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)โ RGB normalized [0, 1] - Output:
(1, 3, 1024, 1024)โ 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
- Original model: xinntao/Real-ESRGAN
- Converted for Fluxforge Studio
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support