Upscale 90s and early 2000 American cartoons

90s Cartoon v1

Upscaling of Animation based on The Legend of Korra.

ATLA KORRA

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

Pretrained: 4x_muy4_035_1.pth

This is my first model, so it's not perfect, but I wanted to see if I could train an upscaling model that didn't result in a lot of detail loss and deblurring like the current Compact upscaling models. I believe I accomplished this, but I was unable to reduce contrast shifting. The contrast shifting may cause skin tones to appear incorrect on bright frames, but it's not too bad overall! I'll list a few examples below; more can be found by clicking the Overview link on the Github release page.

Pretrained model: Kim2091_CrappyCompactV2.pth

Bubble AnimeScale Compact v1

2x_Bubble_AnimeScale_SwinIR_Small_v1 was trained to upscale anime frames faithfully without major contrast shifting compared to my compact model. Although much slower compared to my compact model, the results look significantly better! A few example upscales are listed below; more can be found by clicking the Overview link on the Github release page.

Bubble AnimeScale SwinIR Small v1

Using the Kineko 4K scan the hope was to clean up the Funi DVD releases and upscale to something comparable. This model degrains the series pretty damn well, but what's revealed beneath is a lot of moving noise that's probably best dealt with in pre- or post- with a video editor like AVISynth. So while the model is remarkably temporally stable, the DBZ sources certainly aren't. The movies look really nice when upscaled with raw input, though.

2x_DBZScanLite

Category: Cel Animation
Purpose: Traditional Animation

Upscaling Dragon Ball Z DBox DVD's. - grainy sources. It keeps some grain, but also doing some cleaning, sharpening, and fixing.

DigitalFilmV5 Lite

Category: Digital Animation


This was trained on the dataset that OptimusPrimal used for his DigitalFilm models. This model cleans up the image removing some noise while upscaling. This model is very fast, running around 200x the speed of a standard ESRGAN model on my system. This is primarily a proof of concept for how fast Real-ESRGAN models can get while still producing nice results.

DigitalFlim SuperUltraCompact

This model is designed to upscale the standard definition digital era of the Pokémon anime, which runs from late season 5 (Master Quest) to early season 12 (Galactic Battles). During this time, the show was animated digitally in a 4:3 ratio. This process was also used for Mewtwo Returns, most of Pokémon Chronicles, and the Mystery Dungeon specials.

Advice/Known Limitations:
* This OmniSR model can occasionally produce black frames when run in fp16 mode. This seems to be more common in the TPCi era (seasons 9 and later). The issue is sporadic enough that it probably makes sense to do a first pass in fp16, then re-upscale any affected shots in fp32.
* I recommend using QTGMC on a preset of "Slow" or slower for deinterlacing. While the show is primarily animated at 12/24 fps, some elements like backgrounds are animated at a full 60i.
* The model is not great at handling fonts, particularly the italicized text in the episode credits. This is despite including font images in the training data,.

Digital Pokémon-Large

Meant to preserve original 4:3 framing of G&F while upscaling. Trained to handle all seven seasons, which drastically differ in quality. Fixes include rainbowing, dot-crawl, halos, general noise, and of course MPEG-2 artifacts. It should be generally flexible in dealing with different degrees of those artifacts, but as always the cleaner the source the better. The model could be useful with other shows from the '80s and '90s with ugly video sources. Maybe.

2x_Garfield1_308k

Purpose: 2x anime upscaler

2x omnisr version of the 2xHFA2kCompact model.

Original Link: https://drive.google.com/drive/folders/1QfiPT1uHi7Yxb4Gjhl25M2YI6hWU5hVt?usp=drive_link

HFA2OmniSR

Purpose: 2x anime upscaler

2x Real-CUGAN version of the 2xHFA2kCompact model.

Original Link: https://drive.google.com/drive/folders/1-ijn4RE5vSWJuIwoBTZdA3cKlraw8PcY

Slow Pics examples:
[Example 1](https://slow.pics/c/auAsNwNZ)
[Example 2](https://slow.pics/c/HX2wuZ3E)
[Ludvae1](https://slow.pics/c/oDQT5d3u)
[Ludvae2](https://slow.pics/c/5tJrT8FF)

HFA2Real CUGAN

Purpose: 2x anime upscaler

2x SwinIR-Small version of the 2xHFA2kCompact model.

Original Link: https://drive.google.com/drive/folders/1yM2_BkktUXS2-i1sTCYZuHRyfx-ak2o8

HFA2SwinIR S

Purpose: A lightweight anime 2x upscaling model with realistic degradations, based on musl's HFA2k_LUDVAE dataset

2x lightweight anime upscaler with realistic degradations (compression, noise, blur) based on musl's HFA2k_LUDVAE dataset.

Original Link: https://drive.google.com/drive/folders/1Fe1Uu3-L5YWaVSwPGBTIPG4xU7kK9rZK?usp=drive_link

HFA2k LUDVAE SPAN

Purpose: A lightweight anime 2x upscaling model with realistic degradations, based on musl's HFA2k_LUDVAE dataset

2x lightweight anime upscaler with realistic degradations (compression, noise, blur) based on musl's HFA2k_LUDVAE dataset.

HFA2k LUDVAE compact

Purpose: 2x anime upscaler which tries to preserve dof

2x anime upscaler, a non-otf version of the HFA2kCompact model which tries to preserve dof by not deblurring.

Original Link: https://drive.google.com/drive/folders/1RZbALUTCf4DYDTVMBR74b8Nt-7m6TEyk?usp=drive_link

HFA2k compact multijpg

Purpose: 2x anime upscaler

2x span version of the hfa2k model.

Original Link: https://drive.google.com/drive/folders/1Fe1Uu3-L5YWaVSwPGBTIPG4xU7kK9rZK?usp=drive_link

HFA2kSPAN

Purpose: 2x anime upscaler

2x shallow esrgan version of the HFA2kCompact model.  
This model should be usable with [FAST_Anime_VSR ](https://github.com/Kiteretsu77/FAST_Anime_VSR) using TensorRT for fast inference, as should my [2xHFA2kReal-CUGAN](https://drive.google.com/file/d/1wqlK-rQjPGKJ5pNoVgnK9gcNF1tA8EjV/view?usp=drive_link) model.  

Original Link: https://drive.google.com/drive/folders/1_gtYqZGQgrpq55gsGf17MG_QUP4XeFJD

Slow Pics examples:  
[Example 1](https://slow.pics/c/RZj6GMwS)  
[Example 2](https://slow.pics/c/Q3DHaU45)  
[Ludvae1](https://slow.pics/c/fJi4IphY)  
[Ludvae2](https://slow.pics/c/iIhgHokD)

HFA2kShallowESRGAN

Loyaldk LitePony V1.0

Loyaldk SuperPony V1.0

In addition to removing the vertical blur, the model upscales, sharpens and will remove MPEG-2 artifacting and a small amount of rainbowing and dot crawl. Another series afflicted with the vertical blur is Avatar the Last Airbender, which can be repaired by this model. The video fed into the model MUST be 540 vertical for the deblur to work properly.

SwatKats

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 (2x)

I recommend filtering the source before passing it to the model. 

Note: if the original trainers of the models i used as teachers for this model are not cool with using them in this way, i will remove this model

2xken-v1-eva-01

Purpose: Realtime animation restauration and doing stuff like deblur and compression artefact removal

(Teacher: RealESRGANv2-animevideo-xsx2.pth)

My first attempt to make a REALTIME 2x upscaling model while also applying teacher student learning. It beats Anime4k in every way. These benchmarks use a 3060ti and it shows that everything better than a 3060ti should be able to handle 1080p input if you create engine files and use my TensorRT code. You can see in the readme how to convert onnx files into engines. The 2 right bars compare normal Compact2 and Ultracompact in speed, the 2 on the left showcase older apis I used which isn't too important for this showcase. To use this, you need to use my code which is https://github.com/styler00dollar/VSGAN-tensorrt-docker. If you use Manjaro, it is also possible to pipe the data stream directly into mpv, so you can watch it in a video player without rendering a video. Yeah the model does seem a little noisy if you zoom in a lot, but don't forget that the model itself is only 1.2mb. I think it does quite well. I still try to improve on fast models, but this is good enough to share as a first model. Plz don't steal without credits, k thx.

sudo UltraCompact

This is my attempt at making cugan more efficient and also training it with better loss functions than official training code. Took me months to train on a 4090. It is pure pain to train this network. Nobody will probably beat my iter record any time soon. I tried to balance speed/vram and quality. The image quality is very close to cugan architecture while having ultracompact speed. It usually looks way better than compact, but has different kinds of artefacts. If you have high contrast lines which are a few or one pixel or thin lines with movement, then the model will struggle a bit. That is quite rare though. Exported as onnx for mlrt or vsgan. https://github.com/styler00dollar/VSGAN-tensorrt-docker. I also included old l1 for pretrain purposes, but be warned, it is hard to train.

Architecture	SwinIR
Scale	2x
Size	smalls64w864nf60dim1conv
Color Mode	RGB
License	CC-BY-4.0 Private use Commercial use Distribution Modifications Credit required State Changes No Liability & Warranty Disclaimer
Date	2023-12-26
Dataset	hfa2k
Dataset size	2568
Training iterations	22000
Training epochs	10
Training batch size	12
Training HR size	256
Training OTF	Yes

HFA2SwinIR S

Similar Models