Name: 4x NMKD Superscale
Author: Nmkd

Nice to release a model again! This one is intended for realistic imagery, and works especially well on faces, hair, and nature shots. It should only be used on somewhat clear shots, without a lot of grain. I trained this model on SPAN, which as of the time of release, you'll need chaiNNer-nightly for. I aimed for a softer, more natural look for this model with as few artifacts as possible.

In addition to the Normal model, I've included a "soft" model. The Soft model is... softer. Basically it was an earlier version of the model with a more limited dataset. It produces more natural output on games or rendered content, but suffers a bit more with realistic stuff.

Note: In shots with DOF (depth of field) or bokeh, unfortunately there will be artifacts. 

Compatibility: You'll have to use the latest chaiNNer-nightly to use this model

ClearRealityV1

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

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

4xFaceUpLDAT

4xFaceUpSharpLDAT

Description: 4x realistic upscaler that may also work for general purpose usage. It was trained with OTF random degradation with a very low to very high range of degradations, including blur, noise, and compression. Trained with the same Frankendata dataset that I used for the pretrain model.

Frankendata_FullDegradation_SRFormer

Remove noise, grain, box blur, lens blur and gaussian blur and increase overall image quality.

LADDIER1

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

Upscale compressed photos to x4 their size.

Able to handle JPG compression (30-100).

LSDIR Compact C3

Upscale small photos with compression, noise and slight blur to 4x their size.

Extending my last 4xLSDIRCompact model to Real-ESRGAN, meaning trained on synthetic data instead to handle more kinds of degradations, it should be able to handle compression, noise, and slight blur.

Here is a comparison to show that 4xLSDIRCompact cannot handle compression artifacts, and that these two models will produce better output for that specific scenario. These models are not ‘better’ than the previous one, they are just meant to handle a different use case.

LSDIR Compact R

Upscale (degraded) photos to x4 their size. 

Trained on synthetic data, meant to handle more degradations

LSDIR Compact R3

The RealESRGAN_x4plus finetuned with the big LSDIR dataset (84,991 images / 165 GB), with manually added jpg compression.

4xLSDIRplusC

Purpose: Clean Real-World Images

Upscaling of realistic images/photos with noise and compression artifacts

NMKD Superscale

4xNomos2_otf_esrgan

Scale: 4  
Architecture: ESRGAN  
Architecture Option: esrgan  
[Github Release Link](https://github.com/Phhofm/models/releases/tag/4xNomos2_otf_esrgan)  

Author: Philip Hofmann  
License: CC-BY-0.4  
Purpose: Restoration  
Subject: Photography  
Input Type: Images  
Release Date: 22.06.2024  

Dataset: Nomos-v2  
Dataset Size: 6000  
OTF (on the fly augmentations): Yes  
Pretrained Model: RealESRGAN_x4plus  
Iterations: 246'000  
Batch Size: 8  
GT Size: 256  

Description:  

4x ESRGAN model for photography, trained using the Real-ESRGAN otf degradation pipeline.  

Showcase:
[Slow Pics 8 Examples](https://slow.pics/s/Y5wdyTPh?canvas-mode=fit-width&image-fit=contain)

4xNomos2_otf_esrgan

4xNomos2_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)  
[Github Release](https://github.com/Phhofm/models/releases/tag/4xNomos2_realplksr_dysample)  

Author: Philip Hofmann  
License: CC-BY-0.4  
Purpose: Pretrained  
Subject: Photography  
Input Type: Images  
Release Date: 30.06.2024  

Dataset: [nomosv2](https://github.com/muslll/neosr/?tab=readme-ov-file#-datasets)  
Dataset Size: 6000  
OTF (on the fly augmentations): No  
Pretrained Model: [4xmssim_realplksr_dysample_pretrain](https://github.com/Phhofm/models/releases/tag/4xmssim_realplksr_dysample_pretrain)  
Iterations: 185'000  
Batch Size: 8  
GT Size: 256, 512  

Description: 
A Dysample RealPLKSR 4x upscaling model that was trained with / handles jpg compression down to 70 on the Nomosv2 dataset, preserves DoF.   
Based on the [4xmssim_realplksr_dysample_pretrain](https://github.com/Phhofm/models/releases/tag/4xmssim_realplksr_dysample_pretrain) I released 3 days ago.  
This model affects / saturate colors, which can be counteracted a bit by using wavelet color fix, as used in these examples.  

Showcase:
[Slowpics](https://slow.pics/s/p3sMnd5l)

4xNomos2_realplksr_dysample

[Link to Github Release](https://github.com/Phhofm/models/releases/4xNomos8k_atd_jpg)

Name: 4xNomos8k_atd_jpg   
License: CC BY 4.0   
Author: Philip Hofmann   
Network: [ATD](https://github.com/LabShuHangGU/Adaptive-Token-Dictionary)   
Scale: 4   
Release Date: 22.03.2024   
Purpose: 4x photo upscaler, handles jpg compression   
Iterations: 240'000   
epoch: 152   
batch_size: 6, 3   
HR_size: 128, 192   
Dataset: nomos8k   
Number of train images: 8492   
OTF Training: Yes   
Pretrained_Model_G: 003_ATD_SRx4_finetune   

Description:
4x photo upscaler which handles jpg compression. This model will preserve noise. Trained on the very recently released (~2 weeks ago) Adaptive-Token-Dictionary network.   

Training details: 
AdamW optimizer with U-Net SN discriminator and BFloat16.
Degraded with otf jpg compression down to 40, re-compression down to 40, together with resizes and the blur kernels.  
Losses: PixelLoss using CHC (Clipped Huber with Cosine Similarity Loss), PerceptualLoss using Huber, GANLoss, [LDL](https://github.com/csjliang/LDL) using Huber, YCbCr Color Loss (bt601) and Luma Loss (CIE XYZ) on [neosr](https://github.com/muslll/neosr).

7 Examples:
[Slowpics](https://slow.pics/s/uwnoI435)

 4xNomos8k_atd_jpg

I release my span otf series:
They come in three variations: weak, middle, and strong.
Mainly meant for photos (can be tried on other things of course).

(Also there is a non-otf span model I had been working on simultaneously that I will release shortly, should give better results on less degraded input in comparison to this span otf series)

Basically I trained the otf_strong for 90k iter and then medium and weak based off that, with some more training to de-learn (tone down) the (too?) strong degradations. Used discrim resets to correct occuring colorloss in all of them. gt size was for the most part 512 with batch 9 (since i hoped it would give better results) with 0.55 it/s training speed (first 40k at the beginning were gt size 256 with batch 20 with 0.58 it/s).

Nomos8k_span_otf_medium

Nomos8k_span_otf_strong

Nomos8k_span_otf_weak

i made this model to upscale old anime and denoise.

OLDIES_FINAL

4x photo upscaler on the SSDIR_Sharp dataset, trained with otf, using the same settings as Real_HAT_GAN.  
These otf values are very high in my opinion. This was an experiment if I used the same settings as Real_HAT_GAN (therefore the name).   
This model will denoise very strongly and smooth out a lot (so a lot of details will be lost. But maybe this effect might be beneficial to someone)

4xReal_SSDIR_DAT_GAN

UniScale_Restore has strong compression removal that helps with restoring heavily compressed or noisy images. It is intended to compete with BSRGAN. Trained with BSRGAN_Resize and Combo_Noise in traiNNer.

UniScale Restore

Version of UniScale trained with camera noise injection (NR = Noise Removal). This model removes noise from images while upscaling.

UniScaleNR Balanced

UniScaleNR Strong

Purpose: Game textures/Art

This model upscales artwork for the game Volfoss (2001). The model peaked in quality very quickly. The NR model removes most noise, but has the downside of removing transparent portions. Use the main model in most cases.

Architecture	ESRGAN
Scale	4x
Size	64nf23nb
Color Mode	RGB
License	WTFPL Private use Commercial use Distribution Modifications Disclaimer
Date	2020-07-22

NMKD Superscale

Similar Models