Purpose: Correct old color photos that are tinted red

Correct old color photos that are tinted red. Model only tested in nature.

RedImage10000

BSWolly

Mixed 3D/2D CGI animations on some 2D animations it might sharpen the edges. General usage is to upscale CGI animations compressed by YouTube.

CGIMaster v1

Interpolation between 4x-UltraSharp and 4x-TextSharp-v0.5. Works amazingly on anime. It also upscales text, but it's far better with anime content. I rebranded this model on 2/10/22 to 4x-AnimeSharp from 4x-TextSharpV1.

Pretrained model: Interpolation between 4x-UltraSharp and 4x-TextSharp-v0.5

AnimeSharp

This model is a lite version of AnimeSharp. It was trained using student-teacher learning (if i'm using the term properly), where the HRs are LRs upscaled by the full size AnimeSharp ESRGAN model, and the lite model is trained on those outputs as the HR. It works best on clean or slightly blurry anime. Downscale by 50% first in almost all cases

AnimeSharp lite

This model is designed to upscale game screenshots (3D Games) by 4 times. The SPSR version is an improvement over the ESRGAN based V2.

BS_ScreenBooster_SPSR

This model is designed to mainly upscale anime artworks.

BooruGan 600k

This model is designed to mainly upscale anime artworks. If you have issues with chroma then try the 600k iterations release.

BooruGan 650k

Purpose: upscale anime from dvd

Anime upscale from dvd with x4, a little softer lines and look but keeps the colors.

https://imgsli.com/MjM3ODEy

Drawimation compact

Images from the Fate/Extra games. Works better on the newer ones.

Just a model I trained quickly to test traiNNer-redux and see what I could do with OTF. Works well enough

FatePlus Compact

4x anime image upscaler with a bit of otf jpg compression and blur. Trained on musl's hfa2k dataset release for Anime SISR, which has been extracted from modern anime films, where the selection criteria was high SNR, no DOF and high frequency information.

Examples: https://imgsli.com/MTc2NDgx (PS Example input images are small, each around 500x280 px) \
Example input files: https://drive.google.com/drive/folders/1RI6gGqRy-KxDujbaIrpEMdvFkIWHvfPt \
Example output files: https://drive.google.com/drive/folders/1GqHwPlFp6bIQl4R1AxmrmJ6vUUD8FUxH \
All my model files can be found on my github repo https://github.com/Phhofm/models

HFA2k

Purpose: 4x anime upscaler handling video compression artifacts, trained for 200 epochs

4x anime upscaler handling video compression artifacts since trained with otf degradations for "mpeg2video", "libxvid", "libx264", "libx265" with crf 20-32, mpeg bitrate 3800-5800 (together with the standard Real-ESRGAN otf pipeline). A faster arch using this otf degradation pipeline would be great for handling video compression artifacts. Since this one is a GRL model and therefore slow, [as noted by the dev](https://github.com/Kiteretsu77/VCISR-official/issues/3) maybe more for research purposes (or more for single images/screenshots). Trained using [VCISR](https://github.com/Kiteretsu77/VCISR-official) for 200 epochs.  

"This is epoch 200 and the start iteration is 85959 with learning rate 2.5e-05"  

Slow Pics examples:  
[h264_crf28](https://slow.pics/c/fqOnxXep)  
[ludvae1](https://slow.pics/c/OcukRy7d)  
[ludvae2](https://slow.pics/c/FI33mX4F)

HFA2k VCISR GRLGAN ep200

[Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xHFA2k_ludvae_realplksr_dysample)

4xHFA2k_ludvae_realplksr_dysample  
Scale: 4  
Architecture: [RealPLKSR with Dysample](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: Restoration  
Subject: Anime  
Input Type: Images  
Release Date: 13.07.2024  

Dataset: HFA2k_LUDVAE  
Dataset Size: 10'272  
OTF (on the fly augmentations): No  
Pretrained Model: [4xNomos2_realplksr_dysample](https://github.com/Phhofm/models/releases/tag/4xNomos2_realplksr_dysample)  
Iterations: 165'000  
Batch Size: 12  
GT Size: 256  

Description:  
A Dysample RealPLKSR 4x upscaling model for anime single-image resolution.  
The dataset has been degraded using DM600_LUDVAE, for more realistic noise/compression. Downscaling algorithms used were imagemagick box, triangle, catrom, lanczos and mitchell. Blurs applied were gaussian, box and lens blur (using chaiNNer). Some images were further compressed using -quality 75-92. Down-up was applied to roughly 10% of the dataset (5 to 15% variation in size). Degradations orders were shuffled, to give as many variations as possible.  

Examples are inferenced with [neosr](https://github.com/muslll/neosr) testscript and the released pth file. I include the test images also as a zip file in this release together with the model outputs, so others can test their models against these test images aswell to compare.  

onnx conversions are  static since dysample doesnt allow dynamic conversion, I tested the conversions with [chaiNNer](https://github.com/chaiNNer-org/chaiNNer).  

Showcase:  
[Slowpics](https://slow.pics/c/FKDZAcyI)

4xHFA2k_ludvae_realplksr_dysample

4x anime super-resolution with real degradation.

4xHFA2kLUDVAEGRL_small

4x lightweight anime upscaler with realistic degradations (compression, noise, blur).

4xHFA2kLUDVAESRFormer_light

4xHFA2kLUDVAESwinIR_light

Purpose: Art/CGI

Upscaler for clean images or images with compression artifacts (jpeg quality >75) - Produces very sharp lines/edges due to NN-Filtered HR images. Proven to produce very, very good results on drawings (sharp lines) and CGI, but should also work pretty well for real-world images.

NMKD PatchySharp

Upscaling and dedithering pre-rendered sprites, images and textures made in the 90s. Basically vintage CGI.

ScreenBooster V2

Upscaling CG-painted anime with variable outlines.

Pretrained model: Manga109v2.pth

WaifuGAN v3

This model is based on a private model by @eula 5600x 3070 named 4x_eula_anifilm_v1_225k. He sent me a copy of the model, and I decided to train a compact model based on it with his permission. This model seems to fix the majority of the issues the original model had while being far faster, it's just a tiny bit softer in some images.

The dataset consists of Dragon Ball movies converted to YUV24 with @sgdisk --zap-all /dev/sda's help to reduce artifacts, then upscaled with ArtClarity and eula_anifilm. LRs are the original frames right from DVD. As a result, this model corrects some color space issues. The 2x model's HRs were downscaled by 50% with Lanczos.

The 2x and 4x models are pretty close in output despite being trained separately. The 2x model is a bit softer overall.

The models in the Real-ESRGAN Compatible folder are the original output from Real-ESRGANs training code for compatibility reasons.

Anifilm Compact (4x)

Anime super-resolution, with real degradation.

animerd v1

This is the first community model using the OmniSR network. I trained it mostly to test this network.\nNote: the model output decreases brightness. This is a well known issue we had with OmniSR.

4x_ardo

Purpose: Anime / Visual Novel Art

Third iteration of my eroge upscaling model. Discriminator: https://drive.google.com/file/d/18q-4ktFNZ8tPjkszuoG6kVBhCjKl8iFa/view?usp=sharing

escale

Upscaling cel animation. Trained this more than a year ago, releasing cause I've got a much better v2 and v3 now.

Architecture	ESRGAN
Scale	4x
Size	64nf23nb
Color Mode	RGB
License	CC-BY-NC-4.0 Private use Distribution Modifications Credit required State Changes No Liability & Warranty Disclaimer
Date	2019-07-12
Dataset size	73
Training iterations	30000
Training batch size	2
Training HR size	128

WaifuGAN v3

Similar Models