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 2.42, ONNX Runtime 1.24.1	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ESRGAN	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	28.538 ms	7 - 353 MB	NPU
ESRGAN	ONNX	float	Snapdragon® X2 Elite	34.444 ms	37 - 37 MB	NPU
ESRGAN	ONNX	float	Snapdragon® X Elite	65.508 ms	37 - 37 MB	NPU
ESRGAN	ONNX	float	Snapdragon® 8 Gen 3 Mobile	49.826 ms	7 - 788 MB	NPU
ESRGAN	ONNX	float	Qualcomm® QCS8550 (Proxy)	70.495 ms	0 - 44 MB	NPU
ESRGAN	ONNX	float	Qualcomm® QCS9075	106.789 ms	6 - 9 MB	NPU
ESRGAN	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	38.098 ms	2 - 348 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	16.934 ms	3 - 1057 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® X2 Elite	22.032 ms	29 - 29 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® X Elite	43.59 ms	26 - 26 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	31.864 ms	3 - 1277 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® QCS6490	15432.176 ms	201 - 206 MB	CPU
ESRGAN	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	42.578 ms	0 - 33 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® QCS9075	45.3 ms	3 - 6 MB	NPU
ESRGAN	ONNX	w8a16	Qualcomm® QCM6690	7969.71 ms	183 - 205 MB	CPU
ESRGAN	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	26.4 ms	3 - 906 MB	NPU
ESRGAN	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	7740.946 ms	146 - 165 MB	CPU
ESRGAN	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	26.79 ms	0 - 327 MB	NPU
ESRGAN	QNN_DLC	float	Snapdragon® X2 Elite	34.26 ms	0 - 0 MB	NPU
ESRGAN	QNN_DLC	float	Snapdragon® X Elite	64.939 ms	0 - 0 MB	NPU
ESRGAN	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	49.222 ms	0 - 750 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	451.992 ms	0 - 348 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	63.691 ms	0 - 13 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® SA8775P	503.818 ms	0 - 348 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® QCS9075	106.514 ms	0 - 5 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	124.339 ms	0 - 754 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® SA7255P	451.992 ms	0 - 348 MB	NPU
ESRGAN	QNN_DLC	float	Qualcomm® SA8295P	111.36 ms	0 - 357 MB	NPU
ESRGAN	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	38.175 ms	0 - 333 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	17.147 ms	0 - 985 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® X2 Elite	22.043 ms	0 - 0 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® X Elite	43.159 ms	0 - 0 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	31.434 ms	0 - 1192 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® QCS6490	241.211 ms	0 - 3 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	132.69 ms	0 - 668 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	41.561 ms	0 - 3 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® SA8775P	37.772 ms	0 - 668 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® QCS9075	44.05 ms	0 - 3 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® QCM6690	1138.246 ms	0 - 645 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	77.4 ms	1 - 1275 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® SA7255P	132.69 ms	0 - 668 MB	NPU
ESRGAN	QNN_DLC	w8a16	Qualcomm® SA8295P	64.975 ms	0 - 712 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	28.332 ms	0 - 839 MB	NPU
ESRGAN	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	89.218 ms	0 - 703 MB	NPU
ESRGAN	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	27.777 ms	3 - 371 MB	NPU
ESRGAN	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	48.58 ms	1 - 798 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® QCS8275 (Proxy)	452.045 ms	3 - 391 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® QCS8550 (Proxy)	59.672 ms	3 - 6 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® SA8775P	105.566 ms	3 - 392 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® QCS9075	107.995 ms	3 - 47 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® QCS8450 (Proxy)	118.399 ms	4 - 796 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® SA7255P	452.045 ms	3 - 391 MB	NPU
ESRGAN	TFLITE	float	Qualcomm® SA8295P	111.389 ms	3 - 396 MB	NPU
ESRGAN	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	37.517 ms	3 - 364 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.