Upscale 90s and early 2000 American cartoons

90s Cartoon v1

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

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

Real-time 2x Real-ESRGAN Compact/UltraCompact/SuperUltraCompact models designed for upscaling 1080p anime to 4K. 

The aim of these models is to address scaling, blur, oversharpening, and compression artifacts while upscaling to deliver a result that appears as if the anime was originally mastered in 4K resolution. Can be set up to run in real-time with mpv on Windows using https://github.com/the-database/mpv-upscale-2x_animejanai

The development of the V3 models spanned over seven months, during which over 100 release candidate models were trained and meticulously refined. The V3 models introduce several improvements compared to V2, including:

More faithful appearance to original source
Improved handling of oversharpening artifacts, ringing, aliasing
Better at preserving intentional blur in scenes using depth of field
More accurate line colors, darkness, and thickness
Better preservation of soft shadow edges

Overall, the V3 models yield significantly more natural and faithful results compared to the V2 models.test

AnimeJaNai_HD_V3_Compact

Real-time 2x Real-ESRGAN Compact/UltraCompact/SuperUltraCompact models designed for upscaling 1080p anime to 4K.

The aim of these models is to address scaling, blur, oversharpening, and compression artifacts while upscaling to deliver a result that appears as if the anime was originally mastered in 4K resolution. Can be set up to run in real-time with mpv on Windows using https://github.com/the-database/mpv-upscale-2x_animejanai

The development of the V3 models spanned over seven months, during which over 100 release candidate models were trained and meticulously refined. The V3 models introduce several improvements compared to V2, including:

More faithful appearance to original source Improved handling of oversharpening artifacts, ringing, aliasing Better at preserving intentional blur in scenes using depth of field More accurate line colors, darkness, and thickness Better preservation of soft shadow edges

Overall, the V3 models yield significantly more natural and faithful results compared to the V2 models.

AnimeJaNai_HD_V3_SuperUltraCompact

AnimeJaNai_HD_V3_UltraCompact

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.

AnimeJaNai v2 Compact

AnimeJaNai v2 SuperUltraCompact

[Link to Github Release with more infos to the process](https://github.com/Phhofm/models/releases/tag/2xAoMR_mosr)

2xAoMR_mosr  
Scale: 4  
Architecture: [MoSR](https://github.com/umzi2/MoSR)  
Architecture Option: [mosr](https://github.com/umzi2/MoSR/blob/95c5bf73cca014493fe952c2fbc0bdbe593da08f/neosr/archs/mosr_arch.py#L117)  

Author: Philip Hofmann  
License: CC-BY-0.4  
Purpose: A 2x mosr upscaling model for game textures  
Subject: Game Textures  
Input Type: Images  
Release Date: 21.09.2024 (dd/mm/yy)  

Dataset: Game Textures from Age of Mythology: Retold  
Dataset Size: 13'847  
OTF (on the fly augmentations): No  
Pretrained Model: [4xNomos2_hq_mosr](https://github.com/Phhofm/models/releases/tag/4xNomos2_hq_mosr)  
Iterations: 510'000  
Batch Size: 4  
Patch Size: 64  

## Description:   
In short: A 2x game texture mosr upscaling model, trained on and for (but not limited to) Age of Mythology: Retold textures.

Since I have been playing Age of Mythology: Retold (casual player), I thought it would be interesting to train an single image super resolution model on (and for) game textures of AoMR, but this model should be usable for other game textures aswell.
This is a 2x model, since the biggest texture images are already 4096x4096, I thought going 4x on those would be overkill (also there are already 4x game texture upscaling models, so this model can be used for similiar cases where 4x is not needed).

Model Showcase:
[Slowpics](https://slow.pics/s/IlkmsToH)

2xAoMR_mosr

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

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:
* 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-Small

Upscale modern animation images/videos. Compression, blur, and un-sharpening degradations were used on the dataset. First model I trained and I think it came out pretty well.

ModernSpanimationV1

[Omni Aggregation Networks for Lightweight Image Super-Resolution (OmniSR)](https://github.com/Francis0625/Omni-SR)

While lightweight ViT framework has made tremendous progress in image super-resolution, its uni-dimensional
self-attention modeling, as well as homogeneous aggregation scheme, limit its effective receptive field (ERF) to
include more comprehensive interactions from both spatial and channel dimensions. To tackle these drawbacks,
this work proposes two enhanced components under a new Omni-SR architecture. First, an Omni Self-Attention (OSA) block is proposed based on dense interaction principle, which can simultaneously model pixel-interaction from both spatial and channel dimensions, mining the potential correlations across omni-axis (i.e., spatial and channel). Coupling with mainstream window partitioning strategies, OSA can achieve superior performance with compelling computational budgets. Second, a multi-scale interaction scheme is proposed to mitigate sub-optimal ERF (i.e., premature saturation) in shallow models, which facilitates local propagation and meso-/global-scale interactions, rendering an omni-scale aggregation building block. Extensive experiments demonstrate that Omni-SR achieves recordhigh performance on lightweight super-resolution benchmarks (e.g., 26.95dB@Urban100 ×4 with only 792K parameters). Our code is available at https://github.com/Francis0625/Omni-SR

OmniSR 2x DF2K

OmniSR 2x DIV2K

[Swift-SRGAN - Rethinking Super-Resolution for real-time inference](https://github.com/Koushik0901/Swift-SRGAN)

In recent years, there have been several advancements in the task of image super-resolution using the state of the art Deep Learning-based architectures. Many super-resolution-based techniques previously published, require high-end and top-of-the-line Graphics Processing Unit (GPUs) to perform image super-resolution. With the increasing advancements in Deep Learning approaches, neural networks have become more and more compute hungry. We took a step back and, focused on creating a real-time efficient solution. We present an architecture that is faster and smaller in terms of its memory footprint. The proposed architecture uses Depth-wise Separable Convolutions to extract features and, it performs on-par with other super-resolution GANs (Generative Adversarial Networks) while maintaining real-time inference and a low memory footprint. A real-time super-resolution enables streaming high resolution media content even under poor bandwidth conditions. While maintaining an efficient trade-off between the accuracy and latency, we are able to produce a comparable performance model which is one-eighth (1/8) the size of super-resolution GANs and computes 74 times faster than super-resolution GANs.

NOTE: The author used the wrong file extensions for the models *on GitHub*. You will download a `.pth.tar` file. This is not actually a TAR file. Change the file extension to just `.pth` and the model will work.

Swift-SRGAN 2x

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)

A 2x model designed for hand-drawn animation of the 80's, 90's and early 2000s.

The Super Mario Bros. Super Show is a hybrid animated and live-action show that debuted in 1989. Each episode featured a cartoon segment sandwiched between live-action segments. The combination of the two formats makes the show very difficult to upscale, and creates the need for multiple model files.

These models were trained using footage from the show itself (except for some title images that were recreated in Photoshop) by finding cases where the same image was shown at different resolutions. For the animated footage, I also did some retouching to reduce haloing, color bleed, and other issues.

A few notes:

- The opening sequence (in particular, the first shot with the giant talking Mario face) is very difficult to upscale due to the picture being degraded from multiple layers of compositing. Ideally, a professional remaster of the series would have access to the individual elements, upscale those, then recomposite them.
- Although live-action models are provided, you will likely get better results from commercial upscaling software (I recommend  the Proteus model in Topaz Video AI).
- Footage must be deinterlaced before processing (I recommend QTGMC for both live-action and animated segments).

[Full Read Me](https://www.mediafire.com/file/brp4c0pvv5s42rw/ReadMe.txt/file)

[Sample Animated Result](https://www.mediafire.com/view/wtieecra7iov35f/Animation_Sample.png/file)

[Sample Live Action Result](https://www.mediafire.com/view/xa7jenxl18xd1y7/Live_Action_Sample.png/file)

smbss-2x (small)

smbss-2x (large)

smbss-2x (medium)

4x general purpose upscaler for non-degraded content.

Has been trained as paired dataset on box downsamples as a DAT2 model, AdamW with pixel, perceptual, gan, color, ldl and ff loss.

Architecture	SPAN
Scale	2x
Size	64
Color Mode	RGB
License	MIT Private use Commercial use Distribution Modifications Credit required No Liability & Warranty Disclaimer
Date	2024-04-07
Dataset	ModernAnimation1080v2
Dataset size	2200
Training OTF	No

ModernSpanimationV1

Similar Models