Instructions to use ellyxeo/big-lama-512-gpu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use ellyxeo/big-lama-512-gpu with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Big-LaMa 512 for the LiteRT GPU delegate
Big-LaMa (Suvorov et al., "Resolution-robust Large Mask Inpainting with Fourier Convolutions", WACV 2022) as a 512 x 512 LiteRT (TensorFlow Lite) model where every operation runs on the Android GPU delegate.
- Inputs: RGB image
1x512x512x3in 0..1 and erase mask1x512x512x1(exactly 0 or 1; 1 = fill). - Output: RGB
1x512x512x3in 0..255. - Weights are FP32; run with precision loss allowed (FP16) for speed.
Converted from the ONNX export at https://huggingface.co/AUXOUT-TEAM/agit-lama-inpainting (revision 5646fb0bbd8887fac005e0bd3be7047f2211f74b), itself derived from https://huggingface.co/smartywu/big-lama. The Fourier units' DFT matrices are folded for the fixed size, their real/imaginary stacking is rewritten in 4D, and the DFT matrix products are expressed as 1x1 convolutions. Output matches the source ONNX within 1e-4 on the CPU.
License
Apache-2.0, as the original code and weights: https://github.com/advimman/lama
- Downloads last month
- -