Anti Aliasing

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

[Link to Github Release](https://github.com/Phhofm/models/releases/tag/1xDeH264_realplksr)

# 1xDeH264_realplksr  
Scale: 1  
Architecture: [RealPLKSR](https://github.com/muslll/neosr/?tab=readme-ov-file#supported-archs)  
Architecture Option: [realplksr](https://github.com/muslll/neosr/blob/master/neosr/archs/realplksr_arch.py)  

Author: Philip Hofmann  
License: CC-BY-0.4  
Purpose: Restoration, H264  
Subject: Photography  
Input Type: Images  
Release Date: 08.08.2024  

Dataset: [nomosv2](https://github.com/muslll/neosr/?tab=readme-ov-file#-datasets)  
Dataset Size: 6000  
OTF (on the fly augmentations): No  
Pretrained Model: [1xDeJPG_realplksr_otf](https://github.com/Phhofm/models/releases/tag/1xDeJPG_realplksr_otf)  
Iterations: 210'000  
Batch Size: 8  
Patch Size: 64  

Description:   
A 1x de h264 model to remove h264 compression.  

Showcase:  
[Slowpics](https://slow.pics/c/71ulMz8P?canvas-mode=fit-height)  
[Imgsli](https://imgsli.com/Mjg1NTQy)

1xDeH264_realplksr

[Link to Github Release](https://github.com/Phhofm/models/releases/tag/1xDeJPG_realplksr_otf)

1xDeJPG_realplksr_otf   
Scale: 1    
Architecture: [RealPLKSR](https://github.com/muslll/neosr/?tab=readme-ov-file#supported-archs)   
Architecture Option: [realplksr](https://github.com/muslll/neosr/blob/master/neosr/archs/realplksr_arch.py)   

Author: Philip Hofmann  
License: CC-BY-0.4  
Purpose: JPEG, Restoration  
Subject: Photography  
Input Type: Images  
Release Date: 09.07.2024  

Dataset: [nomosv2](https://github.com/muslll/neosr/?tab=readme-ov-file#-datasets)  
Dataset Size: 6000  
OTF (on the fly augmentations): Yes  
Pretrained Model: This one used the 60 model as pretrain, while I used [4xNomos2_realplksr_dysample](https://github.com/Phhofm/models/releases/tag/4xNomos2_realplksr_dysample) as a pretrain for the 60 model.  
Iterations: 196'000  
Batch Size: 24  
GT Size: 64  

Description:   
A 1x dejpg model, trained with otf down to jpg 40 in both degradation processes, see the yml config file for details.  
I also release the 1xDeJPG_realplksr_otf_60 model additionally, which had been trained with less jpg compression in comparison, down to 60 in both cases, where the hope was that it could give a bit higher quality on less compressed inputs.  
The 40 model is released as default since it will be able to handle more compressed inputs in general.  
Since these are trained with otf will slightly deblur. Examples here are compressed, and then recompressed, with jpg 40.  

Showcase:  
[Slowpics](https://slow.pics/c/c0Wft9H4)  
[Imgsli](https://imgsli.com/Mjc3NzMw)

1xDeJPG_realplksr_otf

[Link to Github Release](https://github.com/Phhofm/models/releases/tag/1xDeNoise_realplksr_otf)

# 1xDeNoise_realplksr_otf  
Scale: 1  
Architecture: [RealPLKSR](https://github.com/muslll/neosr/?tab=readme-ov-file#supported-archs)  
Architecture Option: [realplksr](https://github.com/muslll/neosr/blob/master/neosr/archs/realplksr_arch.py)  

Author: Philip Hofmann  
License: CC-BY-0.4  
Purpose: Restoration, Denoise    
Subject: Photography  
Input Type: Images  
Release Date: 08.08.2024  

Dataset: [nomosv2](https://github.com/muslll/neosr/?tab=readme-ov-file#-datasets)  
Dataset Size: 6000  
OTF (on the fly augmentations): Yes  
Pretrained Model: [1xDeJPG_realplksr_otf](https://github.com/Phhofm/models/releases/tag/1xDeJPG_realplksr_otf)  
Iterations: 200'000  
Batch Size: 8  
Patch Size: 64  

Description:   
A 1x realplksr model to denoise, trained with the realesrgan-otf pipeline, also handles a bit of jpg compression (if stronger jpg compression handling is needed, [1xDeJPG_realplksr_otf](https://github.com/Phhofm/models/releases/tag/1xDeJPG_realplksr_otf) can be used).

1xDeNoise_realplksr_otf 

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

A 1x model designed to reduce artifacts and restore detail to images upscaled by 4xFrankendata_FullDegradation_SRFormer. It could possibly work with other upscaling models too.

Frankenfixer_SRFormerLight

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

[Github Release Link](https://github.com/Phhofm/models/releases/Ludvae200)

Name: Ludvae200   
License: CC BY 4.0   
Author: Philip Hofmann   
Network: [LUD-VAE](https://github.com/zhengdharia/LUD-VAE)   
Scale: 1   
Release Date: 25.03.2024   
Purpose: 1x realistic noise degradation model    
Iterations: 190'000   
H_size: 64   
n_channels: 3   
dataloader_batch_size: 16    
H_noise_level: 8   
L_noise_level: 3   
Dataset: [RealLR200](https://drive.google.com/drive/folders/1L2VsQYQRKhWJxe6yWZU9FgBWSgBCk6mz)   
Number of train images: 200   
OTF Training: No   
Pretrained_Model_G: None   

Description:
1x realistic noise degradation model, trained on the [RealLR200](https://drive.google.com/drive/folders/1L2VsQYQRKhWJxe6yWZU9FgBWSgBCk6mz) dataset as found released on the [SeeSR](https://github.com/cswry/SeeSR) github repo.
Next to the ludvae200.pth model file, I provide a ludvae200.zip file which not only contains the code but also an inference script to run this model on the dataset of your choice.
Adapt the ludvae200_inference.py script accordingly by adjusting the file paths at the beginning section, to your input folder, output folder, the folder path holding the ludvae200.pth model, and a folder path where you want the text file to be generated. I made the textfile generation the same way as I did in [Kim's Dataset Destroyer](https://github.com/Kim2091/helpful-scripts/tree/main/Dataset%20Destroyer), which means you will have each image file logged with each of the values used to degrade that specific image file in the resulting text file, which will append only and never overwrite.

You can also adjust the strength settings inside the inference script file to fit to your needs. If you in general want less strong noise for example, you should adjust the temperature upper limit from 0.4 to 0.2 or go even lower.
So in line 96 change "temperature_strength = uniform(0.1,0.4)" to "temperature_strength = uniform(0.1,0.2)" just to give an example.

These values are defaulted to my needs of my last dataset degradation workflow I used, but feel free to adjust these values. You can also do the same as I did, temporarily using deterministic values with multiple runs to determine the min and max values of noise generation you deem suitable for your dataset needs.

See the examples of what this looked like for my last dataset workflow I used my model in.

Ludvae200

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: Correct old color photos that are tinted red

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

RedImage10000

SS Anti Alias 9x

A 1x model designed for skin contrast (although some backgrounds suffer a little modification), also try the other SkinContrast models

1xSkinContrast-High-SuperUltraCompact

A 1x model designed for skin contrast (although some backgrounds suffer a little modification), some images may suffer from the creation of artifacts, High Alternative is the model that generates the most artifacts, also try the other SkinContrast models

1xSkinContrast-HighAlternative-SuperUltraCompact

1xSkinContrast-SuperUltraCompact

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: 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	SPAN
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	2025-05-05
Dataset	8k Dataset V3, Custom Ansel dataset

SuperScale

Similar Models