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 1.25.0	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 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	53.871 ms	10 - 500 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® X2 Elite	57.047 ms	208 - 208 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® 8 Gen 3 Mobile	94.377 ms	11 - 759 MB	NPU
AOT-GAN	ONNX	float	Qualcomm® QCS8550 (Proxy)	134.407 ms	4 - 72 MB	NPU
AOT-GAN	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	75.225 ms	7 - 614 MB	NPU
AOT-GAN	ONNX	float	Qualcomm® QCS9075	208.083 ms	4 - 49 MB	NPU
AOT-GAN	ONNX	float	Qualcomm® QCS8750	75.225 ms	7 - 614 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	47.592 ms	3 - 484 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® X2 Elite	50.894 ms	4 - 4 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® X Elite	122.23 ms	4 - 4 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	88.73 ms	0 - 689 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® QCS8275	541.007 ms	1 - 543 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	121.545 ms	4 - 366 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® SA8775P	161.342 ms	1 - 543 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® SA8650P	161.342 ms	1 - 543 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® SA8255P	161.342 ms	1 - 543 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	197.982 ms	2 - 606 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® SA7255P	541.007 ms	1 - 543 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® SA8295P	178.726 ms	0 - 475 MB	NPU
AOT-GAN	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	69.984 ms	1 - 572 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® QCS9075	210.987 ms	4 - 13 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® QCS8750	69.984 ms	1 - 572 MB	NPU
AOT-GAN	QNN_DLC	float	Qualcomm® QCS7181	122.23 ms	4 - 4 MB	NPU
AOT-GAN	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	46.636 ms	2 - 508 MB	NPU
AOT-GAN	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	88.378 ms	3 - 726 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® QCS8275	541.281 ms	3 - 557 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® QCS8550 (Proxy)	121.957 ms	3 - 55 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® SA8775P	161.556 ms	3 - 557 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® SA8650P	161.556 ms	3 - 557 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® SA8255P	161.556 ms	3 - 557 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® QCS8450 (Proxy)	200.99 ms	3 - 637 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® SA7255P	541.281 ms	3 - 557 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® SA8295P	178.654 ms	4 - 494 MB	NPU
AOT-GAN	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	69.538 ms	3 - 591 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® QCS9075	210.986 ms	2 - 45 MB	NPU
AOT-GAN	TFLITE	float	Qualcomm® QCS8750	69.538 ms	3 - 591 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.