uuliao's picture
|
download
raw
1.61 kB
metadata
license: cc-by-nc-sa-4.0
pipeline_tag: image-to-image
tags:
  - pytorch
  - super-resolution

Name: 4x-UltraSharp (config and presets included!)

License: CC BY-NC-SA 4.0

Link: https://mega.nz/folder/qZRBmaIY#nIG8KyWFcGNTuMX_XNbJ_g

Model Architecture: ESRGAN

Scale: 4

Purpose: Any, it's universal. This model performs best on JPEG compressed images.

Iterations: 150k

batch_size: 4-8

HR_size: 128

Epoch: ~480

Dataset: So many. I used: RAW images shot by myself, SignatureEdits, AdobeMIT-5K, DIV2K, TLOK from brucethemoose, some rock/stone images from ALSA, and many images provided by @esrgan (thanks!)

Dataset_size: uh, ignore this. anywhere between 2k and 8k full size images throughout training

OTF Training Yes (custom augmentation presets)

Pretrained_Model_G: 4x-UniScale-Balanced

Description: This is my best model yet! It generates lots and lots of detail and leaves a nice texture on images. It works on most images, whether compressed or not. It does work best on JPEG compression though, as that's mostly what it was trained on. It has the ability to restore highly compressed images as well!

The model was trained with KernelGAN (thanks musl for supplying the blur kernels), noise patches, custom augmentation presets (are in with the model), and the losses: pixel, feature, cx, ssim, lpips, and fft. Mixup was used for a while, but abandedoned due to stability issues.

Gradient Clipping helped immensely with model stability throughout training.

Big thanks to musl for giving advice on how to further improve the model!

Xet Storage Details

Size:
1.61 kB
·
Xet hash:
dfe84a2a40e0684fe087ead365af3bd733d83775e1b2914453eb95476ec1a85c

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.