TVPaint Animation
The digital solution for your professional 2D animation projects.
Creativity
Paid
From $750
2D Animation
Storyboarding
Character Design
LaMa Image Inpainting
4.6
Free LaMa provides high-quality image inpainting with good resolution robustness, as evidenced by active community contributions and adaptations.
Resolution-robust Large Mask Inpainting with Fourier Convolutions.
0 views
0 saves
|
Refined 2/22/2026
About LaMa Image Inpainting
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.
Core Capabilities
LaMa (Resolution-robust Large Mask Inpainting with Fourier Convolutions) is an image inpainting tool that generalizes well to high resolutions, surpassing training resolutions.
Main Tasks
Remove Unwanted Objects
Explore all tools that specialize in remove unwanted objects. This domain focus ensures LaMa Image Inpainting delivers optimized results for this specific requirement.
