Name: 1x UnResizeOnly_RCAN
Author: Kim2091

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

Attempts to remove the damages done by BC1 compression.

BCGone Smooth

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

Purpose: Cartoons

This is a simple retrain of SaurusX's 1x_BroadcastToStudioLite_485k model from a couple years ago. This one is trained on compact, actually has less artifacts, and is significantly faster.

__Comparisons:__ <https://slow.pics/c/oGwHyYym>
![1733071729 5752351](https://github.com/user-attachments/assets/f247b870-d49e-4c37-ad39-c4565efe164d)

BroadcastToStudio Compact

This is SaurusX's original description:
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.

-------

Sadly this model has some intense artifacts. Thankfully the SPAN re-train reduced these a bit, but they're still problematic. This was just a quick test of SPAN's capabilities. This was trained only to ~66k iterations, compared to the 480k of the original.

BroadcastToStudio_SPAN

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

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

Incomplete lite model to remove ROQ compression

DeRoqBeta-lite

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

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

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

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

SS Anti Alias 9x

Purpose: Anti-aliasing, Restoration

I was bored, so I did this. This model uses DPID as the scaling algorithm for the HRs. The original images were 8k or 12k. It's significantly sharper than Box/Area scaling, yet does a great job with aliasing. This allows for a very sharp model with minimal artifacts, even on the SPAN version.

The main model is trained on 12k images captured with Nvidia Ansel. It took about 2 days capturing manual 4k and 12k pairs for this model. The 4k captures were used as the LR, the 12k captures were resized to 4k with DPID with randomized lambda values, then trained on as HRs. 

The Alt model is trained exclusively on 8k images from my 8k dataset, resized to 4k with dpid. This provides a clearer result with less noise, but it doesn't handle long edges well at all.

Thanks to CF2lter for advice on preparing the dataset, and umzi2 for creating the [rust version of DPID](<https://github.com/umzi2/pepedpid>). 

**Showcase:** https://slow.pics/c/TCyqje9K
![Animation (2)](https://github.com/user-attachments/assets/fb9f010a-a4e1-4537-8b23-9a69974011c6)

SuperScale

SuperScale_Alt_RPLKSR_S

SuperScale_RPLKSR_S

Purpose: Upscaling older cartoons

This is yet another retrain of SaurusX's SwatKats_Lite model. The dataset was reprocessed with my [Find Misaligned Images](<https://github.com/Kim2091/helpful-scripts/tree/main/Find%20Misaligned%20Images>) script, along with the new [ImgAlign](<https://github.com/sonic41592/ImgAlign>) update, which drastically reduced artifacts and increased the model's capabilities. This particular model is roughly on par with or slightly behind the original, doing better in some spots and worse in others. Refer to the attached examples to see this.

The advantage of this over the original is the speed improvement of Compact over ESRGAN-lite. In a 480p test on an RTX 4090, the original ESRGAN-lite model took 0.28 seconds to process a frame vs Compact's 0.13 seconds.

https://slow.pics/s/dF3Icjpv

OR

<https://imgsli.com/MjQxMzc1/0/1>

SwatKats Compact

Purpose: Artifact Removal

A version of UnResize trained on RCAN, which is faster and provides better quality than ESRGAN

This model does **not remove compression or perform deblurring**, unlike the original UnResize models. __It **only** removes scaling artifacts.__

I've attached the script I used to create the dataset (it utilizes imagemagick) and the config for [traiNNer-redux](https://github.com/the-database/traiNNer-redux)

Architecture	RCAN
Scale	1x
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	2025-01-06
Dataset	UltraSharpV2_Ethical, DigitalArtV3, ModernAnimation1080_v3, Kim2091's 8k Dataset V2
Dataset size	13000
Training iterations	95000
Training batch size	8

UnResizeOnly_RCAN

Similar Models