Saltar al contenido
ModelPublicadoExterno
Descargar

Lama Onnx

This ONNX model is a port of the original PyTorch big-lama model.

Fuentehuggingface.co/KIM2234/lama_onnx/tree/08a7059f70c6e486493eee3080dd391c34293ae2
TipoOtherVersiónLama fp32Ccalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
198 MB
Versión
vLama fp32
Actualizado
9 oct 2026
Fuente
Hugging Face

Descripción de la fuente

LaMa Inpainting Model

This ONNX model is a port of the original PyTorch big-lama model.

HG Space: https://huggingface.co/spaces/Carve/LaMa-Demo-ONNX

Description

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 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 512x512 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.
  4. Exportable to TensorRT: The model can be successfully used in TensorRT, etc.

if you need other resolution - export it using our jupyter notebook

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

Example

Original image: original image

lama_fp32.onnx - output: onnx output

lama.onnx - output: onnx output

Original model output: original model output

Fuentes

1 fuente
Hugging FacePrincipalVersión 08a7059f70c6e486493eee3080dd391c34293ae2
huggingface.co/KIM2234/lama_onnx/tree/08a7059f70c6e486493eee3080dd391c34293ae2

Verificado 9 oct

Artefactos del modelo

2 artefactos

lama_fp32.onnx

onnx · 198 MB · SHA-256 1faef5301d78…68d6 · Hugging Face

Descargar

lama.onnx

onnx · 198 MB · SHA-256 351e481e287f…d1a1 · Hugging Face

Descargar

Extractos de fuentes

2 extractos
Readme31 julhuggingface.co/KIM2234/lama_onnx

--- license: apache-2.0 language: - en pipeline_tag: image-to-image tags: - art - lama - inpainting --- # LaMa Inpainting Model This ONNX model is a port of the original PyTorch big-lama model. > HG Space: https://huggingface.co/spaces/Carve/LaMa-Demo-ONNX ## Description 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 512x512 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. 4. **Exportable to TensorRT**: The model can be successfully used in TensorRT, etc. > if you need other resolution - export it using our [jupyter notebook](https://colab.research.google.com/github/Carve-Photos/lama/blob/main/export_LaMa_to_onnx.ipynb) ### 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:** ![original image](./image.jpg) **lama_fp32.onnx - output:** ![onnx output](./output_onnx_fp32.png) **lama.onnx - output:** ![onnx output](./output_onnx.png) **Original model output:** ![original model output](./output_orig.png)

Note31 julhuggingface.co/KIM2234/lama_onnx

Source context: 0 downloads · 0 likes · Pipeline image-to-image · Repo KIM2234/lama_onnx