---
license: apache-2.0
---
# LaMa Inpainting Model
This is an alpha version of ONNX model ported from original PyTorch big-lama model.

## Notes:
1. We use a custom FourierUnit implementation, as the original cannot be directly ported to ONNX without overhead. The result is not the same, but very close
2. The input shape is fixed to 512x512 pixels.
3. The opset version is 18.
4. The model works slowly due to issues with torch.onnx.dynamo_export with optimization of the onnx model.


Original repo: https://github.com/advimman/lama


## Example
original image
![](./image.jpg)
onnx
![](./output_onnx.png)
original model
![](./output_orig.png)