
TVPaint Animation
The digital solution for your professional 2D animation projects.

Resolution-robust Large Mask Inpainting with Fourier Convolutions.

LaMa (Resolution-robust Large Mask Inpainting with Fourier Convolutions) is an image inpainting tool that generalizes well to high resolutions, surpassing training resolutions. It leverages Fourier convolutions to complete images, even with periodic structures. The architecture includes convolutional neural networks and Fourier transforms to process and reconstruct masked image regions. LaMa offers functionalities such as image completion, object removal, and image restoration. It supports various environment setups including Python virtualenv, Conda, and Docker. Pre-trained models are available for download to facilitate inference, and it supports both CPU and GPU-based processing. The tool allows for training and evaluation, providing metrics on image quality.
LaMa (Resolution-robust Large Mask Inpainting with Fourier Convolutions) is an image inpainting tool that generalizes well to high resolutions, surpassing training resolutions.
Explore all tools that specialize in remove unwanted objects. This domain focus ensures LaMa Image Inpainting delivers optimized results for this specific requirement.
Explore all tools that specialize in fourier convolutions. This domain focus ensures LaMa Image Inpainting delivers optimized results for this specific requirement.
Generalizes well to resolutions higher than training (~2k vs. 256x256).
Uses Fourier convolutions to complete periodic structures effectively.
Provides pre-trained models for immediate use (Places2, CelebA-HQ).
Offers Docker support for easy deployment and environment consistency.
Includes options for refinement to improve the quality of inpainting results.
Clone the repository: git clone https://github.com/advimman/lama.git
Set up the environment using Python virtualenv, Conda, or Docker.
Install required dependencies using pip install -r requirements.txt or conda env create -f conda_env.yml.
Download pre-trained models from the provided Google Drive link.
Prepare input images and masks, ensuring masks are named as [images_name]_maskXXX[image_suffix].
Run the prediction script: python3 bin/predict.py model.path=$(pwd)/big-lama indir=$(pwd)/LaMa_test_images outdir=$(pwd)/output.
All Set
Ready to go
Verified feedback from other users.
"LaMa provides high-quality image inpainting with good resolution robustness, as evidenced by active community contributions and adaptations."
Post questions, share tips, and help other users.

The digital solution for your professional 2D animation projects.

Empowering independent artists with digital music distribution, publishing administration, and promotional tools.

Convert creative micro-blogs into high-performance web presences using generative AI and Automattic's core infrastructure.

Fashion design technology software and machinery for apparel product development.

Instantly turns any text to natural sounding speech for listening online or generating downloadable audio.

Professional studio-quality AI headshot generator for individuals and teams.