DitherDeleter Smooth

Attempts to remove the damages done by dithering. For this model, I downscaled all of the HR images to make their pixel size closer to 1000x1000 using the Box filter and then downscaled them again by 50% using the Point filter. Afterwards, I applied 32-bit Riemersma to every image in the dataset.

https://imgsli.com/NTA5MjU/0/1

DitherDeleterV3 Smooth

DeGif

Category: Art/Pixel Art
Purpose: Digital Art/People
Pretrained: Mainly for digital art, but can be used to upscale pixel art.

ArtStation1337 Dedither

ArtStation1337 Dedither v2

Nice to release a model again! This one is intended for realistic imagery, and works especially well on faces, hair, and nature shots. It should only be used on somewhat clear shots, without a lot of grain. I trained this model on SPAN, which as of the time of release, you'll need chaiNNer-nightly for. I aimed for a softer, more natural look for this model with as few artifacts as possible.

In addition to the Normal model, I've included a "soft" model. The Soft model is... softer. Basically it was an earlier version of the model with a more limited dataset. It produces more natural output on games or rendered content, but suffers a bit more with realistic stuff.

Note: In shots with DOF (depth of field) or bokeh, unfortunately there will be artifacts. 

Compatibility: You'll have to use the latest chaiNNer-nightly to use this model

ClearRealityV1

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

For photos/realistic images, but worth trying on other images that have reduced colors and dithering along with fine details. Trained using the ESRGAN-FS code (https://github.com/ManuelFritsche/real-world-sr/tree/master/esrgan-fs/codes) for better details compared to plain ESRGAN.

FSDedither

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

FSDedither Manga

Fine-tuned 4xFSDedither to upscale images from the game Riven, but should be better in general, particularly on ordered dithering. I adjusted the dataset to have a better variety of dithering parameters, and turned up the HFEN and pixel loss to get better details and color restoration with less noise.

FSDedither Riven

Manga-style images with or without dithering - cartoons, maybe pixel art, etc

FSMangaV2

Category: Art/Pixel Art
Purpose: Pixel Art/Sprites

Upscales medium resolution Sprites, dithered or undithered, can also upscale manga/anime and gameboy camera images.

Fatality 1

Purpose: Anime PSP games, Fate Extra

This model was trained as a favor to Demon and the Fate Extra community. It leaves a nice grain on the images and upscales lines and details accurately without looking odd. This model works on most anime-style PSP games. Enjoy! It works best on content with dithering and quantization. NOTICE: I have included both NCNN and ONNX models to make upscaling easier if you rely on either of these. For NCNN, there's two versions. One is FP16 and the other is FP32. FP16 works best on RTX GPUs. Choose FP32 if in doubt about compatibility, or if FP16 doesn't work for you. To use ONNX, download chaiNNer and upscale through there with the ONNX nodes.

FatePlus-lite

Photos/realistic 3D with JPEG compression, quality 85-95 and 4:2:0 chroma subsampling. - Created for Myst3 images, since all have 4:2:0 chroma subsampling and existing JPEG models did not give good results. Favors smoothing over over-sharpening.

Jaypeg90

A universal model, that is aimed at prerendered images, but handles realistic faces, manga, pixel art and dedithering as well. Trained using the patchgan discriminator, with cx loss, cutmixup and frequency separation, it produces good results with a slight grain due to patchgan, with some sharpening using cutmixup.

Lollypop

Purpose: Art/Anime

Highly flexible 2D Art upscaling

NMKD UltraYandere

PBRify Github: https://github.com/Kim2091/PBRify_Remix

Release Link: https://github.com/Kim2091/Kim2091-Models/releases/tag/4x-PBRify_RPLKSRd_V3

This update brings a new upscaling model, 4x-PBRify_RPLKSRd_V3. This model is roughly 8x faster than the current DAT2 model, while being *higher quality*. It produces far more natural detail, resolves lines and edges more smoothly, and cleans up compression artifacts better.

As a result of those improvements, PBR is also much improved. It tends to be clearer with less defined artifacts. 

However, this model is currently **only compatible with ComfyUI**. chaiNNer has not yet been updated to support this architecture.

[More Comparisons](https://imgsli.com/Mjk5NjQ5)

4x-PBRify_RPLKSRd_V3

This is part of my [PBRify_Remix](<https://github.com/Kim2091/PBRify_Remix>) project. This is a much more capable model based on SwinIR Medium, which should strike a balance between capacity for learning + inference speed. It appears to have done so :)

### Replaced by 4x-PBRify_UpscalerDAT2_V1

4x-PBRify_UpscalerSIR-M_V2

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

## 4xTextures_GTAV_rgt-s_dither

**Scale:** 4  
**Architecture:** [RGT](https://github.com/zhengchen1999/RGT)  
**Architecture Option:** RGT-S  

**Author:** Philip Hofmann  
**License:** CC-BY-0.4  
**Purpose:** Restoration  
**Subject:** Game Textures  
**Input Type:** Images  
**Release Date:** 08.05.2024  

**Dataset:** [GTAV_512_Textures](https://discord.com/channels/547949405949657098/905446120333930566/1132367991808466975)  
**Dataset Size:** 7061  
**OTF (on the fly augmentations):** No  
**Pretrained Model:** 4xTextures_GTAV_rgt-s  
**Iterations:** 128'000  
**Batch Size:** 6,4  
**GT Size:** 128,256  

**Description:**
A model to upscale game textures, trained on GTAV Textures, handles jpg compression down to 80 and was trained with dithering. Basically the previous 4xTextures_GTAV_rgt-s model but extended to handle dithering.

**Showcase:**  
[Slow Pics 25 Examples](https://slow.pics/s/EW7Ifiuw)

4xTextures_GTAV_rgt-s_dither

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

Category: Art/Pixel Art

xbrz plus dedithering style pixel-art upscaling model to wiki under specialised

xbrz+dd

Category: Art/Pixel Art

Low-resolution MS Paint drawings, general pixel art, and general dithered pixel art, all kinds of pixel art

Pretrained model: A mix of: 8x_glasshopper_ArzenalV1.1, 8x_glasshopper_MS-Unpainter, 8x_NMKD-Sphax + Sphax de-dither, and 8x_NMKD-YanderePixelArt4 + Yandere De-Dither, all interpolated with adjustments using the interpolate function in Cupscale

Architecture	ESRGAN
Scale	4x
Size	64nf23nb
Color Mode	RGB
License	GPL-3.0-only Private use Commercial use Distribution Modifications Credit required Same License State Changes No Liability & Warranty Disclaimer
Date	2020-01-29
Dataset	Div2K+Flickr2K, linearly downscaled and dithered (half Floyd-Steinberg, half ordered) using GIMP
Dataset size	3450
Training iterations	55000
Training batch size	16
Training HR size	128

FSDedither

Similar Models