You can deploy this model and start earning money today!

qualcomm/
LaMa-Dilated

Name: LaMa-Dilated
Availability: InStock

Views

No views yet

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 2.45, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
LaMa-Dilated	ONNX	float	Snapdragon® X2 Elite	36.287 ms	8 - 8 MB	NPU
LaMa-Dilated	ONNX	float	Snapdragon® X Elite	77.692 ms	91 - 91 MB	NPU
LaMa-Dilated	ONNX	float	Snapdragon® 8 Gen 3 Mobile	54.91 ms	1 - 484 MB	NPU
LaMa-Dilated	ONNX	float	Snapdragon® 8 Gen 1 Mobile	135.49 ms	1 - 528 MB	NPU
LaMa-Dilated	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	123.656 ms	6 - 14 MB	NPU
LaMa-Dilated	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	77.491 ms	0 - 94 MB	NPU
LaMa-Dilated	ONNX	float	Qualcomm® QCS8450	135.49 ms	1 - 528 MB	NPU
LaMa-Dilated	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	108.969 ms	8 - 15 MB	NPU
LaMa-Dilated	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	77.692 ms	91 - 91 MB	NPU
LaMa-Dilated	ONNX	float	Qualcomm® Dragonwing™ Q-8750	43.643 ms	8 - 437 MB	NPU
LaMa-Dilated	ONNX	float	Snapdragon® 8 Elite Mobile	43.643 ms	8 - 437 MB	NPU
LaMa-Dilated	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	34.317 ms	5 - 402 MB	NPU
LaMa-Dilated	QNN_DLC	float	Snapdragon® X2 Elite	34.378 ms	4 - 4 MB	NPU
LaMa-Dilated	QNN_DLC	float	Snapdragon® X Elite	75.423 ms	4 - 4 MB	NPU
LaMa-Dilated	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	53.063 ms	0 - 454 MB	NPU
LaMa-Dilated	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	133.713 ms	2 - 407 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	120.468 ms	4 - 13 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	403.141 ms	1 - 364 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	74.964 ms	4 - 6 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® SA8775P	107.038 ms	1 - 364 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® SA8650P	107.038 ms	1 - 364 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® SA8255P	107.038 ms	1 - 364 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® QCS8450	133.713 ms	2 - 407 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	111.112 ms	4 - 13 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	75.423 ms	4 - 4 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	39.943 ms	1 - 365 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® SA7255P	403.141 ms	1 - 364 MB	NPU
LaMa-Dilated	QNN_DLC	float	Qualcomm® SA8295P	109.482 ms	1 - 300 MB	NPU
LaMa-Dilated	QNN_DLC	float	Snapdragon® 8 Elite Mobile	39.943 ms	1 - 365 MB	NPU
LaMa-Dilated	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	32.372 ms	1 - 392 MB	NPU
LaMa-Dilated	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	52.837 ms	2 - 539 MB	NPU
LaMa-Dilated	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	137.841 ms	4 - 461 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	121.181 ms	3 - 106 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	404.334 ms	3 - 381 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	76.175 ms	3 - 53 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® SA8775P	106.438 ms	3 - 381 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® SA8650P	106.438 ms	3 - 381 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® SA8255P	106.438 ms	3 - 381 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® QCS8450	137.841 ms	4 - 461 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	106.623 ms	2 - 104 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	40.645 ms	2 - 389 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® SA7255P	404.334 ms	3 - 381 MB	NPU
LaMa-Dilated	TFLITE	float	Qualcomm® SA8295P	110.242 ms	3 - 311 MB	NPU
LaMa-Dilated	TFLITE	float	Snapdragon® 8 Elite Mobile	40.645 ms	2 - 389 MB	NPU
LaMa-Dilated	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	32.501 ms	1 - 415 MB	NPU

License

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

References

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.

qualcomm/LaMa-Dilated