AOT-GAN: Optimized for Qualcomm Devices

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

This is based on the implementation of AOT-GAN 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 2.50, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download

For more device-specific assets and performance metrics, visit AOT-GAN 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 AOT-GAN on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_editing

Model Stats:

• Input resolution: 512x512
• Model checkpoint: CelebAHQ
• Model size (float): 58.0 MB
• Number of parameters: 15.2M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
AOT-GAN	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	44.543 ms	5 - 466 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	69.497 ms	6 - 542 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® X2 Elite	47.777 ms	8 - 8 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® X Elite	124.281 ms	32 - 32 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® 8 Gen 3 Mobile	87.669 ms	0 - 642 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® 8 Gen 1 Mobile	180.78 ms	1 - 578 MB	NPU
AOT-GAN	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	176.574 ms	4 - 12 MB	NPU
AOT-GAN	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	120.926 ms	10 - 13 MB	NPU
AOT-GAN	ONNX	float	Qualcomm® QCS8450	180.78 ms	1 - 578 MB	NPU
AOT-GAN	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	161.989 ms	4 - 11 MB	NPU
AOT-GAN	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	124.281 ms	32 - 32 MB	NPU
AOT-GAN	ONNX	float	Qualcomm® Dragonwing™ Q-8750	69.497 ms	6 - 542 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	44.855 ms	3 - 455 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	66.711 ms	0 - 531 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® X2 Elite	46.023 ms	4 - 4 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® X Elite	119.313 ms	4 - 4 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	85.324 ms	0 - 648 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	181.046 ms	3 - 574 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	173.081 ms	4 - 14 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	117.168 ms	4 - 7 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® SA8650P	161.352 ms	1 - 542 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® SA8255P	161.352 ms	1 - 542 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® QCS8450	181.046 ms	3 - 574 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	157.394 ms	4 - 13 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	119.313 ms	4 - 4 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	66.711 ms	0 - 531 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® SA8295P	181.082 ms	1 - 440 MB	NPU
AOT-GAN	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	44.535 ms	2 - 467 MB	NPU
AOT-GAN	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	67.38 ms	3 - 542 MB	NPU
AOT-GAN	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	86.13 ms	2 - 677 MB	NPU
AOT-GAN	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	181.151 ms	3 - 607 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	173.246 ms	3 - 48 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	118.526 ms	0 - 3 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® SA8650P	161.524 ms	3 - 558 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® SA8255P	161.524 ms	3 - 558 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® QCS8450	181.151 ms	3 - 607 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	157.334 ms	2 - 46 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	67.38 ms	3 - 542 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® SA8295P	181.8 ms	3 - 457 MB	NPU

License

• The license for the original implementation of AOT-GAN can be found here.

References

• Aggregated Contextual Transformations for High-Resolution Image Inpainting
• 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.