90s Cartoon v1

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

Purpose: Anime

This is a successor to AnimeSharpV3 based on RCAN instead of ESRGAN. It outperforms both versions of AnimeSharpV3 in every capacity. It's sharper, retains *even more* detail, and has very few artifacts. It is __extremely faithful__ to the input image, even with heavily compressed inputs. 

To use this model, you must update to the [**latest chaiNNer nightly build**](https://github.com/chaiNNer-org/chaiNNer-nightly/releases)

The `2x-AnimeSharpV4_Fast_RCAN_PU` model is trained on RCAN PixelUnshuffle. This is much faster, but comes at the cost of quality. I believe the model is ~95% the quality of the full V4 RCAN model, but ~6x faster in Pytorch and ~4x faster in TensorRT. This model is ideal for video processing, and as such was trained to handle MPEG2 & H264 compression.

__Comparisons:__ https://slow.pics/c/63Qu8HTN
https://slow.pics/c/DBJPDJM9
![1736292155 679079](https://github.com/user-attachments/assets/875be696-0948-4de2-9d03-85a581891a49)

AnimeSharpV4

AnimeSharpV4_Fast_RCAN_PU

I used frames from 5 episodes from the PAL DVD sets with differing quality levels against the German Blu-rays in order to reverse engineer an AstroRes model. Detail enhancement is very high though it helps to have a good quality source (of course). The model will remove MPEG-2, some halos, and PAL-conversion artifacts like image trails and faded lines to great effect. Temporal stability is quite good.

AstroManLite

Purpose: To recreate the upscale process used in the He-Man German Blu-ray release.

A followup to my previous AstroManLite model. The primary focus is on detail preservation and enhancement of decent DVD material instead of artifact repair. I eliminated the attempt to remove temporal artifacts from the He-Man DVDs as it proved detrimental to the final results. It will, however, remove MPEG-2 artifacts to great effect.

AstroManPlus 262k

upscaling old anime. help to denoise and find lines and dehalo

BIGOLDIES

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 is my first 2xcompact model, the main purpose of it is to upscale Dragon ball GT. for upscaling videos that have grain I would recommend denoising and dehaloing it before passing it to the model for temporal stability.

GT-evA

This is the v2 of my 2xGT model, the main purpose of it is to improve upon the v1 model and make more it generalized.
for upscaling videos that have grain I would recommend denoising and de-haloing it before passing it through  the model.

GT-v2-evA

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

2x span nf48 model trained with 2x_Garfield dataset.
the output of this model is in no way near the 2x_Garfield, but it can do everything that the esrgan model does to some degree and have the speed advantage. 
finally, I would like to thank @SaurusX for providing me with his dataset.
Comp:
https://slow.pics/c/Yezua7O7

GarfieldJr_span

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: 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

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	SPAN
Scale	2x
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	2023-12-13
Dataset	SaurusX's Garfield Dataset
Dataset size	6474
Training iterations	315000
Training epochs	56
Training batch size	6
Training HR size	128
Training OTF	No

GarfieldJr_span

Similar Models