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

BSRGAN

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

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

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

A 4x photo upscale DAT model trained with otf (resize, jpg, small blur) on the LSDIR dataset.

4xLSDIRDAT

Interpolation of 4xLSDIRplusC and 4xLSDIRplusR to handle jpg compression and a little bit of noise/blur

4xLSDIRplus

The RealESRGAN_x4plus finetuned with the big LSDIR dataset (84,991 images / 165 GB), with jpg compression and noise and blur

4xLSDIRplusR

[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

Nomos8kHAT-L_otf

NomosUniDAT_otf

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.

4xNomosUniDAT2_box

[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 4x DF2K

OmniSR 4x DIV2K

Purpose: upscaling model for amateur to professional photos (regular)

Skilled in working with cats, hair, parties, and creating clear images. Also proficient in resizing photos and enlarging large, sharp images. Can effectively improve images from small sizes as well (300px at smallest on one side, depending on the subject). Experienced in experimenting with techniques like upscaling with this model twice and then reducing it by 50% to enhance details, especially in features like hair or animals.

Original image, second is upscale with the model once, and the last is upscaled with model twice.

PurePhoto span

[Link to Github Release](https://github.com/Phhofm/models/releases/4xRealWebPhoto_v2_rgt_s)

Name: 4xRealWebPhoto_v2_rgt_s   
License: CC BY 4.0   
Author: Philip Hofmann   
Network: RGT   
Network Option: RGT-S   
Scale: 4   
Release Date: 10.03.2024   
Purpose: 4x real web photo upscaler, meant for upscaling photos downloaded from the web   
Iterations: 220'000   
epoch: 5   
batch_size: 16   
HR_size: 128   
Dataset: 4xRealWebPhoto_v2 (see details in attached pdf file in github release)   
Number of train images: 1'086'976 (or 543'488 pairs)   
OTF Training: No   
Pretrained_Model_G: RGT_S_x4   

Description:
4x real web photo upscaler, meant for upscaling photos downloaded from the web. Trained on my v2 of my 4xRealWebPhoto dataset, it should be able to handle realistic noise, jpg and webp compression and re-compression, scaling and rescaling with multiple downscampling algos, and handle a little bit of lens blur.

Thought featuring degraded images in the examples, this model should also be able to handle good quality input.

Details about the approach/dataset I made to train this model (and therefore also what this model would be capable of handling) is in the attached pdf in the github release.

My previous tries of this dataset, meaning v0 and v1, will get a separate entry, though this version would be recommended over them.

12 Examples on [Slowpics](https://slow.pics/s/HxXtE1eZ)

 4xRealWebPhoto_v2_rgt_s

[Link to Github Release](https://github.com/Phhofm/models/releases/4xRealWebPhoto_v3_atd)

Name: 4xRealWebPhoto_v3_atd   
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 upscaler for photos downloaded from the web   
Iterations: 250'000   
epoch: 10   
batch_size: 6, 3   
HR_size: 128, 192   
Dataset: 4xRealWebPhoto_v3   
Number of train images: 101'904   
OTF Training: No   
Pretrained_Model_G: 003_ATD_SRx4_finetune   

Description:   
4x real web photo upscaler, meant for upscaling photos downloaded from the web. Trained on my v3 of my 4xRealWebPhoto dataset, it should be able to handle noise, jpg and webp (re)compression, (re)scaling, and just a little bit of lens blur, while also be able to handle good quality input. Trained on the very recently released (~2 weeks ago) Adaptive-Token-Dictionary network. 

My 4xRealWebPhoto dataset tried to simulate the use-case of a photo being uploaded to the web and being processed by the service provides (like on a social media platform) so compression/downscaling, then maybe being downloaded and re-uploaded by another used where it, again, were processed by the service provider. I included different variants in the dataset. The pdf with info to the v2 dataset can be found [here](https://github.com/Phhofm/models/releases/download/4xRealWebPhoto_v2_rgt_s/4xRealWebPhoto_v2.pdf), while i simply included whats different in the v3 png:

![4xRealWebPhoto_v3](https://github.com/Phhofm/models/assets/14755670/2ec67e48-bf21-4b57-9f27-69bc49b84315)


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, [Focal Frequency](https://github.com/EndlessSora/focal-frequency-loss), [Gradient Variance](https://github.com/lusinlu/gradient-variance-loss) with Huber, YCbCr Color Loss (bt601) and Luma Loss (CIE XYZ) on [neosr](https://github.com/muslll/neosr) with norm: true.

11 Examples:
[Slowpics](https://slow.pics/s/plgWVh4j)

 4xRealWebPhoto_v3_atd

[Link to Github Release](https://github.com/Phhofm/models/releases/4xRealWebPhoto_v4_dat2)

## 4xRealWebPhoto_v4_dat2

**Scale:** 4   
**Architecture:** DAT   

**Author:** Philip Hofmann   
**License:** CC-BY-4.0   
**Purpose:** Compression Removal, Deblur, Denoise, JPEG, WEBP, Restoration   
**Subject:** Photography   
**Input Type:** Images   
**Date:** 04.04.2024   

**Architecture Option:** DAT-2   
**I/O Channels:** 3(RGB)->3(RGB)   

**Dataset:** Nomos8k   
**Dataset Size:** 8492   
**OTF (on the fly augmentations):** No   
**Pretrained Model:** DAT_2_x4   
**Iterations:** 243'000   
**Batch Size:** 4-6   
**GT Size:** 128-256   

**Description:** 4x Upscaling Model for Photos from the Web. The dataset consists of only downscaled photos (to handle good quality), downscaled and compressed photos (uploaded to the web and compressed by service provider), and downscale, compressed, rescaled, recompressed photos (downloaded from the web and re-uploaded to the web).

Applied lens blur, realistic noise with my ludvae200 model, JPG and WEBP compression (40-95), and down_up, linear, cubic_mitchell, lanczos, gaussian and box downsampling algorithms. For details on the degradation process, check out the pdf with its explanations and visualizations.

This is basically a dat2 version of my previous 4xRealWebPhoto_v3_atd model, but trained with a bit stronger noise values, and also a single image per variant so drastically reduced training dataset size.
 

**Showcase:** 
[12 Slowpics Examples](https://slow.pics/s/TvJ21pJG)

Architecture	HAT
Scale	4x
Size	HAT-L
Color Mode	RGB
License	CC-BY-4.0 Private use Commercial use Distribution Modifications Credit required State Changes No Liability & Warranty Disclaimer
Date	2023-11-01
Dataset	nomos8k
Dataset size	8492
Training iterations	220000
Training epochs	19
Training batch size	4
Training HR size	128
Training OTF	Yes

Nomos8kHAT-L_otf

Similar Models