1xDeJPG OmniSR model

Meant to remove jpg artifacts. First compression round on the training dataset was 40-95, second round was 80-100.

Example: https://slow.pics/c/70nGEvPR

PS these are non-otf models. otf experiments have not quite done it for me (probably would need more adjusting), but they can be found in the experiments folder and their outputs in the outputs folder: https://drive.google.com/drive/folders/1RRXZCRVqlqU_iaeF-RGUM9UBWtI0HseY?usp=drive_link

DeJPG_OmniSR

1xDeJPG SRFormer light model

Meant to remove jpg artifacts. First compression round on the training dataset was 40-95, second round was 80-100.

onnx conversions in this folder which contains all files: https://drive.google.com/drive/folders/1RRXZCRVqlqU_iaeF-RGUM9UBWtI0HseY

Example: https://slow.pics/c/70nGEvPR

PS these are non-otf models. otf experiments have not quite done it for me (probably would need more adjusting), but they can be found in the experiments folder and their outputs in the outputs folder: https://drive.google.com/drive/folders/1RRXZCRVqlqU_iaeF-RGUM9UBWtI0HseY?usp=drive_link

DeJPG_SRFormer_light

[Link to Github Release](https://github.com/Phhofm/models/releases/tag/1xDeJPG_realplksr_otf)

1xDeJPG_realplksr_otf   
Scale: 1    
Architecture: [RealPLKSR](https://github.com/muslll/neosr/?tab=readme-ov-file#supported-archs)   
Architecture Option: [realplksr](https://github.com/muslll/neosr/blob/master/neosr/archs/realplksr_arch.py)   

Author: Philip Hofmann  
License: CC-BY-0.4  
Purpose: JPEG, Restoration  
Subject: Photography  
Input Type: Images  
Release Date: 09.07.2024  

Dataset: [nomosv2](https://github.com/muslll/neosr/?tab=readme-ov-file#-datasets)  
Dataset Size: 6000  
OTF (on the fly augmentations): Yes  
Pretrained Model: This one used the 60 model as pretrain, while I used [4xNomos2_realplksr_dysample](https://github.com/Phhofm/models/releases/tag/4xNomos2_realplksr_dysample) as a pretrain for the 60 model.  
Iterations: 196'000  
Batch Size: 24  
GT Size: 64  

Description:   
A 1x dejpg model, trained with otf down to jpg 40 in both degradation processes, see the yml config file for details.  
I also release the 1xDeJPG_realplksr_otf_60 model additionally, which had been trained with less jpg compression in comparison, down to 60 in both cases, where the hope was that it could give a bit higher quality on less compressed inputs.  
The 40 model is released as default since it will be able to handle more compressed inputs in general.  
Since these are trained with otf will slightly deblur. Examples here are compressed, and then recompressed, with jpg 40.  

Showcase:  
[Slowpics](https://slow.pics/c/c0Wft9H4)  
[Imgsli](https://imgsli.com/Mjc3NzMw)

1xDeJPG_realplksr_otf

Pretrained model: 1x_DeJpeg_Fatality_01_200000_G.pth

DeJpeg Fatality PlusULTRA!

This model is meant to reduce or eliminate JPEG Compression without making the original images too smooth or killing detail. It manages to do a fairly good job but don't expect overly compressed images to work with this.

Pretrained model: 1xESRGAN + previous attempts

JPEGDestroyer

Pretrained: Trained on Custom (CC0 Textures)

Gallery with sample images: https://drive.google.com/open?id=1HWokMsUwsR_Mw-NOJgc8OdS8mkdIje_C

JPG (00-20%)

Pretrained: Trained on Custom (Photos / Manga)

JPG (20-40%)

JPG (40-60%)

JPG (60-80%)

JPG (80-100%)

Pretrained: Custom JPEG dataset

Model I forgot to release. This doesn't totally remove JPEG artifacts, but it does a decent job at a fast rate. It seemingly does a better job of retaining detail than some other JPEG models. The model is incomplete, I need to train it further on compact rather than ESRGAN. This is just a temporary release

Kim2091 DeJpeg v0

Remove JPEG artifacts from manga without destroying screentone and other details. For 80-50 JPEG Quality

MangaJPEGHQ

Remove JPEG artifacts from manga without destroying screentone and other details. For 95-80 JPEG Quality

MangaJPEGHQPlus

Remove JPEG artifacts from manga without destroying screentone and other details. For 25-5 JPEG Quality

MangaJPEGLQ

Remove JPEG artifacts from manga without destroying screentone and other details. For 60-30 JPEG Quality

MangaJPEGMQ

Model designed exclusively to remove compression artifacts while preserving noise in Manhwa, Manhua, Webtoons etc.

1x Manhwa Null

NMKD Jaywreck3 (Lite)

SaiyaJin DeJpeg

model was created as a compact analog of popular models that delete a screenton in the process of overlaying a new screenton.

Speed(image:1441x2048, video card: 3060 12gb)

  1x_wtp_descreentone_compact: 1.2 sec.

wtp_descreentone_compact

Made to restore screentones and remove compression artifacts in manga images with widths between 650 and 900 pixels (can be more than 900).

2x Manga Ora

Vast improvement over v1 in low frequency detail; moiré and artifacting reduced significantly and less random noise from JPEG artefacts in the input. Also now only works on 1 channel images, so it runs slightly faster on average and resulting images are much smaller but it might not work on some ESRGAN implementations, I personally recommend using chaiNNer. v1 may still be better in some edge cases.

There's also a supplementary 1x model that denoises very low quality LRs and smooths halftones so the image works better with the 4x model. Only trained it to help build the dataset and it's useless for already decent-ish LRs but may help you in some situations.

Architecture	ESRGAN
Scale	1x
Size	32nf12nb
Color Mode	Grayscale
License	CC-BY-NC-SA-4.0 Private use Distribution Modifications Credit required Same License State Changes No Liability & Warranty Disclaimer
Date	2021-06-17
Dataset	Expanded self curated custom manga dataset
Training epochs	23
Training batch size	5
Training HR size	64

MangaJPEGHQPlus

Similar Models