ESRGAN: Optimized for Qualcomm Devices

ESRGAN is a machine learning model that upscales an image with minimal loss in quality.

This is based on the implementation of ESRGAN 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
ONNX	w8a16	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	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 ESRGAN 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 ESRGAN on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.super_resolution

Model Stats:

• Input resolution: 128x128
• Model checkpoint: ESRGAN_x4
• Model size (float): 63.9 MB
• Number of parameters: 16.7M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ESRGAN	ONNX	float	Snapdragon® X2 Elite	34.318 ms	8 - 8 MB	NPU
ESRGAN	ONNX	float	Snapdragon® X Elite	65.423 ms	38 - 38 MB	NPU
ESRGAN	ONNX	float	Snapdragon® 8 Gen 3 Mobile	51.062 ms	0 - 745 MB	NPU
ESRGAN	ONNX	float	Snapdragon® 8 Gen 1 Mobile	118.049 ms	4 - 741 MB	NPU
ESRGAN	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	127.563 ms	6 - 10 MB	NPU
ESRGAN	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	63.529 ms	0 - 43 MB	NPU
ESRGAN	ONNX	float	Qualcomm® QCS8450	118.049 ms	4 - 741 MB	NPU
ESRGAN	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	105.926 ms	6 - 9 MB	NPU
ESRGAN	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	65.423 ms	38 - 38 MB	NPU
ESRGAN	ONNX	float	Qualcomm® Dragonwing™ Q-8750	38.69 ms	7 - 358 MB	NPU
ESRGAN	ONNX	float	Snapdragon® 8 Elite Mobile	38.69 ms	7 - 358 MB	NPU
ESRGAN	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	26.12 ms	5 - 361 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® X2 Elite	21.996 ms	4 - 4 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® X Elite	43.397 ms	26 - 26 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	31.981 ms	3 - 1115 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	83.95 ms	4 - 1198 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	323.654 ms	4 - 7 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	43.191 ms	3 - 7 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	41.903 ms	0 - 725 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® QCS8450	83.95 ms	4 - 1198 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	38.006 ms	3 - 6 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	43.397 ms	26 - 26 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	1128.366 ms	0 - 696 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	89.102 ms	3 - 784 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	26.489 ms	3 - 907 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® 8 Elite Mobile	26.489 ms	3 - 907 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	16.934 ms	3 - 1072 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	89.102 ms	3 - 784 MB	NPU
ESRGAN	QNN_DLC	float	Snapdragon® X2 Elite	34.371 ms	0 - 0 MB	NPU
ESRGAN	QNN_DLC	float	Snapdragon® X Elite	65.02 ms	0 - 0 MB	NPU
ESRGAN	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	48.702 ms	0 - 706 MB	NPU
ESRGAN	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	112.305 ms	0 - 709 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	127.079 ms	0 - 6 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	62.121 ms	0 - 4 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® SA8775P	105.485 ms	1 - 351 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® SA8650P	105.485 ms	1 - 351 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® SA8255P	105.485 ms	1 - 351 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® QCS8450	112.305 ms	0 - 709 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	105.513 ms	0 - 5 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	65.02 ms	0 - 0 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	37.969 ms	0 - 332 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® SA7255P	452.028 ms	1 - 352 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® SA8295P	111.356 ms	0 - 358 MB	NPU
ESRGAN	QNN_DLC	float	Snapdragon® 8 Elite Mobile	37.969 ms	0 - 332 MB	NPU
ESRGAN	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	25.47 ms	0 - 334 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® X2 Elite	21.845 ms	0 - 0 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® X Elite	43.152 ms	0 - 0 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	31.436 ms	0 - 1030 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	89.46 ms	0 - 1114 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	320.624 ms	0 - 3 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	42.732 ms	0 - 4 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	41.399 ms	0 - 3 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® SA8775P	37.636 ms	0 - 667 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® SA8650P	37.636 ms	0 - 667 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® SA8255P	37.636 ms	0 - 667 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® QCS8450	89.46 ms	0 - 1114 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	37.347 ms	0 - 3 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	43.152 ms	0 - 0 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	1125.268 ms	0 - 621 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	87.728 ms	2 - 710 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	28.284 ms	0 - 837 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® SA7255P	132.81 ms	0 - 666 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® SA8295P	68.189 ms	0 - 713 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	28.284 ms	0 - 837 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	16.427 ms	0 - 995 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	87.728 ms	2 - 710 MB	NPU
ESRGAN	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	49.895 ms	3 - 750 MB	NPU
ESRGAN	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	114.837 ms	2 - 743 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	126.871 ms	3 - 46 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	63.901 ms	3 - 6 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® SA8775P	105.574 ms	0 - 391 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® SA8650P	105.574 ms	0 - 391 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® SA8255P	105.574 ms	0 - 391 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® QCS8450	114.837 ms	2 - 743 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	105.353 ms	3 - 46 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	37.53 ms	3 - 374 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® SA7255P	452.042 ms	4 - 396 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® SA8295P	111.359 ms	3 - 392 MB	NPU
ESRGAN	TFLITE	float	Snapdragon® 8 Elite Mobile	37.53 ms	3 - 374 MB	NPU
ESRGAN	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	25.558 ms	3 - 375 MB	NPU

License

• The license for the original implementation of ESRGAN can be found here.

References

• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• 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.