Real-ESRGAN-General-x4v3: Super Resolution
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
Performance Reference
Please search model by model name in Model Farm
Inference & Model Conversion
Please search model by model name in Model Farm
License
Source Model: BSD-3-CLAUSE
Deployable Model: APLUX-MODEL-FARM-LICENSE