Update README.md

README.md

@@ -2,22 +2,44 @@
 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.
+This ONNX model is a port of the original PyTorch big-lama model.
 
+## Description
 
-Original repo: https://github.com/advimman/lama
+There are two versions of the model:
 
+### 1. `lama_fp32.onnx` (RECOMMENDED)
+
+This version was exported using the old torch to ONNX converter (`torch.onnx.export`).
+
+**Notes:**
+1. **Custom FourierUnitJIT**: A custom [FourierUnitJIT](https://github.com/Carve-Photos/lama/blob/main/saicinpainting/training/modules/ffc.py) implementation is used since the original cannot be directly ported to ONNX without overhead. The result is identical to the original model.
+2. **Fixed Input Shape**: The input shape is fixed at 1024x1024 pixels. Although dynamic input shapes are possible, they would require resolving issues with dynamic padding in the `irfft` and `rfftn` functions in `ffc.py`.
+3. **Opset Version 17**: This model uses opset version 17.
+
+### 2. `lama.onnx` (NOT RECOMMENDED)
+
+This version was exported using the new torch to ONNX converter (`torch.onnx.dynamo_export`).
+
+**Notes:**
+1. **Custom DFT irfftn Logic**: Uses a custom irfftn ONNX logic (patched `onnxscript`).
+2. **Fixed Input Shape**: The input shape is fixed at 512x512 pixels.
+3. **Opset Version 18**: This model uses opset version 18.
+4. **Performance**: The model works slowly due to issues with `torch.onnx.dynamo_export` and optimization of the ONNX model.
+
+## Resources
+
+- Original repository: [advimman/lama](https://github.com/advimman/lama)
+- Repository with custom implementation of exportable LaMa: [Carve-Photos/lama](https://github.com/Carve-Photos/lama)
 
 ## Example
-original image
-![](./image.jpg)
-onnx
-![](./output_onnx.png)
-original model
-![](./output_orig.png)
+
+**Original image:**
+![original image](./image.jpg)
+
+**ONNX output:**
+![onnx output](./output_onnx.png)
+
+**Original model output:**
+![original model output](./output_orig.png)