Hugging Face's logo

qualcomm
/
Real-ESRGAN-x4plus

Image-to-Image
PyTorch
LiteRT
ONNX
android
Model card Files Community
1

Real-ESRGAN-x4plus: Optimized for Mobile Deployment

Upscale images and remove image noise

Real-ESRGAN is a machine learning model that upscales an image with minimal loss in quality. The implementation is a derivative of the Real-ESRGAN-x4plus architecture, a larger and more powerful version compared to the Real-ESRGAN-general-x4v3 architecture.

This model is an implementation of Real-ESRGAN-x4plus found here.

This repository provides scripts to run Real-ESRGAN-x4plus on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Model_use_case.super_resolution
  • Model Stats:
    • Model checkpoint: RealESRGAN_x4plus
    • Input resolution: 128x128
    • Number of parameters: 16.7M
    • Model size (float): 63.9 MB
    • Model size (w8a8): 16.7 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
Real-ESRGAN-x4plus float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 451.259 ms 3 - 173 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 448.627 ms 40 - 171 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 121.58 ms 3 - 165 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 118.279 ms 0 - 144 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 63.369 ms 3 - 43 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 62.583 ms 0 - 42 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 107.178 ms 3 - 171 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 105.295 ms 0 - 130 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float SA7255P ADP Qualcomm® SA7255P TFLITE 451.259 ms 3 - 173 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float SA7255P ADP Qualcomm® SA7255P QNN_DLC 448.627 ms 40 - 171 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 64.835 ms 0 - 69 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 64.491 ms 0 - 43 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float SA8295P ADP Qualcomm® SA8295P TFLITE 114.003 ms 3 - 160 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float SA8295P ADP Qualcomm® SA8295P QNN_DLC 110.91 ms 0 - 141 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 69.529 ms 0 - 73 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 63.591 ms 0 - 44 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float SA8775P ADP Qualcomm® SA8775P TFLITE 107.178 ms 3 - 171 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float SA8775P ADP Qualcomm® SA8775P QNN_DLC 105.295 ms 0 - 130 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 70.901 ms 3 - 38 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 63.334 ms 0 - 43 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 76.056 ms 3 - 107 MB NPU Real-ESRGAN-x4plus.onnx
Real-ESRGAN-x4plus float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 50.224 ms 3 - 178 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 49.404 ms 0 - 131 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 50.329 ms 6 - 210 MB NPU Real-ESRGAN-x4plus.onnx
Real-ESRGAN-x4plus float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 41.632 ms 3 - 203 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 39.627 ms 0 - 126 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 39.083 ms 6 - 136 MB NPU Real-ESRGAN-x4plus.onnx
Real-ESRGAN-x4plus float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 65.22 ms 142 - 142 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 65.666 ms 37 - 37 MB NPU Real-ESRGAN-x4plus.onnx
Real-ESRGAN-x4plus w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 73.985 ms 1 - 180 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 74.901 ms 0 - 202 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 38.067 ms 1 - 186 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 41.68 ms 0 - 194 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 25.017 ms 0 - 36 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 26.932 ms 0 - 42 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 23.797 ms 1 - 180 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 25.458 ms 0 - 202 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 107.221 ms 1 - 258 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 170.45 ms 0 - 160 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 1924.044 ms 0 - 71 MB GPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 73.985 ms 1 - 180 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 74.901 ms 0 - 202 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 24.914 ms 0 - 35 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 26.929 ms 0 - 43 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 43.317 ms 1 - 178 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 37.665 ms 0 - 197 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 23.547 ms 0 - 35 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 26.892 ms 0 - 42 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 23.797 ms 1 - 180 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 25.458 ms 0 - 202 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 23.207 ms 0 - 36 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 27.136 ms 0 - 41 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 32.288 ms 8 - 86 MB NPU Real-ESRGAN-x4plus.onnx
Real-ESRGAN-x4plus w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 17.697 ms 1 - 185 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 18.974 ms 0 - 200 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 22.97 ms 8 - 262 MB NPU Real-ESRGAN-x4plus.onnx
Real-ESRGAN-x4plus w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 17.199 ms 1 - 182 MB NPU Real-ESRGAN-x4plus.tflite
Real-ESRGAN-x4plus w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 17.01 ms 0 - 186 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 19.418 ms 6 - 233 MB NPU Real-ESRGAN-x4plus.onnx
Real-ESRGAN-x4plus w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 31.069 ms 110 - 110 MB NPU Real-ESRGAN-x4plus.dlc
Real-ESRGAN-x4plus w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 34.564 ms 22 - 22 MB NPU Real-ESRGAN-x4plus.onnx

Installation

Install the package via pip:

pip install "qai-hub-models[real-esrgan-x4plus]"

Configure Qualcomm® AI Hub to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub with your Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.

With this API token, you can configure your client to run models on the cloud hosted devices.

qai-hub configure --api_token API_TOKEN

Navigate to docs for more information.

Demo off target

The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input.

python -m qai_hub_models.models.real_esrgan_x4plus.demo

The above demo runs a reference implementation of pre-processing, model inference, and post processing.

NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.real_esrgan_x4plus.demo

Run model on a cloud-hosted device

In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following:

  • Performance check on-device on a cloud-hosted device
  • Downloads compiled assets that can be deployed on-device for Android.
  • Accuracy check between PyTorch and on-device outputs.
python -m qai_hub_models.models.real_esrgan_x4plus.export

Profiling Results
------------------------------------------------------------
Real-ESRGAN-x4plus
Device                          : cs_8275 (ANDROID 14)                  
Runtime                         : TFLITE                                
Estimated inference time (ms)   : 451.3                                 
Estimated peak memory usage (MB): [3, 173]                              
Total # Ops                     : 1025                                  
Compute Unit(s)                 : npu (1025 ops) gpu (0 ops) cpu (0 ops)

How does this work?

This export script leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on-device. Lets go through each step below in detail:

Step 1: Compile model for on-device deployment

To compile a PyTorch model for on-device deployment, we first trace the model in memory using the jit.trace and then call the submit_compile_job API.

import torch

import qai_hub as hub
from qai_hub_models.models.real_esrgan_x4plus import Model

# Load the model
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S24")

# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()

pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])

# Compile model on a specific device
compile_job = hub.submit_compile_job(
    model=pt_model,
    device=device,
    input_specs=torch_model.get_input_spec(),
)

# Get target model to run on-device
target_model = compile_job.get_target_model()

Step 2: Performance profiling on cloud-hosted device

After compiling models from step 1. Models can be profiled model on-device using the target_model. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics.

profile_job = hub.submit_profile_job(
    model=target_model,
    device=device,
)

Step 3: Verify on-device accuracy

To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device.

input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
    model=target_model,
    device=device,
    inputs=input_data,
)
    on_device_output = inference_job.download_output_data()

With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output.

Note: This on-device profiling and inference requires access to Qualcomm® AI Hub. Sign up for access.

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.real_esrgan_x4plus.demo --eval-mode on-device

NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.real_esrgan_x4plus.demo -- --eval-mode on-device

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

  • TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on Real-ESRGAN-x4plus's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of Real-ESRGAN-x4plus can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month
413
Inference Providers NEW
Image-to-Image
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support