Hugging Face's logo

LocalMuseAI
/
coreml-realesrgan-x4plus

Core ML
super-resolution
real-esrgan
image-upscaling
Model card Files
xet
 Community
coreml-realesrgan-x4plus / README.md
Devserhii's picture
Devserhii
Document LocalMuse mirror and include BSD license
4f6c21f verified
preview code
|
Raw
History Blame Contribute Delete
1.34 kB
metadata 
license: bsd-3-clause
tags:
  - coreml
  - super-resolution
  - real-esrgan
  - image-upscaling

LocalMuseAI distribution mirror

This repository mirrors the Core ML artifact originally published by VincentGOURBIN/RealESRGAN-CoreML for use by the LocalMuse iOS app. The model archive is preserved unchanged.

Real-ESRGAN CoreML

CoreML conversion of xinntao/Real-ESRGAN (RealESRGAN_x4plus) for use in macOS/iOS apps.

Model

  • Architecture: RRDBNet (23 RRDB blocks, 64 features, 32 growth channels)
  • Scale: 4x upscaling
  • Precision: Float16
  • Input: (1, 3, 256, 256) — RGB normalized [0, 1]
  • Output: (1, 3, 1024, 1024) — RGB [0, 1]
  • Size: ~33 MB (mlpackage), ~30 MB (zip)
  • Target: macOS 15+

Usage

Download RealESRGAN-x4plus.mlpackage.zip, unzip, then compile:

let compiledURL = try MLModel.compileModel(at: mlpackageURL)
let model = try MLModel(contentsOf: compiledURL)

For images larger than 256x256, use tile-based processing with overlap padding.

License

BSD-3-Clause (same as original Real-ESRGAN)

Credits