[Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xArtFaces_realplksr_dysample)

# 4xArtFaces_realplksr_dysample  
Scale: 4  
Architecture: [RealPLKSR with Dysample](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  
Subject: Art  
Input Type: Images  
Release Date: 08.08.2024  

Dataset: [ArtFaces](https://github.com/Phhofm/models/releases/tag/dataset_artfaces)  
Dataset Size: 5'630  
OTF (on the fly augmentations): No  
Pretrained Model: [4xNomos2_realplksr_dysample](https://github.com/Phhofm/models/releases/tag/4xNomos2_realplksr_dysample)  
Iterations: 139'000  
Batch Size: 6  
Patch Size: 64  

Description:  
A Dysample RealPLKSR 4x upscaling model for art / painted faces.   
Based on my [ArtFaces Dataset](https://github.com/Phhofm/models/releases/tag/dataset_artfaces) which is a curated version of the [metfaces dataset](https://github.com/NVlabs/metfaces-dataset) for the purpose of training single image super resolution models.

 4xArtFaces_realplksr_dysample

Upscale Steve Harvey, but maybe other things, somehow??

BSSbeveHarvey

[Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021)](https://github.com/cszn/BSRGAN)

BSRGAN

BigFace

BigFace V3 Blend

BigFace V3 Clear

BigFace v3

FArtFace

4x photo upscaler for faces with otf jpg compression, blur and resize, trained on FFHQ dataset. This has been trained on and for faces, but i guess can also be used for other photos, might be able to retain skin detail. This is not face restoration, but simply a 4x upscaler trained on faces, therefore input images need to be of good quality if good output quality is desired.

4xFFHQDAT

Since the above 4xFFHQDAT model is not able to handle the noise present in low quality input images, i made a small variant/finetune of this, the 4xFFHQLDAT model. This model might come in handy if your input image is of bad quality/not suited for the previous model. I basically made this model in a response to an input image posted in upscaling-results channel as a request to this upscale model (since 4xFFHQDAT would not be able to handle noise), see Imgsli1 example below for result.

4xFFHQLDAT

Face-Ality V1 (Fatality Faces)

Face De-blur - slightly out of focus / blurred images of faces. It is aimed at faces / hair

Face Focus

Description: 4x photo upscaler for faces, trained on the FaceUp dataset. These models are an improvement over the previously released 4xFFHQDAT and are its successors. These models are released together with the FaceUp dataset, plus the accompanying [youtube video](https://www.youtube.com/watch?v=TBiVIzQkptI)

This model comes in 4 different versions:  
4xFaceUpDAT (for good quality input)  
4xFaceUpLDAT (for lower quality input, can additionally denoise)  
4xFaceUpSharpDAT (for good quality input, produces sharper output, trained without USM but sharpened input images, good quality input)  
4xFaceUpSharpLDAT (for lower quality input, produces sharper output, trained without USM but sharpened input images, can additionally denoise)  

I recommend trying out 4xFaceUpDAT

4xFaceUpDAT

4xFaceUpLDAT

4xFaceUpSharpDAT

4xFaceUpSharpLDAT

Upscale faces both pixelized and real

Pretrained model: 4x_Faces_N_250000.pth

Faces_04_N

A normal ESRGAN model without degradations and without any pretrain, simply an RRDBNet model trained on paired dataset (4x downsampled) on the full LSDIR dataset (84,991 images / 165 GB)

4xLSDIR

Upscale small good quality photos to 4x their size

My first ever model 😄 Well, it’s not the best, but, it’s something 😉 
I provide some 15 examples from the validation set here for you to visually see the generated output (with chaiNNer), photo dimensions are in the name

LSDIR Compact

Upscale photos to x4 their size.

4xLSDIRCompactv2 supersedes the previously released models, it combines all my progress on my compact model. Both CompactC and CompactR had received around 8 hours more training since release with batch size 10 (CompactR had only been up to 5 on release), and these two were then interpolated together. This allows v2 to handle some degradations, while preserving the details of the CompactC model. Examples: https://imgsli.com/MTY0Njgz/0/2

LSDIR Compact v2

Upscale small photos with compression to 4x their size.

Trying to extend my previous model to be able to handle compression (JPG 100-30) by manually altering the training dataset, since 4xLSDIRCompact can't handle compression. Use this instead of 4xLSDIRCompact if your photo has compression (like an image from the web).

LSDIR Compact C

Nomos8kHAT-L_otf

Purpose: Art/People

A sharp upscaler trained specifically for small sprite faces. Does not blend, so avoid using on painted/photo portraits unless you were trying to retain more of the outlines somehow.

SmolFace

SmolFace Clean

Purpose: Faces / Game Textures

character textures for star wars games, including the heroes, rebels, sith and imperial. Plus a few main aliens…Why called trixie? Because jar jars big adventure would be too long of a name… This also provides good upscale for face textures for general purpose as well as basic star wars

Architecture	DAT
Scale	4x
Color Mode	RGB
License	CC-BY-4.0 Private use Commercial use Distribution Modifications Credit required State Changes No Liability & Warranty Disclaimer
Date	2023-09-02
Dataset	FaceUp
Dataset size	10000
Training iterations	140000
Training epochs	54
Training batch size	4
Training HR size	128
Training OTF	Yes

4xFaceUpDAT

Similar Models