Real-ESRGAN-General-x4v3 is a lightweight image super-resolution model based on the Real-ESRGAN architecture, optimized for mobile devices and edge computing platforms. It can upscale low-resolution images by 4× while effectively removing noise, enhancing image quality. With approximately 1.21 million parameters and a model size of 4.66 MB, it is designed for input resolutions of 128×128 pixels. The model supports various deployment formats, including TFLite and ONNX, enabling efficient inference on NPUs of chips like Qualcomm Snapdragon. It is suitable for applications in virtual reality, augmented reality, gaming, and mobile apps.
Source model
- Input shape: 1x3x128x128
- Number of parameters: 1.16M
- Model size: 4.79M
- Output shape: 1x3x512x512
The source model can be found here
When the user has fine-tuned the source model, the model conversion process must be performed again.
Users can refer to either of the following two methods to complete the model conversion:
Using AIMO for model conversion: Click Model Conversion Reference in the Performance Reference section on the right to view the conversion steps.
Using Qualcomm QNN for model conversion: Please refer to the Qualcomm QNN Documentation.
The model performance benchmarks and example code provided by Model Farm are all implemented based on the AIDLux AidLite SDK.
For models in .bin format, you can use either of the following two inference engines to run inference on Qualcomm chips:
Inference using APLUX AidLite: please refer to the APLUX AidLite Developer Documentation
Inference using Qualcomm QNN: Please refer to the Qualcomm QNN Documentation
Inference Example Code
The inference example code is implemented using the AidLite SDK.
Click Model & Code to download the model files and the inference code package. The file structure is as follows:
/model_farm_{model_name}_aidlite
|__ models # folder where model files are stored
|__ python # aidlite python model inference example
|__ cpp # aidlite cpp model inference example
|__ README.md