stars. No commits in the last 6 months.
Use this if you need to seamlessly remove large, intricate, or regularly patterned objects from high-resolution images, like removing a person from a crowd or a scratch from a texture.
Not ideal if you need fine-grained control over every pixel during the inpainting process or require specialized tools for very specific image restoration tasks beyond object removal.
Stars
9,765
Forks
1,036
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Feb 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/advimman/lama"
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".