LaMa-Dilated: Optimized for Qualcomm Devices

LaMa-Dilated is a machine learning model that allows to erase and in-paint part of given input image.

This is based on the implementation of LaMa-Dilated found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
ONNX	float	Universal	QAIRT 2.37, ONNX Runtime 1.23.0	Download
QNN_DLC	float	Universal	QAIRT 2.42	Download
TFLITE	float	Universal	QAIRT 2.42, TFLite 2.17.0	Download

For more device-specific assets and performance metrics, visit LaMa-Dilated on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

• Custom weights (e.g., fine-tuned checkpoints)
• Custom input shapes
• Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for LaMa-Dilated on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_editing

Model Stats:

• Model checkpoint: Dilated CelebAHQ
• Input resolution: 512x512
• Number of parameters: 45.6M
• Model size (float): 174 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
LaMa-Dilated	ONNX	float	Snapdragon® X Elite	76.578 ms	90 - 90 MB	NPU
LaMa-Dilated	ONNX	float	Snapdragon® 8 Gen 3 Mobile	53.225 ms	12 - 426 MB	NPU
LaMa-Dilated	ONNX	float	Qualcomm® QCS8550 (Proxy)	76.366 ms	0 - 94 MB	NPU
LaMa-Dilated	ONNX	float	Qualcomm® QCS9075	115.895 ms	6 - 13 MB	NPU
LaMa-Dilated	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	41.157 ms	6 - 345 MB	NPU
LaMa-Dilated	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	32.789 ms	10 - 315 MB	NPU
LaMa-Dilated	QNN_DLC	float	Snapdragon® X Elite	74.997 ms	4 - 4 MB	NPU
LaMa-Dilated	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	52.976 ms	0 - 468 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	402.698 ms	1 - 360 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	75.574 ms	4 - 7 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® SA8775P	495.25 ms	2 - 360 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® QCS9075	119.61 ms	4 - 13 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	135.779 ms	2 - 416 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® SA7255P	402.698 ms	1 - 360 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® SA8295P	113.567 ms	1 - 345 MB	NPU
LaMa-Dilated	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	39.956 ms	1 - 363 MB	NPU
LaMa-Dilated	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	32.369 ms	1 - 385 MB	NPU
LaMa-Dilated	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	52.512 ms	1 - 551 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® QCS8275 (Proxy)	402.766 ms	3 - 376 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® QCS8550 (Proxy)	73.442 ms	3 - 132 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® SA8775P	105.688 ms	0 - 373 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® QCS9075	119.496 ms	1 - 103 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® QCS8450 (Proxy)	137.336 ms	4 - 496 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® SA7255P	402.766 ms	3 - 376 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® SA8295P	109.358 ms	3 - 329 MB	NPU
LaMa-Dilated	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	40.128 ms	0 - 372 MB	NPU
LaMa-Dilated	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	32.395 ms	2 - 405 MB	NPU

License

• The license for the original implementation of LaMa-Dilated can be found here.

References

• Resolution-robust Large Mask Inpainting with Fourier Convolutions
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.