A lightweight Python wrapper for LaMa image inpainting, supporting CPU and GPU inference. Current version 0.1.2, updated irregularly on PyPI.
pip install simple-lama-inpaintingNo compatibility data collected yet for this library.
Verified import paths — ran on the pinned version, not inferred.
Basic usage: load image and mask (both PIL), run inpainting, save result.
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu118 (adjust CUDA version as needed)
Ensure mask is converted to binary (0/255) before passing. Use: mask = mask.point(lambda x: 255 if x > 128 else 0)
Set LAMA_MODEL_PATH=/path/to/big-lama.pt in your environment to use a local model file.