[Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) aims at developing Practical Algorithms for General Image/Video Restoration.

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
We extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data.

We add small models that are optimized for anime videos :-)

RealESRGANv2 AnimeVideo xs-x2

I've been experimenting a lot since the last descripton was released to save even more detail, and to get rid of some of the beginner's soreness. All three models are not yet perfect and I will develop them, but what is the essence of the three models, the models on omni is just a division of VL eats less large screenton, VH is just a re-trained model on a modified dataset and with VL as a prevoritolnoy shadowing that it would demolish more screenton, while not going to demolish all the textures and very large screenton. Esrgan model was trained on a dataset VH for use in the colab, it works in some places worse than Omni, so could not fight with overlapping screenton.

DWTP_descreenton_H_esrgan

DWTP_descreenton_VH4

DWTP_descreenton_VL4

Cartoons/pixel art/other non-realistic stuff with dithering

FSDedither Manga

Fatality Comix

Fatality Comix MK3

Purpose: Illustrations, digital art, manga covers

Model for color images including manga covers and color illustrations, digital art, visual novel art, artbooks, and more. The DAT2 version is the highest quality version but also the slowest. See the ESRGAN version for faster performance. 

https://slow.pics/c/GfArurPG

IllustrationJaNai_V1_DAT2

Purpose: Illustrations, digital art, manga covers

Model for color images including manga covers and color illustrations, digital art, visual novel art, artbooks, and more. The ESRGAN version is high quality with balanced performance. See the DAT2 version for maximum quality. 

https://slow.pics/c/GfArurPG

IllustrationJaNai_V1_ESRGAN

Upscale Anime while keeping as much of the original detail as possible. Isn't among the sharpest models and if the anime is somewhat blurry it will retain that detail but add more pixels to give a smoother edge. Doesn't change the color very much and may make some scene's very slightly darker.

Pretrained model: Pony Models

Loyaldk Giroro

Loyaldk Keroro

Loyaldk Kororo

Purpose: Art/Anime

Highly flexible 2D Art upscaling

NMKD UltraYandere

A 4x photo upscaler with otf jpg compression, blur and resize, trained on musl's Nomos8k_sfw dataset for realisic sr, this time based on the [DAT arch](https://github.com/zhengchen1999/DAT), as a finetune on the official 4x DAT model.


The 295 MB file is the pth file which can be run with the [dat reo github code](https://github.com/zhengchen1999/DAT). The 85.8 MB file is an onnx conversion.


All Files can be found in [this google drive folder](https://drive.google.com/drive/folders/1b2vQHxlFQrVW22osIhQbDk98sdXzzFkx). If above onnx file is not working, you can try the other conversions in the onnx subfolder.


Examples:

[Imgsli1](https://imgsli.com/MTk4Mjg1) (generated with onnx file)

[Imgsli2](https://imgsli.com/MTk4Mjg2) (generated with onnx file)

[Imgsli](https://imgsli.com/MTk4Mjk5) (generated with testscript of dat repo on the three test images in dataset/single with pth file)

4xNomos8kDAT

4x photo upscaler with otf jpg compression and blur, trained on musl's Nomos8k_sfw dataset for realisic sr. 
Provided is a 16fp onnx (154.1MB) download, and a pth (316.2MB) download.
Since this is a big model, upscaling might take a while.

4xNomos8kSCHAT-L

4x photo upscaler with otf jpg compression and blur, trained on musl's Nomos8k_sfw dataset for realisic sr. 
HAT-S version/model. 
Fp16 Onnx (56.5MB) and pth (77.3MB) file download provided.

4xNomos8kSCHAT-S

4x photo upscaler with otf jpg compression and blur, trained on musl's Nomos8k_sfw dataset for realisic sr. SRFormer base model/version. Provided are onnx fp16 (45.8MB) and pth (185.4MB) downloads.

4xNomos8kSCSRFormer

4x Multipurpose DAT upscaler

Trained on DAT with Adan, U-Net SN, huber pixel loss, huber perceptial loss, vanilla gan loss, huber ldl loss and huber focal-frequency loss, on paired nomos_uni (universal dataset containing photographs, anime, text, maps, music sheets, paintings ..) with added jpg compression 40-100 and down_up, bicubic, bilinear, box, nearest and lanczos scales. No blur degradation had been introduced in the training dataset to keep the model from trying to sharpen blurry backgrounds.

The three strengths of this model (design purpose):
1. Multipurpose
2. Handles bokeh effect
3. Handles jpg compression

This model will not:
- Denoise
- Deblur

4xNomosUniDAT_bokeh_jpg

4x photo upscaler on the SSDIR_Sharp dataset, trained with otf, using the same settings as Real_HAT_GAN.  
These otf values are very high in my opinion. This was an experiment if I used the same settings as Real_HAT_GAN (therefore the name).   
This model will denoise very strongly and smooth out a lot (so a lot of details will be lost. But maybe this effect might be beneficial to someone)

4xReal_SSDIR_DAT_GAN

I just decided to finish off the previous one, made the manga design more clear and corrected the deviation in color temperature by adding a more diverse set of colors

WTP UDS Esrgan

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.

eula digimanga bw v2 nc1

[Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) aims at developing Practical Algorithms for General Image/Video Restoration.

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
We extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data.

We add small models that are optimized for anime videos :-)

We have made the following improvements:
- better naturalness
- Fewer artifacts
- more faithful to the original colors
- better texture restoration
- better background restoration

RealESR AnimeVideo v3

[Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) aims at developing Practical Algorithms for General Image/Video Restoration.

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
We extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data.

This model is optimized for anime images with much smaller model size.

RealESRGAN_x4Plus Anime 6B

RealESRGANv2 AnimeVideo xs-x4

In general, what was the point? The project was conceived for a manga scale with a screentone using the method of superimposing a new screentone, but for this the old screentone must be removed, but this is not all the same important contour. With the screentone overlay method, the contour should be as close to 1 bit as possible, otherwise we will see full contours, wavy contours, etc. This is the whole idealogy of this model.

Architecture	DAT
Scale	4x
Size	mediums64\|8x3264nf180dim2.0ef1conv
Color Mode	RGB
License	CC-BY-NC-SA-4.0 Private use Distribution Modifications Credit required Same License State Changes No Liability & Warranty Disclaimer
Date	2024-02-24
Dataset	digital art, anime
Dataset size	199936
Training iterations	190000
Training batch size	6
Training HR size	256
Training OTF	No

IllustrationJaNai_V1_DAT2

Similar Models