Hugging Face's logo

qualcomm
/
NAFNet-DeNoise

Image-to-Image
PyTorch
android
Model card Files
xet
 Community

NAFNet-DeNoise: Optimized for Qualcomm Devices

NAFNET is designed for lightweight real-time denoising of images.

This is based on the implementation of NAFNet-DeNoise 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 NAFNet-DeNoise 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 NAFNet-DeNoise on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_editing

Model Stats:

  • Input resolution: 256x256
  • Model checkpoint: NAFNet-SIDD-width64
  • Model size (float): 463.93 MB
  • Number of parameters: 115.98M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
NAFNet-DeNoise ONNX float Snapdragon® X2 Elite 14.842 ms 4 - 4 MB NPU
NAFNet-DeNoise ONNX float Snapdragon® X Elite 33.857 ms 228 - 228 MB NPU
NAFNet-DeNoise ONNX float Snapdragon® 8 Gen 3 Mobile 27.869 ms 0 - 849 MB NPU
NAFNet-DeNoise ONNX float Snapdragon® 8 Gen 1 Mobile 62.127 ms 3 - 722 MB NPU
NAFNet-DeNoise ONNX float Qualcomm® Dragonwing™ IQ-8275 45.407 ms 2 - 6 MB NPU
NAFNet-DeNoise ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 35.341 ms 0 - 258 MB NPU
NAFNet-DeNoise ONNX float Qualcomm® QCS8450 62.127 ms 3 - 722 MB NPU
NAFNet-DeNoise ONNX float Qualcomm® Dragonwing™ IQ-9075 42.418 ms 2 - 5 MB NPU
NAFNet-DeNoise ONNX float Qualcomm® Dragonwing™ IQ-X7181 33.857 ms 228 - 228 MB NPU
NAFNet-DeNoise ONNX float Qualcomm® Dragonwing™ Q-8750 19.378 ms 2 - 500 MB NPU
NAFNet-DeNoise ONNX float Snapdragon® 8 Elite Mobile 19.378 ms 2 - 500 MB NPU
NAFNet-DeNoise ONNX float Snapdragon® 8 Elite Gen 5 Mobile 14.477 ms 0 - 536 MB NPU
NAFNet-DeNoise ONNX w8a16 Snapdragon® X2 Elite 11.782 ms 1 - 1 MB NPU
NAFNet-DeNoise ONNX w8a16 Snapdragon® X Elite 28.499 ms 118 - 118 MB NPU
NAFNet-DeNoise ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 21.054 ms 0 - 593 MB NPU
NAFNet-DeNoise ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 45.154 ms 1 - 611 MB NPU
NAFNet-DeNoise ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 132.698 ms 1 - 4 MB NPU
NAFNet-DeNoise ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 26.694 ms 1 - 5 MB NPU
NAFNet-DeNoise ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 28.342 ms 0 - 156 MB NPU
NAFNet-DeNoise ONNX w8a16 Qualcomm® QCS8450 45.154 ms 1 - 611 MB NPU
NAFNet-DeNoise ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 27.727 ms 1 - 4 MB NPU
NAFNet-DeNoise ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 28.499 ms 118 - 118 MB NPU
NAFNet-DeNoise ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 261.694 ms 1 - 871 MB NPU
NAFNet-DeNoise ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 33.143 ms 1 - 588 MB NPU
NAFNet-DeNoise ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 16.349 ms 1 - 470 MB NPU
NAFNet-DeNoise ONNX w8a16 Snapdragon® 8 Elite Mobile 16.349 ms 1 - 470 MB NPU
NAFNet-DeNoise ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 11.235 ms 0 - 543 MB NPU
NAFNet-DeNoise ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 33.143 ms 1 - 588 MB NPU
NAFNet-DeNoise QNN_DLC float Snapdragon® X2 Elite 15.722 ms 1 - 1 MB NPU
NAFNet-DeNoise QNN_DLC float Snapdragon® X Elite 35.788 ms 1 - 1 MB NPU
NAFNet-DeNoise QNN_DLC float Snapdragon® 8 Gen 3 Mobile 28.756 ms 0 - 888 MB NPU
NAFNet-DeNoise QNN_DLC float Snapdragon® 8 Gen 1 Mobile 61.188 ms 0 - 729 MB NPU
NAFNet-DeNoise QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 47.67 ms 1 - 5 MB NPU
NAFNet-DeNoise QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 37.986 ms 1 - 3 MB NPU
NAFNet-DeNoise QNN_DLC float Qualcomm® SA8775P 43.513 ms 1 - 558 MB NPU
NAFNet-DeNoise QNN_DLC float Qualcomm® SA8650P 43.513 ms 1 - 558 MB NPU
NAFNet-DeNoise QNN_DLC float Qualcomm® SA8255P 43.513 ms 1 - 558 MB NPU
NAFNet-DeNoise QNN_DLC float Qualcomm® QCS8450 61.188 ms 0 - 729 MB NPU
NAFNet-DeNoise QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 43.728 ms 1 - 4 MB NPU
NAFNet-DeNoise QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 35.788 ms 1 - 1 MB NPU
NAFNet-DeNoise QNN_DLC float Qualcomm® Dragonwing™ Q-8750 20.528 ms 1 - 544 MB NPU
NAFNet-DeNoise QNN_DLC float Qualcomm® SA7255P 136.146 ms 1 - 546 MB NPU
NAFNet-DeNoise QNN_DLC float Qualcomm® SA8295P 48.022 ms 1 - 399 MB NPU
NAFNet-DeNoise QNN_DLC float Snapdragon® 8 Elite Mobile 20.528 ms 1 - 544 MB NPU
NAFNet-DeNoise QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 14.719 ms 0 - 621 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Snapdragon® X2 Elite 13.292 ms 0 - 0 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Snapdragon® X Elite 28.803 ms 0 - 0 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 21.15 ms 0 - 582 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 46.055 ms 0 - 593 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 129.853 ms 0 - 3 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 26.903 ms 0 - 4 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 28.255 ms 1 - 3 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® SA8775P 28.06 ms 1 - 477 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® SA8650P 28.06 ms 1 - 477 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® SA8255P 28.06 ms 1 - 477 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® QCS8450 46.055 ms 0 - 593 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 28.218 ms 0 - 3 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 28.803 ms 0 - 0 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 395.731 ms 1 - 919 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 48.182 ms 0 - 631 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 16.028 ms 0 - 478 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® SA7255P 57.57 ms 1 - 476 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Qualcomm® SA8295P 36.901 ms 1 - 474 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 16.028 ms 0 - 478 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 11.472 ms 0 - 520 MB NPU
NAFNet-DeNoise QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 48.182 ms 0 - 631 MB NPU
NAFNet-DeNoise TFLITE float Snapdragon® 8 Gen 3 Mobile 28.441 ms 0 - 1120 MB NPU
NAFNet-DeNoise TFLITE float Snapdragon® 8 Gen 1 Mobile 65.428 ms 1 - 961 MB NPU
NAFNet-DeNoise TFLITE float Qualcomm® Dragonwing™ IQ-8275 47.946 ms 1 - 234 MB NPU
NAFNet-DeNoise TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 37.239 ms 1 - 5 MB NPU
NAFNet-DeNoise TFLITE float Qualcomm® SA8775P 43.697 ms 1 - 777 MB NPU
NAFNet-DeNoise TFLITE float Qualcomm® SA8650P 43.697 ms 1 - 777 MB NPU
NAFNet-DeNoise TFLITE float Qualcomm® SA8255P 43.697 ms 1 - 777 MB NPU
NAFNet-DeNoise TFLITE float Qualcomm® QCS8450 65.428 ms 1 - 961 MB NPU
NAFNet-DeNoise TFLITE float Qualcomm® Dragonwing™ IQ-9075 44.153 ms 1 - 233 MB NPU
NAFNet-DeNoise TFLITE float Qualcomm® Dragonwing™ Q-8750 20.409 ms 1 - 764 MB NPU
NAFNet-DeNoise TFLITE float Qualcomm® SA7255P 136.591 ms 1 - 764 MB NPU
NAFNet-DeNoise TFLITE float Qualcomm® SA8295P 50.844 ms 1 - 629 MB NPU
NAFNet-DeNoise TFLITE float Snapdragon® 8 Elite Mobile 20.409 ms 1 - 764 MB NPU
NAFNet-DeNoise TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 14.813 ms 1 - 849 MB NPU

License

  • The license for the original implementation of NAFNet-DeNoise can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image-to-Image
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/NAFNet-DeNoise