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 2.42, ONNX Runtime 1.24.3	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a16	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	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:

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

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 Mobile	58.425 ms	10 - 503 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® X2 Elite	61.634 ms	32 - 32 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® X Elite	149.337 ms	31 - 31 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® 8 Gen 3 Mobile	102.64 ms	11 - 761 MB	NPU
AOT-GAN	ONNX	float	Qualcomm® QCS8550 (Proxy)	144.849 ms	0 - 38 MB	NPU
AOT-GAN	ONNX	float	Qualcomm® QCS9075	226.001 ms	4 - 11 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	77.984 ms	9 - 634 MB	NPU
AOT-GAN	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	35.549 ms	5 - 617 MB	NPU
AOT-GAN	ONNX	w8a16	Snapdragon® X2 Elite	37.856 ms	23 - 23 MB	NPU
AOT-GAN	ONNX	w8a16	Snapdragon® X Elite	85.603 ms	21 - 21 MB	NPU
AOT-GAN	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	61.686 ms	5 - 716 MB	NPU
AOT-GAN	ONNX	w8a16	Qualcomm® QCS6490	13232.214 ms	392 - 396 MB	CPU
AOT-GAN	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	82.235 ms	0 - 25 MB	NPU
AOT-GAN	ONNX	w8a16	Qualcomm® QCS9075	109.501 ms	5 - 8 MB	NPU
AOT-GAN	ONNX	w8a16	Qualcomm® QCM6690	6563.072 ms	327 - 335 MB	CPU
AOT-GAN	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	46.876 ms	5 - 527 MB	NPU
AOT-GAN	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	6613.717 ms	332 - 340 MB	CPU
AOT-GAN	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	47.351 ms	4 - 491 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® X2 Elite	51.722 ms	4 - 4 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® X Elite	122.71 ms	4 - 4 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	89.043 ms	4 - 692 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	543.726 ms	1 - 541 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	121.695 ms	4 - 220 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® SA8775P	162.174 ms	1 - 540 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® QCS9075	214.72 ms	6 - 15 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	199.395 ms	2 - 610 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® SA7255P	543.726 ms	1 - 541 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® SA8295P	179.565 ms	1 - 478 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	69.442 ms	3 - 577 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	35.984 ms	2 - 633 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Snapdragon® X2 Elite	39.017 ms	2 - 2 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Snapdragon® X Elite	85.217 ms	2 - 2 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	62.544 ms	2 - 664 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Qualcomm® QCS6490	298.434 ms	1 - 6 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	188.888 ms	2 - 510 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	82.958 ms	2 - 4 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Qualcomm® SA8775P	82.455 ms	2 - 511 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Qualcomm® QCS9075	110.796 ms	1 - 6 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Qualcomm® QCM6690	1239.876 ms	2 - 673 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	144.001 ms	2 - 660 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Qualcomm® SA7255P	188.888 ms	2 - 510 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Qualcomm® SA8295P	116.051 ms	0 - 509 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	48.801 ms	2 - 567 MB	NPU
AOT-GAN	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	123.265 ms	2 - 667 MB	NPU
AOT-GAN	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	46.72 ms	2 - 506 MB	NPU
AOT-GAN	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	88.89 ms	0 - 721 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® QCS8275 (Proxy)	541.191 ms	3 - 558 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® QCS8550 (Proxy)	116.855 ms	3 - 7 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® SA8775P	161.574 ms	3 - 558 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® QCS9075	210.953 ms	2 - 45 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® QCS8450 (Proxy)	200.608 ms	3 - 633 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® SA7255P	541.191 ms	3 - 558 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® SA8295P	178.63 ms	3 - 493 MB	NPU
AOT-GAN	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	69.172 ms	3 - 596 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.