16xESRGAN

Pretrained: RRDB_PSNR_x4.pth

The original RRDB_PSNR_x4.pth model converted to 1x, 2x, 8x and 16x scales, intended to be used as pretrained models for new models at those scales. These are compatible with victor's 4xESRGAN.pth conversions

16x PSNR Pretrained Model

Category: Anime and Cartoon Restoration
Purpose: Animation

This model corrects jagged lines on animation that has been deinterlaced. It handles simple line doubling, line interpolation, and even Yadif-style artifacts. It can also handle sources that were resized after deinterlacing, for example resizing from ntsc to pal resolutions. If a source has been upscaled after deinterlacing, it will need to be downsized before applying this model.

AnimeUndeint Compact

Purpose: Anti aliasing / Images with pixelated edges

Anti Aliasing

Pretrained: 4xPSNR

Texture retaining denoiser and sharpener for digital artwork

Sample images: https://1drv.ms/u/s!Aip-EMByJHY28xKFp93VIGydNsoN?e=vN2WYh

ArtClarity

A model to help remove compression artifacts in BC1-BC3/DXT1-DXT5 compressed images (these all have color encoded the same way)

BC1 Smooth 2

BCGone Detailed

BCGone Detailed V2 40-60

Attempts to remove the damages done by BC1 compression.

BCGone Smooth

B/W | 100% Desaturated images. It mostly results in Blue and Yellow images with slight hints of Green, Orange and Magenta. You are free to use this as a pretrain to achieve better results.

BS_Colorizer/Vapourizer

Category: Luminance/Chroma
Purpose: Sharpen

ChromaSharpen - makes the colors slightly more vibrant with a sideeffect of possibly adding Chromatic Abberation to the image. I am not sure about the usage of this model on real case scenarios but anything blurry or with fuzzy colors could work

BSChroma

Category: Luminance/Chroma
Purpose: Luma

Fix Luminance issues?? LumaSharpen ESRGAN Edition? - This model mostly does what "Lumasharpen" algorithms do. It may help fixing images with Luminance images issues? Like old DVD rips? I am not sure, didn't test.

BSLuma

Category: VHS Tapes
Purpose: VHS

Fixing minor VHS Chroma and Pattern Noise - NOTE: only works on deinterlaced sources

BaldrickVHSFix V0.2

Attempts to remove the damages done by color banding. 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 64-bit color banding to every image in the dataset.

Comparisons with other models: https://imgsli.com/NTA1NTk

Bandage Smooth

Category: Anime and Cartoon Restoration
Purpose: Animation

This model helps repair color bleed and heavy chroma noise that may be present on some older footage, particularly that which was recorded on VHS. It also cleans up rainbows if they are present.

BleedOut Compact

Purpose: Animation

Improvement of low-quality cartoons from broadcast sources.
Will greatly increase the visual quality of bad broadcast tape sources of '80s and '90s cartoons (e.g. Garfield and Friends, Heathcliff, DuckTales, etc). Directly addresses chroma blur, dot crawl, and rainbowing. You're highly advised to take care of haloing beforehand in your favorite video editor as the model will not fix it and may make existing halos more noticeable.

BroadcastToStudio Lite

This is a collection of pretrained models for Real-ESRGAN's Compact architecture. There are 1x, 2x, and 4x models, as well as 1x and 2x "UltraCompact" and "SuperUltraCompact" models (think of these as the equivalent to ESRGAN "lite" models). By using these are pretrains for your models, you can ensure that your models are able to be interpolated with other Compact models that were trained from these. These pretrains are compatible with most existing compact models.

Compact Pretrain

To retain details while removing artifacts caused by dxt compression on textures

DEDXT

Attempts to remove PVRTC compression artifacts. If 1x_DEPVR is unable to remove some artifacts you should use the other version but it can't remove color artifacts properly so you should overlay color of normal version to it.

DEPVR

DEPVR Artifact

Create realistic noise and compression artifacts on images. This is meant to synthesize paired dataset for SISR training.

DM600_LUDVAE

Removing compression artifacts from DXT1 compressed textures. This model was created to remove DXT1 compression artifacts from textures imported into the Source Engine. Compressed textures in the engine sometimes have a green-tint which this model also corrects. The data for this model contained a good mix of diffuse textures and normal maps which means this model is pretty good at removing compression from normals as well. Creating this model was a real learning experience for me and I hope someone finds a good use for it.

DXTDecompressor Source V3

Category: Video Game Textures

This model is made for Source Engine textures. It tries to remove compression artifacts such as blockyness, discoloration, green tint. It does pretty well on a lot of things, realistic stuff as well, but it was mostly made to work on TF2 textures. It's made to keep as much detail as possible, without any unnecessary denoising/sharpening. Huge thanks to Twittman for assisting me along this journey.

DXTless SourceEngine

DeBLR

Category: Video Compression
Purpose: Compression

This model was trained on lossless video frames of Metal Arms: Glitch in the System, compressed with Bink V1 for the LR frames. It's a lot more efficient than my first DeBink model, and also has less artifacts. It's not quite as robust, but the compression is barely noticeable in videos after processing with this.

Sample video: https://cdn.discordapp.com/attachments/903415274521374750/904129653374078976/XB_Demo_Mov-85600_G.mp4

DeBink Lite

Category: Video Compression
Purpose: Compression

This model removes early 2000s Bink and other compression artifacts. Works well on almost any image or video compression type.

DeBink v4

DeBink v5

DeBink v6

Halo Removal + edge removal. This model softens edges without blurring other parts of the image.

Comparison and use case: https://imgsli.com/MjgxMDU

DeEdge

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

Pretrained model: 1x_DeJpeg_Fatality_01_200000_G.pth

DeJpeg Fatality PlusULTRA!

Category: Video Compression
Purpose: Compression

Incomplete lite model to remove ROQ compression

DeRoqBeta-lite

Category: Oversharpening
Purpose: Denoise
Pretrained: 1st attempt on random sharpening with the same dataset at 200000 iterations, which was trained on non-random desharp model, total ~600000 iterations on 3 models.

Made for rare particular cases when the image was destroyed by applying noise, i.e. game textures or any badly exported photos. If your image does not have any oversharpening, it won't hurt them, leaving as is. In theory, this model knows when to activate and when to skip, also can successfully remove artifacts if only some parts of the image are oversharpened, for example in image consisting of several combined images, 1 of them with sharpen noise.

DeSharpen

Debandurh_FS Ultra-lite

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

Category: Anime and Cartoon Restoration
Purpose: Animation

Wipes out dot crawl and rainbows in animation.

Dotzilla Compact

Category: DeToon
Purpose: Detooning

An attempt to detoon images/drawings of people

DoubleDetoon

1xESRGAN

Category: Anime and Cartoons
Purpose: Anime or Text

This model is far from perfect, but it does a decent job on removing dot crawl and dehalo\deblock old anime at fast rate without removing many details. chaining it with models like 2x-anifilm-compact or 2xLD-ANIME or 2x_AnimeClassics_UltraLite_510K will give good results i think.

Epsilon-one compact

Pretrained model: 1x_DeJpeg_Fatality_01_175000_G.pth

Fatality DeBlur

Film-Degrainer_1-000

Category: Video Compression
Purpose: artifact

This model attempts to make films upscaled to 4K with Topaz Gaia-HQ look more natural and filmic. It sharpens, adds film grain, and smooths out small artefacts from the upscaling process. I recommend adding a tiny amount of grain to the input to seed the model (you can do this in VEAI), otherwise the film grain will remain static across frames that don't move much. Pretrain model used with permission to relicense from Twittman.

Filmify4K v2

These models deblur most images. It was trained mostly on aniso2 and iso blurring (BSRGAN augmentation) with some gaussian mixed in. It performs well on most blurry images, but I'd recommend using something like Fatality_Deblur for very strong gaussian blur.

Focus

Focus Moderate

Category: Normal Map/Bump Map Generation
Purpose: Map Generation - roughness and displacement maps

This model generates "Franken Maps" (named after Frankenstein), which is a custom material map combination I made. Basically, the Red channel of RGB is just the texture converted to grayscale, the Green channel is the roughness map, and the Blue channel is the displacement map. I had to do this to get around the current limitation of CX loss where it requires a 3 channel output (otherwise I would have just made a 2 channel model, or separate single channel models). As of right now the channels need to be manually split from each other but I will be making a tool for doing this automatically in the coming days.

Pretrained model: 1x_DIV2K-Lite_450k.pth

FrankenMapGenerator-CX Lite

Purpose: Anti aliasing / Deblur

To eliminate aliasing and general artifacts caused by not enough resolution while bringing out details Im stopping its training here because it's getting worse, i think of some aligment issues by game's rendering pipeline + downscaling...

GainRESV3 (Aggro)

GainRESV3 (Natural)

GainRESV3 (Passive)

Eliminate aliasing and general artifacts caused by not enough resolution. Model knows to add clarity and soften oversharpened areas. Gives image a supersampled look. Had a better version thats more faithful to details but i lost it.

GainRESV4

Category: Images
Purpose: Realistic Ghibli Grain

Text or Anime
Attempt to get the nostalgic grain feel of classically animated Ghibli movies. Got the idea from researching the making of Ronin's :PKT_blue: 1x_AnimeFilmGrain28k. This was made running Nate video denoising with the preset "more denoising" on kiki's delivery service then overlaying it 66.65 percent over the original with DaVinci. On digital drawn anime it gives a slightly [10%] more organic/sharp feel to black lines. Matches well with content that already has a light digital grain. Run Twice for heavy grain. Eternal Thanks to all that indulge all my :psyduck: Wonderings :element_fire_neon:

Ghibli Grain

Category: Anime and Cartoon Restoration
Purpose: Animation

This is a sharpening/deblurring model for anime video. It was created with three goals in mind:
Be blazing fast
Try to avoid enhancing noise and compression artifacts
Try to avoid over-enhancing intentionally blurred parts of the image

Despite that last point, this is not intended to be used on modern anime which makes heavy of use depth-of-field effects.

HurrDeblur SuperUltraCompact

ISO denoise v1

ISO denoise v2

Removes banding, blocking, dithering, aliasing, noise and color tint on DDS Compressed Skin Diffuse Textures.

This should work extremely well on most modern DDS compression types. The training set was compressed with BC3/DXT5, BC3/DXT5 Fast, BC2/DXT3, BC2/DXT3 Fast, and a small number of JPEG compressed images to cover outliers.

This model is trained to remove the slight green color tint that DDS compression tends to add to skin textures, so the model output will not match the original color tone of the input image. This is the desired result though, as DDS compression shifts the colors to a sickly green tint and this model corrects that to more natural color tones.

The training set included faces, body parts, eyes, mouths and hair in a variety of skin types and tones so it should work well on most related diffuse textures.

However it's not just limited to skin, many other images and textures can be cleaned with this model. Designed to be used as a first step cleaning pass before applying additional models after. Check out the other ITF Models.

ITF SkinDiffDDS v1

Category: Skin
Purpose: Skin Upscaling

Adds plausible high frequency detail and removes subtle blur. This is an early unfinished attempt at a x1 Lite model designed specifically for enhancing detail on skin diffuse textures of 3d characters. Even in its current state it works quite well.

Best suited for uncompressed or cleaned textures - otherwise it may just enhance any existing compression artefacts too. The training set included faces, body parts, eyes and hair in a variety of skin types and tones so it should work well on most related diffuse textures.

However it's not just limited to skin, many other images and textures can be enhanced with this model. The results are subtle, so run multiple times if desired.

Pretrained model: 50/50 Interpolation of DIV2K-Lite and SpongeBC1-Lite

ITF SkinDiffDetail Lite v1

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%)

Category: Drawings
Purpose: Art

Clean up model for scanned illustrations. - Made to remove moire patterns, reduce small imperfections, and correct mild compression artifacts in scanned Kingdom Death: Monster illustrations. CMYK printing often shifts colors, so this is intended to reverse that color shifting as well.

Pretrained model: Failed attempts based on ESRGAN_1x_JPEG_80to100

KDM003 scans

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

Category: Anime and Cartoons
Purpose: Animation

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 SharpKeroro

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

N64 textures use a color depth of 5-bits per channel, this model attempts to clean them, restoring smooth gradients in textures

N64clean

NMKD Jaywreck3 (Lite)

NMKD Jaywreck3-Soft (Lite)

NMKD YandereInpaint

Category: Video Compression
Purpose: Texturizing

Tries to reverse heavy h264 compression. Fails. Can be used to texturize images though.

NMKD h264Texturize

NoiseToner Poisson

Purpose: Noise remover

Attempts to remove the damages done from noise. Successor of sorts to Noisetoner_Poisson_150000_G

NoiseToner Poisson Detailed

NoiseToner Poisson Soft

NoiseToner Uniform

NoiseToner Uniform Detailed

NoiseToner Uniform Soft

Category: Normal Map/Bump Map Generation
Purpose: Map Generation - normal maps

Generating normal maps from textures

Pretrained model: 1x_DIV2K-Lite_450k.pth

NormalMapGenerator-CX Lite

1x PSNR Pretrained Model

PixelSharpen

Category: Foliage/Ground
Purpose: bad upscale

Images of plants, trees or other foliage upscaled with Photoshop Preserve Details 2.0. Sharpens and "subdivides" details and noise so it doesn't look upscaled.

Plants

Purpose: Deblur / ReFocus

Purpose: DeBlur, ReFocus, Sharpen Manga, Anime and cartoon style images, but will work on real life images too.

ReFocus Cleanly

Purpose: Deblur / ReFocus

Purpose: DeBlur, ReFocus, Sharpen Real life style images, but will work on Anime images too.

ReFocus V3

Category: CGI
Purpose: Correct old color photos that are tinted red

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

RedImage10000

Category: Video Compression
Purpose: Compression

This model decompresses images and video compressed using RoQ. Config and presets will be added when Mega decides to let me use their site!

RoQ_nRoll

SBDV-DeJPEG Lite

SS Anti Alias 9x

SaiyaJin DeJpeg

Category: Anime and Cartoons
Purpose: Animation

Restoring frames from the show "Sheeep"

This model was trained to restore "Sheeep" while retaining and enhancing the noise present in the show. The model amazingly finished training in only 8.8k iterations with no pretrain, with a dataset of only 4 image pairs. This model should work well for animes and cartoons with a lot of grain present. There are some slight haloing issues in dark colors unfortunately, but I was unable to fix it.

SheeepIt!

Category: Anime and Cartoons
Purpose: BC1/DXT1 compression

First ever lite BC1/DXT1 model. Probably only useful for cartoony textures like those in spongebob games or other cartoon licensed games.

Pretrained model: 1x_DIV2K-Lite_80k

SpongeBC1 Lite

The first attempt at ESRGAN colorization that produces more than 2 colors. Doesn't work that great but it was a neat experiment.

SpongeColor Lite

Category: Anime and Cartoons
Purpose: Animation - Quantized

Removed color quantization/indexing and dithering from cartoon style images and textures

Pretrained model: 1x_1xDEDITHER_32_512_126900_G

Spongebob De-Quantize

SuperUltraCompact Pretrain

Category: Anime and Cartoons
Purpose: Animation

Fix vertical blur / split lines / shadowing. A 1x lite model of my 2xSwatKats. Resolves the same video problems as before, but 1x and faster and meant for chaining to other 2x models (or whatever). Input MUST be 540 vertical as the blur problem is very resolution sensitive.

SwatKats Lite

Sharpening, line darkening and slight line thinning, specifically made for the Boruto anime.

ThePi7on Solidd Deborutify UltraLite

Category: VHS Tapes
Purpose: VHS

Best when used on cartoons, it can work on anime. Due to the dataset it does struggle a bit with orange colors and grainy dark spots. This model is meant to be used to clean up the image before using it on a 2x or 4x model. Example with 2x-BIGOLDIES https://imgsli.com/OTQ0NjM/1/0.

ToonVHS

UltraCompact Pretrain

Purpose: Deblur / Unresize

Purpose: Fix images that have been arbitrarily / poorly resized, such as non-integer nearest-neighbor upscaling/downscaling - Also acts as an image sharpener/deblur when used on slightly soft inputs

Pretrained model: 1x_UnResize_MKII_030000_G.pth

UnResize V3

Category: VHS Tapes
Purpose: VHS

Make old VHS footage crispy. This model will **not** work on video and images with noticeable JPEG/Video compression artifacts, noticeable interlacing or haloing, heavy tape distortion/artifacts and scenes with tons of detail. For best results, use a downscaled HD capture of the VHS tape you intend to use it on.

VHS-Sharpen

Artifacts BC1 Free alsa

Artifacts Dithering alsa

Category: Video Compression
Purpose: Compression

Removal of Compression such as Cinepak, msvideo1 and Roq

cinepak

mdeblur

Category: Normal Map/Bump Map Generation
Purpose: Map Generation - Normal Maps

This model generates "Franken Maps" (named after Frankenstein), which is a custom material map combination I made. Basically, the Red channel of RGB is just the texture converted to grayscale, the Green channel is the roughness map, and the Blue channel is the displacement map. I had to do this to get around the current limitation of CX loss where it requires a 3 channel output (otherwise I would have just made a 2 channel model, or separate single channel models). As of right now the channels need to be manually split from each other but I will be making a tool for doing this automatically in the coming days.

Normals Generator General

Experimental PartialConv2D attempt to paint with ESRGAN. Took ~10.4 days of training on a P100 and around 1.5 months in total due to Colab limits. Not sure if I will continue training it since training is very slow, but may get better.. Warning: Result can vary with different tilesizes. Try not to tile your data.

Sample image: https://e.pcloud.link/publink/show?code=kZQOu7ZldzmFyMPUcFNGkEvwqOxQ8Bl3CeX

Sudo Inpaint PartialConv2D

Upscale 90s and early 2000 American cartoons

90s Cartoon v1

Category: Anime and Cartoons
Purpose: Animation.pth

Upscaling of Animation based on The Legend of Korra.

ATLA KORRA

Ani4K is a 2x model for creating natural-looking 2K and 4K upscales of modern anime. The model places emphasis on depth of field and blur effect retention, which are extremely common in modern anime and something that many anime models struggle with. In addition, Ani4K is trained for strong detail retention, WEB/BD compression clean-up, and producing pleasing lineart. 

More info on the Github page: https://github.com/Sirosky/Sirosky-Upscaling-Models.

Blur Retention Comparisons (including vs. xinntao's 2x paper model): https://imgsli.com/MTg2NTg5/4/5

General Comparisons: https://imgsli.com/MTg2ODI2

Ani4K

2x general purpose anime upscaler, with a focus on cleaning up scuffed sources while enhancing texture detail. While the model was trained on DVDs, it still works well on modern anime. The model is trained to deal with noise, compression artifacts, blur, bleeding, haloing and scuffed line art. Apparently, it also learned to deal with some dotcrawl.

AniScale

Category: Anime and Cartoons
Purpose: Anime/Pretrained

A 2x Ultra Lite model coming in under 8MB. Trained with over 15 sets of LRs ranging in a wide amount of issues. Handles Rainbows, Dot Crawl, MPEG/H.264 Compression, and may even assist in removing halos, and fixing blurriness in certain cases. This is my first public model for everyone. Best when used on old anime that is grainy. I can't say what anime it's best suited for as I have tried multiple series, and have found it does a good job on most all the tests. I wouldn't say use this for Western Animation, but it may work. I have done a few tests that I have shown in the upscale results, but that was chained with other models to achieve such a result. This model is meant to retain the more natural look of a series. There is a color shift on the end result, not drastic, but still noticable. I figure you should fix any color issues in post that way to give a more polished upscale. Big thanks to @SaurusX for the model name, and just helping out in general with anything.

AnimeClassics UltraLite

Realtime 2x model intended for high or medium quality 1080p anime with an emphasis on correcting the inherit blurriness of anime while preserving details and colors. Not suitable for artifact-heavy or highly compressed content as it will just sharpen artifacts. Also works with SD anime by running the model twice. Can be set up to run with mpv on Windows using https://github.com/the-database/mpv-upscale-2x_animejanai

Minimum of RTX 3080 is recommended for running UltraCompact model on 1080p in realtime; RTX 4090 is required to run Compact on 1080p in realtime. SuperUltraCompact should run in realtime on 1080p on some lower cards. The compact model is recommended on SD content. 

Samples: https://imgsli.com/MTUxMDYx \
Comparisons to Anime4K + other compact models and upscalers: https://imgsli.com/MTUxMjY4

AnimeJaNai Standard v1 Compact

AnimeJaNai Standard v1 SuperUltraCompact

AnimeJaNai Standard v1 UltraCompact

AnimeJaNai Strong v1 Compact

AnimeJaNai Strong v1 UltraCompact

Real-time 2x Real-ESRGAN Compact/UltraCompact/SuperUltraCompact models designed for upscaling 1080p anime to 4K. The models correct the inherent blurriness found in anime while preserving details and colors. Optimized for upscaling from 1080p to 4K, but can still produce worthwhile results when upscaling some lower-resolution anime. Can be set up to run in real-time with mpv on Windows using https://github.com/the-database/mpv-upscale-2x_animejanai

Most HD anime are not produced in native 1080p resolution but rather have a production resolution between 720p and 1080p. When the anime is distributed to consumers, the video is scaled up to 1080p, causing scaling artifacts and blur in the video. The aim is to address these issues while upscaling to deliver a result that appears as if the anime was originally mastered in 4K resolution.

Development of the V2 models spanned over four months, during which over 200 release candidate models were trained and meticulously refined. The V2 models introduce several improvements compared to V1:

More accurate "native-res aware" sharpening, so the model works just as well on blurry native 720p sources, sharper native 1080p sources, and everything in between
More accurate colors including line colors
Improved artifact handling
Better preservation and enhancement of background details and grain

Overall, the V2 models yield much more natural and faithful results compared to V1.

Notice

The best place to find AI Upscaling models