Difference between revisions of "Model Database"

From Upscale Wiki
Jump to navigation Jump to search
(Removed Texture Maps)
(Fix BC1 Model // Edit via Wikitext Extension for VSCode)
 
(190 intermediate revisions by 19 users not shown)
Line 6: Line 6:
 
=ESRGAN ("old Architecture") Models=
 
=ESRGAN ("old Architecture") Models=
  
Models that use the "old" ESRGAN architecture. They can be used either with the official ESRGAN repository (old arch tag) and BasicSR (old arch or preferably victorc's fork). You can also use tools that wrap around one of them, like IEU from Honh.
+
Models that use the "old" ESRGAN architecture. They can be used either with the official ESRGAN repository (old arch tag)
 +
and BasicSR (old arch or preferably victorc's traiNNer version). You can also use tools that wrap around one of them, like IEU from Honh or Cupscale by [[User:nmkd|Nmkd]].
  
 
==Image scaling and Video upscaling==
 
==Image scaling and Video upscaling==
  
In computer graphics and digital imaging, image scaling refers to the resizing of a digital image. In video technology, the magnification of digital material is known as upscaling or resolution enhancement.
+
===Universal Models===
 +
 
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
|-
 +
 
 +
 
 +
|[https://drive.google.com/drive/folders/1YCLuYo_xDErhBi9GkHSTvzPfxIDcvhZW?usp=sharing CountryRoads]
 +
|[[User:EzoGaming|EzoGaming]]
 +
|4x
 +
|WTFPL
 +
|ESRGAN
 +
|Universal Upscaler
 +
|2021-08-26
 +
|Streets with dense foliage in the background. Outdoor scenes.
 +
|[https://drive.google.com/drive/folders/1ldwajXL50uC7PCS63B4Wato6Dnk-svNL 4xPSNR]
 +
|https://cdn.discordapp.com/attachments/547949806761410560/880291337373618236/unknown.png, https://media.discordapp.net/attachments/547949806761410560/880290211026853918/unknown.png, https://media.discordapp.net/attachments/547949806761410560/880299665428447232/unknown.png, https://cdn.discordapp.com/attachments/880291340301254657/880303552315146340/unknown.png
 +
|-
 +
 
 +
| [https://u.pcloud.link/publink/show?code=kZgSLsXZ0M1fT3kFGfRXg2tNtoUgbSI4kcSy Remacri]
 +
| Foolhardy
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
|
 +
| General Upscaler
 +
| 2021-04-09
 +
| A creation of BSRGAN with more details and less smoothing, made by interpolating IRL models such as Siax, Superscale, Superscale Artisoft, Pixel Perfect, etc. This was, things like skin and other details don't become mushy and blurry.
 +
| none - interpolated
 +
|
 +
|-
 +
 
 +
|[https://mega.nz/folder/zUJjnCoB#_zK3vs5iW6atyElO735XDA UniScale-Balanced/Strong (Includes Interp)]
 +
|[[User:Kim2091|Kim2091]]
 +
|4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
|ESRGAN
 +
|Universal Upscaler
 +
|2021-08-23
 +
|UniScale strikes a nice balance between sharpness and realism. This model can upscale almost anything well. It was originally intended to upscale game textures, but was expanded into a universal upscaler. Interp is these two models interpolated.
 +
|[https://mega.nz/#!uhAVEaAA!qfwIQ44Ba3rXMAb2-M3aM3zFBCwzmyQ64IO_0O-csJE 4xESRGAN]
 +
|https://slow.pics/c/i75q0yN1
 +
|-
 +
 
 +
|[https://mega.nz/folder/zUJjnCoB#_zK3vs5iW6atyElO735XDA UniScaleNR-Balanced/Strong]
 +
|[[User:Kim2091|Kim2091]]
 +
|4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
|ESRGAN
 +
|Universal Upscaler
 +
|2021-08-23
 +
|Version of UniScale trained with camera noise injection (NR = Noise Removal). This model removes noise from images while upscaling.
 +
|[https://mega.nz/#!uhAVEaAA!qfwIQ44Ba3rXMAb2-M3aM3zFBCwzmyQ64IO_0O-csJE 4xESRGAN]
 +
|https://slow.pics/c/UkCwdK13
 +
|-
 +
 
 +
|[https://mega.nz/folder/zUJjnCoB#_zK3vs5iW6atyElO735XDA UniScale_Restore]
 +
|[[User:Kim2091|Kim2091]]
 +
|4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
|ESRGAN
 +
|Universal Upscaler
 +
|2021-08-27
 +
|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.
 +
|[https://mega.nz/#!uhAVEaAA!qfwIQ44Ba3rXMAb2-M3aM3zFBCwzmyQ64IO_0O-csJE 4xESRGAN]
 +
|https://cdn.discordapp.com/attachments/880826637543964712/880934732748169226/unknown.png, https://cdn.discordapp.com/attachments/880826637543964712/880932754102026290/unknown.png
 +
|-
 +
 
 +
|[https://mega.nz/folder/zUJjnCoB#_zK3vs5iW6atyElO735XDA UniScaleV2_Soft/Moderate/Sharp]
 +
|[[User:Kim2091|Kim2091]]
 +
|4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
|ESRGAN
 +
|Universal Upscaler
 +
|2021-09-06
 +
|This model set is much sharper overall than UniScale V1. These models work great on game textures when interpolated 50/50 with UniScale_Restore, and work amazingly on uncompressed images. DO NOT USE FOR COMPRESSED IMAGES, use the original UniScale for that.
 +
|[https://mega.nz/#!uhAVEaAA!qfwIQ44Ba3rXMAb2-M3aM3zFBCwzmyQ64IO_0O-csJE 4xESRGAN]
 +
|https://cdn.discordapp.com/attachments/884239326471393331/884296266857713704/unknown.png https://cdn.discordapp.com/attachments/884239326471393331/884294468709257216/unknown.png https://cdn.discordapp.com/attachments/884239326471393331/884298572894441512/unknown.png https://cdn.discordapp.com/attachments/884239326471393331/884302370136289323/unknown.png
 +
|-
 +
 
 +
| [https://e.pcloud.link/publink/show?code=XZ6msZu8BOExSFH4SxixhuxoyrmbRYGQQk Misc]
 +
| [[User:Alsa|Alsa]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| General Upscaler
 +
|
 +
| The Misc model is trained on various pictures shot by myself ([[User:Alsa|Alsa]]), including bricks, stone, dirt, grass, plants, wood, bark, metal and a few others.
 +
| [http://www.mediafire.com/file/w3jujtm752hvdj1/Manga109Attempt.pth.zip/file Manga109Attempt]
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/file/d/1IHp3Ibs3B8wSKZg2iGAVy4DP5bTSTOBb/view FuzzyBox]
 +
| |[[User:BlueAmulet|BlueAmulet]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| General upscaler
 +
| 2020-07-21
 +
| Photographs, Artwork, Textures, Anything really - Tried out a new pixel loss idea based on ensuring the HR downscaled matches the LR. Colors are pretty good as well as edges, but generated details seem slightly fuzzy hence the name.
 +
| RRDB_ESRGAN_x4
 +
|
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/u/1/uc?id=10h8YXKKOQ61ANnwLjjHqXJdn4SbBuUku&export=download Lollypop]
 +
| |[[User:LyonHrt|LyonHrt]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| General upscaler
 +
| 2020-09-11
 +
| A universal model, that is aimed at prerendered images, but handles realistic faces, manga, pixel art and dedithering as well. Trained using the patchgan discriminator, with cx loss, cutmixup and frequency separation, it produces good results with a slight grain due to patchgan, with some sharpening using cutmixup.
 +
| 4X_esrgan.pth
 +
|
 +
|-
  
===Drawings===
 
  
Drawing is a form of visual art in which a person uses various drawing instruments to mark paper or another two-dimensional medium. Instruments include graphite pencils, pen and ink, various kinds of paints, inked brushes, colored pencils, crayons, charcoal, chalk, pastels, various kinds of erasers, markers, styluses, and various metals (such as silverpoint). Digital drawing is the act of using a computer to draw. Common methods of digital drawing include a stylus or finger on a touchscreen device, stylus- or finger-to-touchpad, or in some cases, a mouse. There are many digital art programs and devices.
 
  
====Manga/Anime====
+
| [https://drive.google.com/drive/u/1/folders/15dV3rhMcq_LXg5Vrn7DG6lwo4M6cXt6C UniversalUpscalerV2]
 +
| |[[User:Mutin_Choler|Mutin_Choler]]
 +
| 4x
 +
| WTFPL
 +
| ESRGAN
 +
| General Upscaler
 +
| 2021-04-01
 +
| General Upscaler
 +
| 1xESRGAN
 +
| https://imgsli.com/NDc3ODA/2/1
 +
|-
  
 +
 +
| [https://icedrive.net/1/43GNBihZyi NMKD Siax ("CX")]
 +
| |[[User:nmkd|Nmkd]]
 +
| 4x
 +
| WTFPL
 +
| ESRGAN
 +
| General upscaler
 +
| 2020-11-06
 +
| Universal upscaler for clean and slightly compressed images (JPEG quality 75 or better)
 +
| 4xPSNR
 +
|
 +
|-
 +
|}
 +
 +
===Realistic Photos===
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://mega.nz/file/STI3kIKJ#mr3PqAu35SI9yGHWUdCJsXm2kai1R1SrsYsBafyH-Vo 4x-Valar]
 +
| musl
 +
| 4x
 +
| CC0
 +
| ESRGAN+
 +
| Realistic Photos
 +
| 2021-09-16
 +
| Meant as an experiment to test latest techniques implemented on traiNNer, including: AdaTarget, KernelGAN, UNet discriminator, nESRGAN+ arch, noise patches, camera noise, isotropic/anisotropic/sinc blur, frequency separation, contextual loss, mixup, clipL1 pixel loss, AdamP optimizer, etc. The config file is provided on the download link above. I encourage everybody to mirror the model, distribute and modify it in anywway you want.
 +
| 4x_RRDB_ESRGAN
 +
| [https://cdn.discordapp.com/attachments/579685650824036387/888256099986321408/5.png Sample 1]
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/1KToK9mOz05wgxeMaWj9XFLOE4cnvo40D/view 4x_Box]
 +
| buildist
 +
| 4x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| Realistic Photos
 +
| 2019-06-20
 +
| RRDB_ESRGAN_x4 replacement for stuff that's supposed to look realistic.
 +
| none
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/1d89zvzC6BKf5EKapBtc4MH2DX5GClKzl/view Nickelback]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 4x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| Realistic Photos
 +
| 2020-02-12
 +
| this model aims to improve further on what has been achieved by the regular 4xESRGAN and also 4xBox. It can upscale most pictures/photos (granted they are clean enough) without destroying as much detail as the aforementioned models. It generates less moiré like patterns and keeps details without oversharpening or blurring the image too much.
 +
| 4xESRGAN
 +
|
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/1GL0OjGPsMwSmCr_FmkqtRjZu2IM0s019/view NickelbackFS]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 4x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN-FS
 +
| Realistic Photos
 +
| 2020-07-10
 +
| This model aims to improve further on what has been achieved by the old Nickelback which was an improvement attempt over 4xESRGAN and also 4xBox. It can upscale most pictures/photos (granted they are clean enough) without destroying as much detail as Box and basic ESRGAN.
 +
| 4xESRGAN
 +
|
 +
|-
 +
 
 +
| [https://icedrive.net/1/43GNBihZyi 4x NMKD Superscale]
 +
| |[[User:nmkd|Nmkd]]
 +
| 4x
 +
| WTFPL
 +
| ESRGAN
 +
| Clean Real-World Images
 +
| 2020-07-22
 +
| Upscaling of realistic images/photos with noise and compression artifacts
 +
| 4xESRGAN
 +
|
 +
|-
 +
|}
 +
 
 +
 
 +
===Art/Pixel Art===
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://drive.google.com/open?id=1LFd4BqZ2N8p21JzjLX6hGdm7RpVIkH7s 4x_xbrz_90k]
 +
| LyonHrt
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Pixel Art
 +
| 2019-06-05
 +
| Xbrz style pixel art upscaler
 +
| 4xPSNR
 +
|
 +
|-
 +
 
 +
| [https://drive.google.com/u/1/uc?id=1WXJQzqVGTKaX_8_Ma1hJ45W5nUkZBGFu&export=download Rebout]
 +
| LyonHrt
 +
| 4x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Pixel Art/Sprites
 +
| 2019-08-04
 +
| For upscaling character sprites
 +
| Detoon
 +
|
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/u/1/uc?id=1h-bY4gq_61sRF_xK3F4OiVK1cWRX0Q9w&export=download Rebout Blend]
 +
| |[[User:LyonHrt|LyonHrt]]
 +
| 4x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Pixel Art/Sprites
 +
|
 +
| Dataset: Custom prepared sprites from kof 94 rebout, which with gradients blending
 +
| Detoon
 +
|
 +
|-
 +
 
 +
 
 +
| [https://u.pcloud.link/publink/show?code=kZ4WthXZDDnqbo4Hye8zBgCkhgbbQf3WXT27 Arzenal (v1.1)]
 +
| ComputerK
 +
| 8x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Pixel Art
 +
|
 +
| Smooth general pixel art, Minecraft textures
 +
| [https://nmkd.de/?esrgan-list Interpolated from nmkd's pixel art upscaling models with different interpolation settings and de-dithered versions]
 +
|
 +
|-
 +
 
 +
| [https://drive.google.com/open?id=1jE2le5Lsab-AcMUMm0Zr9L-OvFNhnRAG 4x_scalenx_90k]
 +
| LyonHrt
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Pixel Art
 +
| 2019-06-15
 +
| Scalenx style pixel art upscaler
 +
| 4xPSNR
 +
|
 +
|-
 +
 
 +
| [https://drive.google.com/open?id=1h5YufgcS1jbCdqwsw7dye0DvLj3kIfox 4x_xbrz+dd_260k]
 +
| LyonHrt
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Pixel Art
 +
| 2019-06-17
 +
| xbrz plus dedithering style pixel-art upscaling model to wiki under specialised
 +
| 4x_xbrz_90k
 +
|
 +
|-
 +
 
 +
 
 +
| [https://1drv.ms/u/s!Aip-EMByJHY20xsc9EvnxVZ50Ja7 Lady0101_208000.pth]
 +
| DinnJerr
 +
| 4x
 +
|
 +
| ESRGAN
 +
| Pixel Art/Paintings
 +
| 2019-07-25
 +
| Upscale pixel art/paintings to digital painting style
 +
| WaifuGAN_v3_30000.pth
 +
|
 +
|-
 +
 
 +
 
 +
 
 +
| [https://de-next.owncube.com/index.php/s/LQSgW98ZeaoA3Po Fatality (4x_Fatality_01.pth)]
 +
| [[User:twittman|twittman]]
 +
| 4x
 +
|
 +
| ESRGAN
 +
| Pixel Art/Sprites
 +
| 2019-07-29
 +
| Upscales medium resolution Sprites, dithered or undithered, can also upscale manga/anime and gameboy camera images.
 +
| 4x_Faces_04_N_180000_G.pth
 +
|
 +
|-
 +
 
 +
 
 +
| [https://de-next.owncube.com/index.php/s/bT8nHoK4oD2MjoH Fatality MK2 (4x_Fatality_MKII_90000_G.pth)]
 +
| [[User:twittman|twittman]]
 +
| 4x
 +
|  
 +
| ESRGAN
 +
| Pixel Art/Sprites
 +
|  
 +
| Dataset: Anime, Manga and some real life
 +
| A previously attempted MK2
 +
|
 +
|-
 +
 
 +
 
 +
| [https://de-next.owncube.com/index.php/s/KRa4bDzZpAGgyWr Fatal Pixels (4x_FatalPixels_340000_G.pth)]
 +
| [[User:twittman|twittman]]
 +
| 4x
 +
|
 +
| ESRGAN
 +
| Pixel Art/Sprites
 +
|
 +
| Dataset: Anime, Manga
 +
| Fatality_MKII_90k
 +
|
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/open?id=1BzT-KwUBiZzACxGdIN6w930aOVvvfhg7 Faithful 2x]
 +
| Joey
 +
| 2x
 +
| CC-BY-NC 4.0
 +
| ESRGAN
 +
| Pixel Art
 +
| 2019-09-08
 +
|
 +
| 2xESRGAN
 +
|
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/file/d/114yFJKeYCcr6st7aNNo9FJ8wDbEzLpdz/view?usp=sharing deviantPixelHD]
 +
| raulsangonzalo
 +
| 4x
 +
| You're free to use this model for all non-commercial projects and interpolation, please give credit if featured in any projects
 +
| ESRGAN
 +
| Pixel Art
 +
| 2019-09-09
 +
| Similar to Manga109, can be used as a general digital upscaler as well as with pixel art
 +
| RRDB_PSNR_x4
 +
| https://www.youtube.com/channel/UCwBfuiHdSPQ-zslOmiW8OHg
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/1hLhsp3aKurLys4cALQiEkYxyxGWNf1ET/view?usp=drivesdk 4x_BS_Deviance]
 +
| systemd-resolved/BlackScout
 +
| 4x
 +
| GNU GPLv3
 +
| ESRGAN
 +
| Art
 +
| 2020-02-25
 +
| This model upscales Digital Drawings. It was trained on random drawings found on DeviantArt. Mostly Landscape and Scenery and Illustrations of Characters. It does fairly well and works on many different styles.
 +
| 4xESRGAN
 +
|
 
|-
 
|-
|[http://www.mediafire.com/file/w3jujtm752hvdj1/Manga109Attempt.pth.zip/file Manga109Attempt]||Kingdomakrillic||4||[https://creativecommons.org/licenses/by/4.0/ CC BY 4.0]||Anime / Manga||?||4||?||0.1K||Manga109||RRDB_PSNR_x4
+
 
 +
 
 +
| [https://drive.google.com/open?id=1Uc9RUc2YpZKpPoGQeGxNUb3Ro-U720cH 4xSmoothRealism]
 +
| Joey
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Pixel Art
 +
| 2020-03-04
 +
| Pixel art, rocky/grainy textures? Quantization smoothing, adding detail.
 +
| 4x_RRDB_PSNR_old_arch.pth
 +
|
 
|-
 
|-
|[https://drive.google.com/open?id=1bqyG9llxkJ6i6MJTaNUiSgSXtrlPi0d7 Falcon Fanart]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Anime / Manga||125K||8||128||3.393K||Falcon Fanart||RRDB_PSNR_x4
+
 
 +
| [https://1drv.ms/u/s!Aip-EMByJHY26nuB0Lo0rdirfGoi?e=XI9Fa2 8x_HugePeeps_v1]
 +
| DinJerr
 +
| 8x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Art/People
 +
| 2020-06-16
 +
| Painted humans
 +
| TGHQFace8x
 +
|  
 
|-
 
|-
|[https://1drv.ms/u/s!Aip-EMByJHY20wpGoLuSRzjdqh0T WaifuGAN v3]||[[User:DinJerr|DinJerr]]||4||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||Anime / Manga||30K||2||128||0.173K||CG-Painted Anime||Manga109v2
+
 
 +
| [https://1drv.ms/u/s!Aip-EMByJHY27CHg3-1Uue5KgbtK?e=6k0COU BigFace_v3_Clear]
 +
| DinJerr
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Art/People
 +
| 2020-07-22
 +
|  
 +
| 4x_BigFace
 +
|
 
|-
 
|-
|[https://drive.google.com/open?id=1uJvdx3g3GEY0VxMnHb0ItBvoc6pmGvuH De-Toon]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Toon Shading / Sprite||225K||8||128||7.117K||Custom Cartoon-style photos||RRDB_PSNR_x4
+
 
 +
| [https://drive.google.com/file/d/1OVqM2D-T5meRBCdFjsGVl0bgQZd8kZe5/view?usp=drivesdk 4x_BS_DevianceV2]
 +
| systemd-resolved/BlackScout
 +
| 4x
 +
| GNU GPLv3
 +
| ESRGAN-FS
 +
| Art
 +
| 2020-07-25
 +
| upscales Digital Drawings. It was trained on random drawings found on DeviantArt. Mostly Landscape and Scenery and Illustrations of Characters. It does fairly well and works on many different styles.
 +
| 4xESRGAN
 +
|
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/1OVqM2D-T5meRBCdFjsGVl0bgQZd8kZe5/view?usp=drivesdk 4x_BS_DevianceMIP]
 +
| systemd-resolved/BlackScout
 +
| 4x
 +
| GNU GPLv3
 +
| ESRGAN-FS
 +
| Art
 +
| 2020-07-25
 +
| upscales Digital Drawings. It was trained on random drawings found on DeviantArt. Mostly Landscape and Scenery and Illustrations of Characters. It does fairly well and works on many different styles.
 +
| 4xESRGAN
 +
|
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/file/d/1RhEkTYy-1DxJP2ynLW5NSrz6BjVMy8xx/view 4x_Struzan]
 +
| Laserschwert
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Art
 +
| 2020-10-12
 +
| Upscaling airbrush/pencil-based artwork
 +
| 4xPSNR
 +
| https://drive.google.com/drive/folders/1fyeIWInDrM6r-xxrCW4U09oafWw08u9S?usp=sharing
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/drive/u/1/folders/1C82o6p9jXzOZIZtMHeVXFW8BYV0s10FA 4x_PixelPerfectV4_137000_G]
 +
| Mutin Choler
 +
| 4x
 +
| WTFPL
 +
| ESRGAN
 +
| Pixel Art/Sprites
 +
| 2020-11-16
 +
| Sprite Upscaler
 +
| 4xESRGAN
 +
| https://imgsli.com/MzgxMTc/1/2
 
|-
 
|-
|[https://drive.google.com/open?id=103MX2bvd3GW0MYpC53ABU5VYY6v1t99Y DigiPaint]||TheAtheistGod||4||[https://creativecommons.org/publicdomain/zero/1.0/ CC0]||Digital Art Upscaler||35K||6||128||48.493K||Misc digital art, material studies||4xfalcoon300(manga)
+
 
 +
| [https://1drv.ms/u/s!Aip-EMByJHY200v-vXPezsCsUd5T?e=r7mBNn BigFArt]
 +
| DinJerr
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Pixel art
 +
| 2020-15-31
 +
| Larger-scaled pixels to digital painting
 +
| Face Focus
 +
|  
 
|-
 
|-
|[https://drive.google.com/file/d/114yFJKeYCcr6st7aNNo9FJ8wDbEzLpdz/view?usp=sharing DeviantPixelHD]||Raulsangonzalo||4||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||Digital Art Upscaler||250K||16||128||2.797K||Digital Art from Deviant Art||RRDB_PSNR_x4
+
 
 +
 
 +
| [https://u.pcloud.link/publink/show?code=kZPTiBXZPnCIVsFUmrpu4NY1sKfKw8Pyw6rk MS Unpainter]
 +
| FoolhardyVEVO
 +
| 8x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Pixel Art
 +
| 2021-03-24
 +
| Low-resolution MS Paint drawings, general pixel art, and general dithered pixel art, all kinds of pixel art
 +
| A mix of: 8x_glasshopper_ArzenalV1.1, 8x_glasshopper_MS-Unpainter, 8x_NMKD-Sphax + Sphax de-dither, and 8x_NMKD-YanderePixelArt4 + Yandere De-Dither, all interpolated with adjustments using the interpolate function in Cupscale
 +
|  
 
|-
 
|-
 +
 +
| [https://u.pcloud.link/publink/show?code=kZPTiBXZPnCIVsFUmrpu4NY1sKfKw8Pyw6rk MS Unpainter De-Dither]
 +
| FoolhardyVEVO
 +
| 8x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Pixel Art
 +
| 2021-03-24
 +
| Low-resolution MS Paint drawings, general pixel art, and general dithered pixel art, all kinds of pixel art
 +
| A mix of: 8x_glasshopper_ArzenalV1.1, 8x_glasshopper_MS-Unpainter, 8x_NMKD-Sphax + Sphax de-dither, and 8x_NMKD-YanderePixelArt4 + Yandere De-Dither, all interpolated with adjustments using the interpolate function in Cupscale
 +
|
 
|-
 
|-
|[https://drive.google.com/file/d/1hLhsp3aKurLys4cALQiEkYxyxGWNf1ET/view?usp=drivesdk BS_Deviance]||[[User:BlackScout|BlackScout]]||4||[https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]||Digital Art Upscaler||60K||12||128||5.435K||Digital Art from DeviantArt||4xESRGAN
+
 
 +
| [https://1drv.ms/u/s!Aip-EMByJHY22BhfdJ1Epkfc3ugq?e=yVfXkz UltraFArt_v3 / FArtDIV3 Suite]
 +
| DinJerr
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Art
 +
| 2021-05-14
 +
| Painting style with larger shaped features (?).
 +
| 4x_UltraFArt
 +
| https://1drv.ms/u/s!Aip-EMByJHY27UIFr1mk87zFytap?e=ZZliII
 
|-
 
|-
|[https://drive.google.com/open?id=192Mw2_yUwCgqt3tAJ2sRxZ8hYHe4CKrZ FireAlpha]||[[User:BlueAmulet|BlueAmulet]]||4||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||Artwork with an alpha channel||1.285M|| ||128||104k tiles, 1.2k imgs||Fire Emblem artwork with transparency||None
+
 
 +
| [https://drive.google.com/drive/folders/1mYTMpwDlKQulBmjgKpcxL3-T6xAGXVxl?usp=sharing NXbrz]
 +
| Archerpolation
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Pixel Art
 +
| 2021-06-09
 +
| Basic pixel art upscaling, for people who want a more simpler style and lightweight pixel art upscaling model.
 +
| https://drive.google.com/drive/folders/1mYTMpwDlKQulBmjgKpcxL3-T6xAGXVxl?usp=sharing
 
|-
 
|-
|[https://drive.google.com/open?id=1Vtwt9kgnmju1edibl07WI6Rg7CrAlHIx 4xFSDedither_Manga]||Jacob_ (buildist)||4||GNU GPL v3||Manga and pixel art||200K||16||128||1,526||Manga109 copied 14 times with different dithering and scaling||RRDB_ESRGAN_x4.pth
 
 
|}
 
|}
  
Manga109Attempt is slightly blurry, but performs well as a general upscaler.
+
===Drawn Material===
  
Falcoon Fanart tries to improve upon it with the goal of removing checkerboard patterns / and dithering. It has oil color based shading with sharp lines.
+
====Anime====
  
WaifuGAN v3 is [[User:DinJerr|DinJerr]]’s third attempt at training from a mostly anime dataset sourced from image boards and is intended for upscaling CG-painted anime with variable outlines. Only PNGs were used, mainly with brush strokes and gradients. Texturised images avoided as much as possible. If too generative, tone down by interpolating with a softer model.
+
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
  
De-Toon, is a model that does the opposite of tooning an image. It takes toon style shading and detail, and attempts to make it realistic. Its very sensitive, and can be used on small sprites, to large images. Also included is a alt version, which is less sharp.
 
  
DigiPaint is a digital art upscaler designed to take brush strokes into account, based off of the Falcoon Fanart model.
+
|-
 +
| [https://drive.google.com/open?id=1H3F8OVBnK2cd5NjbCyc3tGwTZJBF1gk7 Sol Levante NTSC2HD]
 +
| Phoenix
 +
| 4x
 +
| UNLICENSE
 +
| ESRGAN
 +
| Anime/Pretrained
 +
| 2020-04-08
 +
| NTSC DVD-spec encode x4 scale super-resolution for Anime Drawing style content. The dataset has a LOT of data throughout almost every frame, so it had a lot of stuff to learn. The resulting DVD-spec encode also had some blocking at times so it also learned to fight off blocking.
 +
| RRDB_PSNR_x4
 +
|
 +
|-
  
DeviantPixelHD was designed to upscale original LucasArts games' backgrounds. High Definition digital art from Deviant Art was used, reducing the LR training to 32 colors so the training images looked pixelated. Can be used with other environments such as manga or digital art. Examples can be found on Raúl Sangonzalo's YouTube account (<nowiki>https://www.youtube.com/channel/UCwBfuiHdSPQ-zslOmiW8OHg</nowiki>).
+
|-
 +
| [https://drive.google.com/file/d/1FWzEgqaSg2z0qOSjcmAxEUB3clEkm1PG/view 2x_Byousoku_5_Centimeter.pth]
 +
| Mystery_Bullet#0642 (Shady Adel)
 +
| 2x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| Anime/Pretrained
 +
| 2020-04-08
 +
| Anime landscape upscale. Trained on Frames from BluRay of Byousoku 5 Centimeter
 +
| [https://mega.nz/#!vtgSWKQT!K7Asn2zKe4N70R2aV89KEMTKhH3aiyGAAiuQDJF09qs 2xESRGAN]
 +
|
 +
|-
  
FireAlpha is an attempt to create a 4 channel model that handles transparency without splitting and upscaling separately.
+
| [https://1fichier.com/?tsmmdifzgwkwtdfcc5uo 4x_OLDIES_290000_G_FINAL]
 +
| solidd93110
 +
| 4x
 +
| WTFPL
 +
| ESRGAN
 +
| Anime
 +
| 2020-08-16
 +
| i made this model to upscale old anime and denoise.
 +
| RRDB_PSNR_x4.pth
  
*'''''Notice:''' IEU can use the model but will attempt to split and handle transparency itself, BlueAmulet's fork of ESRGAN is required to use this model. https://github.com/BlueAmulet/ESRGAN''
+
|
 +
|-
 +
| [https://www23.zippyshare.com/v/lhOStpVa/file.html fidelbd_pokemodel]
 +
| Neo-Raws#4055
 +
| 2x
 +
| WTFPL
 +
| ESRGAN
 +
| Anime
 +
| 2020-08-29
 +
| Made this model to upscale old anime that looks blurry.
 +
| 2xESRGAN
  
4xFSDedither_Manga was intended for pixel art containing dithering patterns, but ended up being effective on pixel art and manga/cartoon style images without any dithering at all.
+
| https://imgsli.com/MjExMjQ/
 +
|-
  
====Cartoon / Comic====
+
| [https://1fichier.com/?u7kwdxdn6uljha3icte8 4x_OLDIES_ALTERNATIVE_FINAL.pth]
 +
| solidd93110
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Anime
 +
| 2020-09-01
 +
| This model was made for my project captain tsubasa anime so i don't know if it works good for anything else. just try it ;)
 +
| RRDB_PSNR_x4.pth
 +
 
 +
| https://imgsli.com/MjEzMDU
 +
|-
 +
 
 +
| [https://1fichier.com/?cnw3fwws08tdoaxycimj 2x_SHARP_ANIME_V1]
 +
| solidd93110
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Anime
 +
| 2020-09-12
 +
| this model has been trained to work on lines and details - works well on animes which have fairly fine lines at the base but also the video must be progressive or deinterlaced
 +
| 2xPSNR.pth
 +
 
 +
| https://imgsli.com/MjIwMDY
 +
|-
 +
 
 +
| [https://s.katou.pw/4x_MeguUp_150000_G.pth MeguUp]
 +
| /katoumegumi_#3231
 +
|
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3].
 +
| ESRGAN
 +
| Anime
 +
| 2020-09-16
 +
| Upscaling of lossless (uncompressed) anime art.
 +
| interpolated - SYNLA: |[[User:LyonHrt|LyonHrt]] (bloc97 dataset, MIT license). Fatal Pixels, Fatality Anime: Twittman (CC BY-NC-SA 4.0, acquired special permission to relicense. https://s.katou.pw/Discord_dPUiI1x3Pf.png). Deviance: |[[User:BlackScout|BlackScout]] ([https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3])
 +
 
 +
|
 +
|-
 +
 
 +
 
 +
| [https://icedrive.net/1/43GNBihZyi NMKD UltraYandere]
 +
| |[[User:nmkd|Nmkd]]
 +
| 4x
 +
| WTFPL
 +
| ESRGAN
 +
| Art/Anime
 +
| 2020-10-08
 +
| Highly flexible 2D Art upscaling
 +
| 4xESRGAN
 +
 
 +
|
 +
|-
 +
 
 +
| [https://icedrive.net/1/43GNBihZyi NMKD UltraYandere Lite]
 +
| |[[User:nmkd|Nmkd]]
 +
| 4x
 +
| WTFPL
 +
| ESRGAN Lite [nf=32 nb=12]
 +
| Anime
 +
| 2020-10-15
 +
| Fast Anime/Art upscaling
 +
| 4x_DIV2K-Lite
 +
 
 +
|
 +
|-
 +
 
 +
| [https://www115.zippyshare.com/v/O2do1VCf/file.html 2x_pokemodel_lite_100000_G]
 +
| Neo-Raws#4055
 +
| 2x
 +
| WTFPL
 +
| ESRGAN
 +
| Anime
 +
| 2020-11-01
 +
| Upscale old anime like pokemon
 +
| none
 +
 
 +
| https://imgsli.com/Mjc3Nzk https://imgsli.com/Mjc3Nzg https://imgsli.com/Mjc3ODA https://imgsli.com/Mjc3ODE https://imgsli.com/Mjc3ODI
 +
|-
 +
 
 +
 
 +
| [https://1fichier.com/?020t1y83kjrusd95dh0a 2x_SHARP_ANIME_V2]
 +
| solidd93110
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Anime
 +
| 2020-12-09
 +
| 2x_PSNR.pth
 +
|
 +
| https://imgsli.com/MzI0MDk
 +
|-
 +
 
 +
| [https://1fichier.com/?23hzkj20isef5b75cw3y 2x_BIGOLDIES_415000_G.pth]
 +
| solidd93110
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Anime
 +
| 2020-12-09
 +
| upscaling old anime. help to denoise and find lines and dehalo
 +
| 2x_PSNR.pth
 +
| https://imgsli.com/MzI0MDc
 +
|-
 +
 
 +
 
 +
| [https://icedrive.net/1/f0UAiRqz3N NMKD YandereNeo]
 +
| |[[User:nmkd|Nmkd]]
 +
| 2x
 +
| WTFPL
 +
| ESRGAN (Lite)
 +
| Anime
 +
| 2021-01-26
 +
|
 +
|
 +
| https://i.imgur.com/oxs71v5.png
 +
 
 +
 
 +
|-
 +
| [https://icedrive.net/1/f0UAiRqz3N NMKD YandereNeo]
 +
| |[[User:nmkd|Nmkd]]
 +
| 4x
 +
| WTFPL
 +
| ESRGAN (Lite)
 +
| Anime
 +
| 2021-01-26
 +
|
 +
| 4x_DIV2K-Lite_1M
 +
| https://i.imgur.com/oxs71v5.png
 +
|-
 +
 
 +
| [https://u.pcloud.link/publink/show?code=XZRAmuXZRy3vkvvBdTftheNOFeJ0tLLv74eX 2x_Waifaux-NL3-SuperLite]
 +
| Joey
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
|
 +
| 2021-02-23
 +
| Trained this model to see how it would work trying to essentially get the same results as Waifu2x but with ESRGAN
 +
| none
 +
|
 +
|-
 +
 
 +
| [https://u.pcloud.link/publink/show?code=XZPLWuXZbQz9nPrUhlytIN0ne4UjyzQRMHmX 2x_Waifaux-NL3-SRResNet]
 +
| Joey
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| EDSR (SRResNet)
 +
|
 +
| 2021-02-25
 +
| Emulating Waifu2x at Noise Level 3 NOTE: You can't use this with regular esrgan forks or the bot, it has to be run through basicsr
 +
| none
 +
|
 +
|-
 +
 
 +
| [https://u.pcloud.link/publink/show?code=kZcUlBXZ9egcFjtf3cjX02lDqNAr5j4l3jFX 4x_Training4Melozard_Anime]
 +
| Joey
 +
| 4x
 +
| Whatever @B.Melozard2 wants
 +
| ESRGAN
 +
| Anime
 +
| 2021-03-17
 +
|
 +
| RRDB_ESRGAN_x4_old_arch
 +
|
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/18iWj4eWiMfUd2WyLCEzMlZK1JVT7L8nT/view?usp=sharing 2x_LD-Anime_Skr_v1.0]
 +
| Skr
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Denoise/Dehalo
 +
| 2021-04-17
 +
| Denoise, dehalo, derainbow old anime
 +
| 2xESRGAN
 +
| https://imgsli.com/NTA3MDU/
 +
|-
 +
 
 +
| [https://drive.google.com/drive/u/4/folders/19IQNM5Vo5vGcoKaRJaRrLScfxBbFBVff 2x_KemonoScale_v2]
 +
| EzoGaming
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Anime
 +
| 2021-06-05
 +
| Upscaling frames from Irodori anime (namely kemono friends) from 540p (the source render resolution) to 1080p, low resolution flat shaded art, de-JPEG of the aforementioned
 +
| x2_CGIMaster_v1
 +
| https://cdn.discordapp.com/attachments/705815801290293329/850614850735439892/unknown.png
 +
|-
 +
 
 +
| [https://s.katou.pw/4x_muy4_035_1.pth 4x_muy4_035_1.pth]
 +
| katoumegumi_
 +
| 4x
 +
| WTFPL
 +
| ESRGAN
 +
| Anime
 +
| 2021-07-18
 +
| Upscaling of anime art (Specifically visual novel CG art)
 +
|
 +
| https://cdn.knightlab.com/libs/juxtapose/latest/embed/index.html?uid=278999ec-e802-11eb-abb7-b9a7ff2ee17c (Hakurei Reimu from Touhou Project illustrated by "okawa friend") https://cdn.knightlab.com/libs/juxtapose/latest/embed/index.html?uid=f3d4781a-e801-11eb-abb7-b9a7ff2ee17c (Kitaooji Karen from Making * Lovers developed by SMEE.)(edited)
 +
|-
 +
 
 +
| [http://www.mediafire.com/file/w3jujtm752hvdj1/Manga109Attempt.pth.zip/file Falcon Fanart]
 +
| |[[User:LyonHrt|LyonHrt]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Anime
 +
| not on discord
 +
|
 +
| 4xPSNR
 +
|
 +
|-
 +
|}
 +
 
 +
====Manga====
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 
|-
 
|-
|[https://drive.google.com/open?id=1qjpxp8z4FGLZxieUDEVKd6FDum-8vpvJ Comic Book]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Comic / Drawings||115K||8||128||1.548K||Custom (Spider-Man)||none (no interpolation)
+
| [https://drive.google.com/file/d/1uraeNuUPx46HKZ77xUI1PCBBoH-LhikY/view?usp=sharing FSMangaV2]
 +
| Jacob_
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Manga
 +
| 2020-12-14
 +
| Manga-style images with or without dithering - cartoons, maybe pixel art, etc
 +
| RRDB_PSNR_x4
 +
| https://i.imgur.com/oVBVthF.png
 
|-
 
|-
 +
 +
| [https://mega.nz/file/nR51EYYC#RcAKkxb8hAzvZAj4TLxnAukd9gbrYuUeyjUp2l1ffb8 MangaScaleV3]
 +
| Bunzero++
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN+
 +
| Manga
 +
| 2021-05-24
 +
| To upscale manga including halftones, instead of trying to smooth them out.
 +
| unreleased model
 +
| https://imgsli.com/NTUyMjg
 
|-
 
|-
|[https://mega.nz/file/E1o21QRK#FoXh-5v2KITjc_cjC30HrFoh2etp1cmBkNqruMARPeA DeteriorationFrames 1.0]||Klexos||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Animation||102K||2||128||6.75K||HD to bad DVD transfer|| Scratch
+
|}
 +
 
 +
====Cartoons====
 +
{| class="wikitable sortable"
 
|-
 
|-
|[https://mega.nz/file/UhZDmYgQ#IzW5VzWV1DKAVZiORhq1ro6RxfmVBBtUFxBPe5X_NRU FilmFrames 0.5]||Klexos||2||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Film Animation||677K||3||192||250||SD to HD film rescan|| Scratch
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 
|-
 
|-
|[https://mega.nz/#!dg4UzaCJ!dFQ0RdoeCWOypoaf2MGwCru1afArBB0yuYFDFRCfJ74 DigitalFrames 1.0]||Klexos||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Clean Digital Animation||1.06M||15||128||0.25K - 2.5K||Digital Cartoon Images||RRDB_PSNR_x4
+
 
 +
 
 
|-
 
|-
 +
| [https://u.pcloud.link/publink/show?code=kZy6TKXZruJNkiysJ3R2fqxMra9RQQquMczV 8x_BoyMeBob-Redux]
 +
| Joey
 +
| 8x
 +
| CC BY-NC-SA 4.0
 +
| ESRGAN+ (Joey's fork, eFonte fork, or iNNfer required to use)
 +
| Animation
 +
| 2021-08-19
 +
| Upscaling cartoons
 +
| 8xBoyMeBob (unreleased) which used 8xESRGAN
 +
| [https://u.pcloud.link/publink/show?code=kZy6TKXZruJNkiysJ3R2fqxMra9RQQquMczV Examples]
 
|-
 
|-
|[https://mega.nz/#!twxxWQTT!OjPL0o9sq2MM6Flac1shLo9CvE33P9mKKF73OMT-j2I DigitalFrames 2.0]||Klexos||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Digital Animation||905K||27||128||1.636M||Digital Cartoon Images||RRDB_PSNR_x4
+
 
 
|-
 
|-
 +
| [https://drive.google.com/file/d/1dT7Pw0iwPkQC4-rWriibrVLuA3KS3pS4/view SpongeBob]
 +
| Joey
 +
| 4x
 +
| CC-BY-NC 4.0
 +
| ESRGAN
 +
| Animation
 +
| 2019-09-12
 +
|
 +
| 4xESRGAN
 +
|
 
|-
 
|-
|[https://mega.nz/#!lwAhQY5D!btyx5fjIRxD6GJwA8Dnnn7beUTvK_NIpDU8Qo69X-Ao DigitalFrames 2.1_Aggressive]||Klexos||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Flat Digital Animation||230K||27||128||1.8M||Digital Cartoon Images||DigitalFrames 2.0
+
 
 
|-
 
|-
 +
| [https://drive.google.com/file/d/1qoiIvjMuazD6MCw_aZ5pEPESA6Pi03oM/view Spongebob De-Quantize]
 +
| Joey
 +
| 1x
 +
| CC-BY-NC 4.0
 +
| ESRGAN
 +
| Animation - Quantized
 +
| 2019-11-02
 +
| Removed color quantization/indexing and dithering from cartoon style images and textures
 +
| 1x_1xDEDITHER_32_512_126900_G
 +
|
 
|-
 
|-
|[https://mega.nz/#!wgJ1yQAS!tY6P-9-fPKvpRouIw1uoBN3uMkzZKUbJs-WVfhIxa8E DigitalFrames 2.1_Final]||Klexos||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Digital & Traditional Animation||230K||27||128||1.8M||Cartoon Images||DigitalFrames 2.0
+
 
 +
| [https://drive.google.com/open?id=1geNLDAnQzLadMvvoRLhVy4MXhQf5t8JP 4x Spongebob v6 Deblur]
 +
| Joey
 +
| 4x
 +
| CC-BY-NC 4.0
 +
| ESRGAN
 +
| Animation
 +
| 2019-11-08
 +
| After not being entirely happy with the main Spongebob v6 model, I trained a new one with blurring OTF options and two different downscale types. This one is much better in my opinion.
 +
| 4x Spongebob v6
 +
|  
 
|-
 
|-
 +
 +
| [https://drive.google.com/open?id=1HFA1e75QvdostGAZVPBxFHtkiru5gLPa 4x Spongebob v6 De-Quantize]
 +
| Joey
 +
| 4x
 +
| CC-BY-NC 4.0
 +
| ESRGAN
 +
| Animation - Quantized
 +
| 2019-11-08
 +
| A model I trained to do both de-quantizing as well as upscaling. The results are pretty blurry but it works decently for what it is.
 +
| 4x Spongebob v6
 +
|
 
|-
 
|-
|[https://1fichier.com/?tsmmdifzgwkwtdfcc5uo Oldies_Final]||solidd93110||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Upscaling old anime & denoise||290K||16||128||31.316K||Anime frames from BD||RRDB_PSNR_x4.
+
 
 +
| [https://drive.google.com/open?id=1NHuNF36dp_myvPH__IesJ5x6GuppUwS6 4x Spongebob v6]
 +
| Joey
 +
| 4x
 +
| CC-BY-NC 4.0
 +
| ESRGAN
 +
| Animation
 +
| 2019-11-08
 +
| New version of the Spongebob model. Ideally it's a lot sharper and cleaner but I'm still not sure if it works better than the old one. From what I can tell it's better in many cases.
 +
| 4xESRGAN
 +
|  
 
|-
 
|-
|[https://de-next.owncube.com/index.php/s/jYnFtncarkBmpcF FatalimiX]||[[User:Twittman|Twittman]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Comic and Cartoon style images||260k||10||128||69k/79k||Digital Comics||4x_Fatality_MKII_90000_G_02.pth
+
 
 +
| [https://drive.google.com/open?id=1D3AjglmYlQ2HGda7iw4JXckSGbVBqsQr SpongeBob.CEL.2.HD.125ki.499e-PHOENiX.pth]
 +
| Phoenix
 +
| 4x
 +
| GPLv3 - SHARE YOUR CHANGES - If you use this as a pretrained model, share your new model!!!
 +
| ESRGAN
 +
| Animation
 +
| 2019-12-24
 +
| Restorative CEL Animation MPEG-1 and 2 Model specifically crafted for SpongeBob S01.
 +
| RRDB_PSNR_x4.pth
 +
|
 
|-
 
|-
|[https://drive.google.com/open?id=1dT7Pw0iwPkQC4-rWriibrVLuA3KS3pS4 SpongeBob]||Joey||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Cartoons & SpongeBob Games||235k||20||128||8k||Scene-detected frames from random Season 11 episodes||4xESRGAN
+
 
 +
| [https://u.pcloud.link/publink/show?code=kZ8f9HXZaNaKIDTqP9YPl33NGlz7VmaA3kqV 1x_SpongeBC1-Lite]
 +
| Joey
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
|  
 +
| BC1/DXT1 compression
 +
| 2020-11-01
 +
| First ever lite BC1/DXT1 model. Probably only useful for cartoony textures like those in spongebob games or other cartoon licensed games.
 +
| 1x_DIV2K-Lite_80k
 +
|  
 
|-
 
|-
|[https://drive.google.com/open?id=1NHuNF36dp_myvPH__IesJ5x6GuppUwS6 SpongeBob v6]||Joey||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Cartoons||190k||20||128||4,803||1 frame of every scene of season 11, downscaled 50% with nearest neighbor||4xESRGAN
+
 
 +
| [https://u.pcloud.link/publink/show?code=kZh614XZIyy5JlX7rFm4d3HJJTBovbSz3ycy 4x_SpongeBob-Reloaded]
 +
| Joey
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Animation, Pixel Art
 +
| 2020-12-11
 +
|  
 +
| 4xSpongeBob
 +
|  
 
|-
 
|-
|[https://drive.google.com/open?id=1HFA1e75QvdostGAZVPBxFHtkiru5gLPa Spongebob v6 De-Quantize]||Joey||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Quantized Cartoons||90k||20||128||4,803||1 frame of every scene of season 11, downscaled 50% with nearest neighbor||4x Spongebob v6
+
| [https://u.pcloud.link/publink/show?code=kZh614XZIyy5JlX7rFm4d3HJJTBovbSz3ycy 4x_SpongeBob-Reloaded-SWAG]
 +
| Joey
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Animation, Pixel Art
 +
| 2020-12-11
 +
|  
 +
| 4xSpongeBob
 +
|  
 
|-
 
|-
|[https://drive.google.com/open?id=1geNLDAnQzLadMvvoRLhVy4MXhQf5t8JP Spongebob v6 Deblur]||Joey||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Cartoons||65k||20||128||4,803||1 frame of every scene of season 11, downscaled 50% with nearest neighbor||4x Spongebob v6
+
 
 
|-
 
|-
|[https://1drv.ms/u/s!Aip-EMByJHY26nuB0Lo0rdirfGoi?e=XI9Fa2 HugePeeps]||[[User:DinJerr|DinJerr]]||8||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||Painted humans||360k||4||256||1,000+||A bunch of pretty girls (and guys) from ArtStation||TGHQFace8x
+
| [https://mega.nz/folder/zUJjnCoB#_zK3vs5iW6atyElO735XDA 2x-UniScale_CartoonRestore-lite]
 +
| [[User:Kim2091|Kim2091]]
 +
| 2x
 +
| CC BY-NC-SA 4.0
 +
| ESRGAN
 +
| Animation, Pixel Art
 +
| 2021-08-31
 +
| This model has VERY strong compression removal and line restructuring that allows it to restore any heavily compressed drawings, animation, cartoons, or anime. Also works on games as well as DDS compression. It renders frames very quickly and is very viable for restoring videos.
 +
| 4x-MMScale
 +
| Comparisons:
 +
https://cdn.discordapp.com/attachments/880826637543964712/882136618461458462/unknown.png
 +
https://cdn.discordapp.com/attachments/880826637543964712/882136455999262750/unknown.png
 +
https://cdn.discordapp.com/attachments/880826637543964712/882136979410673684/unknown.png
 +
https://cdn.discordapp.com/attachments/649861104645701637/882121519973666886/unknown.png
 +
https://cdn.discordapp.com/attachments/649861104645701637/882124248368427078/unknown.png
 +
Video Example:
 +
https://cdn.discordapp.com/attachments/880826637543964712/882110147676221480/Spongebob_UniScale_CartoonRestore.mp4
 +
Original for comparison: https://cdn.discordapp.com/attachments/547949806761410560/881971445813633044/Spongebob_Original.mp4
 
|-
 
|-
|[https://de-next.owncube.com/index.php/s/x99pKzS7TNaErrC Fatal_Anime]||[[User:Twittman|Twittman]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Anime and Cartoons||500k||6||128||183k||Anime and Manga images||4x_Fatality_Comix_MKII_430000_G.pth
+
 
 +
| [https://www108.zippyshare.com/v/PYWFtETd/file.html 2x_ATLA_KORRA_336200_G.pth]
 +
| aptitude
 +
| 2x
 +
|
 +
| ESRGAN
 +
| Animation
 +
| 2021-07-22
 +
| Upscaling of Animation based on The Legend of Korra.
 +
| 2xESRGAN.pth
 +
| https://imgsli.com/NjIzMzU https://imgsli.com/NjIzMTY https://imgsli.com/NjIzMTc https://imgsli.com/NjIzMTg https://imgsli.com/NjIzMTk https://imgsli.com/NjIzMjA https://imgsli.com/NjIzMjE https://imgsli.com/NjIzMjQ https://imgsli.com/NjIzMjc https://imgsli.com/NjIzMjY https://imgsli.com/NjIzMjU
 
|-
 
|-
|[https://1drv.ms/u/s!Aip-EMByJHY26wU-wOqApp7Hu7tt?e=4ihnBr HugePaint]||[[User:DinJerr|DinJerr]]||8||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||Digital Illustrations||500k||4||256||1,000+||Variety of images from ArtStation||HugePeeps
+
 
 
|}
 
|}
  
The Comic Book model was trained using stills from the film spiderman into the spiderverse, has a comic book crosshatch shading effect to the images. [https://cdn.discordapp.com/attachments/547950274313191425/564427623204388864/6de7c88f.png Sample]
+
====Digital Animation====
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
  
FilmFrames 0.5: Purpose of the model is upscaling medium quality sourced SD animation frames to an HD "Film rescan" status. https://imgsli.com/MjA2NDM
+
|-
 +
| [https://u.pcloud.link/publink/show?code=XZQlqjXZPNgmLRJl5HLLG0M3VRmzmzmHr5hk 4x_DigitalFake-2.1]
 +
| Joey
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Digital Animation
 +
| 2021-02-18
 +
| Replica of DigitalFrames 2.1 but interpolatable
 +
| RRDB_ESRGAN_x4_old_arch.pth
 +
|
 +
|-
  
DeteriorationFrames 1.0: The purpose of this model is to aid in the creation of datasets aimed at animation by saving you time and allowing you to deteriorate the HQ/HD frames directly though this model instead of having to go through frame by frame to find SD/LQ counterparts. This iteration in particular adds dot crawl, ringing and chromatic aberrations. https://imgsli.com/MTk4MjA.
+
| [https://mega.nz/folder/QsUWWJjb#SIuqcPEzrkpLW0WNSth66g 4X_KCJPUNK_1.0233089 G.pth]
Important note: Resizing your HD counterparts before using this model to create the LRs is essential.
+
| KCJPUNK
Tip: If you blur the HRs after resizing them but before using the deterioration model on them, depending on how much you blur you'll get less Chromatic aberrations. So with this you can tweak both blurriness and the aberrations to match better the source you intend to actually use the model you are about to train on.
+
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Digital Animation
 +
| 2021-03-23
 +
| Up-scaling Digital Animation
 +
| 4x_fatal_Anime_500000_G
 +
|
 +
|-
  
DigitalFrames 1.0: The purpose of this model is upscaling digital *only* animation frames while cleaning and restoring textures and details, but it can also works well on a variety of other things such as medium sized sprites and digital art. This model is highly sensitive to grain and other type of noise so if an improper input image is feed, the results can have severe blobs of noise if the source image has any type of grain, even if barely noticeable.
+
| [https://mega.nz/folder/4oVRHQaA#vE3Lplfetc9z9SJOxZD6nA 2X_KcjpunkAnime_2.0_Lite_196496_G]
 +
| KCJPUNK
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN-light
 +
| Digital Animation
 +
| 2021-03-23
 +
| Up-scaling Digital Animation
 +
| This is my first attempt to make Light model so I started with 2x version. This model is much faster and give better results than my previous one.  
 +
|
 +
|-
 +
|}
  
DigitalFrames 2.0: Was trained completely separately from 1.0 with a completely new and bigger dataset. It has a reduced sensitivity to noise which reduces the blobs of noise phenomena. It can also work reasonably well on Cel/Film Toons now. Overall it's a big leap from 1.0.
+
====Drawings====
  
DigitalFrames 2.1_Aggressive: Provides the sharpest results yet. It's the most aggressive version of DF. Does it's best on animation with little to no textures. The model as well as any version of DF is not suitable at all for overly deteriorated/blurred and low quality TVRips and VHSRips copies of animation pieces.
+
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
  
DigitalFrames 2.1_Final: The most universally "compatible" from the 2.0 branch that works well for all types of animation. If your piece has few textures or none at all, 2.1_Aggressive can perform better, but for all other scenarios _Final takes the cake with a much higher texture retention and "natural" look.
 
  
FatalimiX is specialized in making those low res comics high res again!
+
|-
 +
| [https://www.dropbox.com/s/52hsqa7ymt5pgga/KDM003_scans_1x.pth KDM003_scans_1x.pth]
 +
| BoxDrop
 +
| 1x
 +
|
 +
| ESRGAN
 +
| Art
 +
| 2019-07-29
 +
| Clean up model for scanned illustrations. - Made to remove moire patterns, reduce small imperfections, and correct mild compression artifacts in scanned Kingdom Death: Monster illustrations. CMYK printing often shifts colors, so this is intended to reverse that color shifting as well.
 +
| Failed attempts based on ESRGAN_1x_JPEG_80to100
 +
|
 +
|-
  
The SpongeBob model was trained for the purpose of upscaling Battle for Bikini Bottom's textures, but it works well for upscaling scenes from the show as well. It was initially trained on the clean downscaled images but later JPEG, quantization, dithering, and Gaussian blur were added to the LR OTF options to help it upscale the textures better.
+
|-
 +
| [https://drive.google.com/open?id=103MX2bvd3GW0MYpC53ABU5VYY6v1t99Y DigiPaint]
 +
| Rastrum
 +
| 4x
 +
| CC0
 +
| ESRGAN
 +
| Art
 +
| 2019-09-07
 +
| Digital Art Upscaler
 +
| 4xfalcoon300(manga).pth
 +
|
 +
|-
 +
|}
  
Spongebob v6 is ideally a lot sharper and cleaner, but Joey's still not sure if it works better than the old one. It still seems to be better in many cases.
+
====General Animation====
  
Spongebob v6 De-Quantize is for de-quantizing as well as upscaling. The results are pretty blurry but it works decently enough.
+
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
  
Spongebob v6 Deblur was created as Joey wasn't entirely happy with the main Spongebob v6 model. It was trained with blurring OTF options and two different downscale types.
+
|-
 +
| [https://drive.google.com/file/d/1i68bWo7xh3JPFIO-zLv9UMD72E-5xNr_/view American Dad 2 (American.Dad.2.HD.150ki.5e-PHOENiX.pth)]
 +
| PHEONiX (?)
 +
| 4x
 +
|
 +
| ESRGAN
 +
| Animation
 +
|
 +
| American Dad
 +
|
 +
|
 +
|-
  
HugePeeps v1 was created by DinJerr to test out a theory on how to properly train 8x models. This particular model best works on painted pics of ladies.
+
|-
 +
| [https://de-next.owncube.com/index.php/s/jYnFtncarkBmpcF FatalimiX]
 +
| |[[User:Twittman|Twittman]]
 +
| 4x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0] (?)
 +
| ESRGAN
 +
| Animation
 +
| 2019-10-29
 +
| Comic and Cartoon style images
 +
| 4x_Fatality_MKII_90000_G_02.pth
 +
|
 +
|-
  
HugePaint v1 is trained on a more generic dataset with a balance of illustrated humans, vegetation, minerals and some animals.
+
|-
 +
| [https://drive.google.com/open?id=1qjpxp8z4FGLZxieUDEVKd6FDum-8vpvJ Comic Book]
 +
| |[[User:LyonHrt|LyonHrt]]
 +
| 4x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Animation
 +
|
 +
| Comic / Drawings. Trained on Custom (Spider-Man) dataset
 +
| none (no interpolation)
 +
|
 +
|-
  
Some of the first cartoon painted models for ESRGAN can still be found [https://esrgan.blogspot.com/2019/01 here], but have been mostly superseded by newer models.
+
|-
 +
| [https://de-next.owncube.com/index.php/s/x99pKzS7TNaErrC Fatal_Anime]
 +
| |[[User:Twittman|Twittman]]
 +
| 4x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0] (?)
 +
| ESRGAN
 +
| Animation
 +
|
 +
| Trained on Anime and Manga images
 +
| none (no interpolation)
 +
|
 +
|-
  
====Pixel Art====
+
|-
 +
| [https://1drv.ms/u/s!Aip-EMByJHY26wU-wOqApp7Hu7tt?e=4ihnBr HugePaint]
 +
| |[[User:DinJerr|DinJerr]]
 +
| 8x
 +
| [https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Digital Illustrations
 +
|
 +
| Trained on a variety of images from ArtStation
 +
| HugePeeps
 +
|
 +
|-
  
Pixel art is a form of digital art, created through the use of software, where images are edited on the pixel level. The aesthetic for this kind of graphics comes from 8-bit and 16-bit computers and video game consoles, in addition to other limited systems such as graphing calculators. In most pixel art, the color palette used is extremely limited in size, with some pixel art using only two colors.
+
|-
 +
| [http://cloud.mitch.best/index.php/s/iio9SL9BdgWiCoi 4x_AbeScale]
 +
| |[[User:mitch#1337|mitch#1337]]
 +
| 4x
 +
| GNU
 +
| ESRGAN
 +
| Linework Cartoons
 +
|
 +
| Dataset: LR: Clone High DVD, HR: Re-illustrated Vectors from Frames
 +
| [https://mega.nz/#!uhAVEaAA!qfwIQ44Ba3rXMAb2-M3aM3zFBCwzmyQ64IO_0O-csJE 4xESRGAN]
 +
|
 +
|-
  
Creating or modifying pixel art characters or objects for video games is sometimes called spriting, a term that arose from the hobbyist community. The term likely came from the term sprite, a term used in computer graphics to describe a two-dimensional bitmap that is used in tandem with other bitmaps to construct a larger scene.  
+
|-
 +
| [https://mega.nz/file/9dJFjYrT#LY4Op8myZGJsh6ytUvF6ITVGXpx8XODN_AG-kzvWg4Y 2x_Loyaldk-SuperPony_370000 V1.0]
 +
| ChaseMMD
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Animation
 +
| 2021-02-24
 +
| Upscale MLP episodes
 +
| 2x_ERGAN
 +
| https://imgsli.com/NDIwNTY https://imgsli.com/NDIwNTg https://imgsli.com/NDIwNjE https://imgsli.com/NDIwNjI https://imgsli.com/NDIwNjM
 +
|-
 +
 
 +
|-
 +
| [https://mega.nz/file/RYxGEKRL#nTe0Zy2gB9e9QF5T8UhJSla1oEPQjSCXAB0BpNrTrRk 2x_Loyaldk-LitePony_380500 V1.0]
 +
| ChaseMMD
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Animation
 +
| 2021-03-01
 +
| Upscale MLP episodes. Liter version.
 +
| 2x_ESRGAN
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://mega.nz/file/VM5WmLwb#QvO1n6w6llYRh8qauXXkXy4tElrBCwclCl5VHM3IH8M 2x_Loyaldk-LitePony_500000_V2.0]
 +
| ChaseMMD#6957
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN (NF=32, NB=12)
 +
| Animation
 +
| 2021-04-06
 +
| Upscale MLP episodes. Liter version. Able to handle compression better compared to V1.0 and no longer creates halo's/rainbows. Good for Vector 2D art however converts detail to blobs.
 +
| none
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://mega.nz/file/YMwm0TbZ#agDBMDkswkpMM7FE1tDRlGX4zIOE4D0WBzcWudkN7Mc 2x_Loyaldk-MediumPony_500000_V2.0]
 +
| ChaseMMD
 +
| 2x
 +
|
 +
| ESRGAN (NF=48, NB=18)
 +
| Animation
 +
| 2021-04-11
 +
| Upscale MLP episodes. Liter version. Able to handle compression better compared to V1.0 and no longer creates halo's/rainbows. Good for Vector 2D art however converts detail to blobs. Leaves more blobs when converting detail to blobs compared to litepony
 +
| none
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://mega.nz/file/hcoViIQQ#O1cmQ8FsLk5RAIP5lxB3Q2L0suh9IWX_dGHhuSuL9U4 4x_Loyaldk-LitePony_500000_V2.0]
 +
| ChaseMMD
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN (NF=32, NB=12)
 +
| Animation
 +
| 2021-04-12
 +
| Good for Vector 2D art however converts detail to blobs. Quality seems weak with this one. However posting anyways to see if a use is found.
 +
| none
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://mega.nz/file/IBhElRYJ#C_lVc8Vr2q8X6hEltJKD6I63U7oL_FDLeJgPh72AZmg 2x_Loyaldk-SuperPony_500000_V2.0]
 +
| ChaseMMD
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Animation
 +
| 2021-04-30
 +
| Upscale MLP episodes. Full version. Able to handle compression better compared to V1.0 and no longer creates halo's/rainbows. Good for Vector 2D art however converts detail to blobs.
 +
| none
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://mega.nz/file/BMhUCbJZ#kYz0wvc26RW0n0f8AUXekW_ZCuRamKmh2-iWf1eefn0 4x_Loyaldk-SuperPony_500000_V2.0]
 +
| ChaseMMD
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Animation
 +
| 2021-04-30
 +
| Upscale MLP episodes. Full version. Able to handle compression better compared to V1.0 and no longer creates halo's/rainbows. Good for Vector 2D art however converts detail to blobs.
 +
| none
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://mega.nz/file/lYo01DRI#HIiJ7M5YaXjwAb3zEbtSLzAI59iljwEX72Ad88CvUf0 4x_Loyaldk-MediumPony_500000_V2.0]
 +
| ChaseMMD
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Animation
 +
| 2021-04-30
 +
| Upscale MLP episodes. Full version. Able to handle compression better compared to V1.0 and no longer creates halo's/rainbows. Good for Vector 2D art however converts detail to blobs.
 +
| none
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://mega.nz/folder/5UAlQCRJ#2Bj1lq8PYeB3P9k5UKSvkQ Platoon Model Set]
 +
| ChaseMMD
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Animation
 +
| 2021-06-07
 +
| Upscale Anime while keeping as much of the original detail as possible. Isn't among the sharpest models and if the anime is somewhat blurry it will retain that detail but add more pixels to give a smoother edge. Doesn't change the color very much and may make some scene's very slightly darker.
 +
| Pony Models
 +
| https://mega.nz/folder/5UAlQCRJ#2Bj1lq8PYeB3P9k5UKSvkQ
 +
|-
 +
|}
 +
 
 +
 
 +
====Traditional Animation====
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 
|-
 
|-
|[https://1drv.ms/u/s!Aip-EMByJHY27CHg3-1Uue5KgbtK?e=6k0COU BigFace v3]||[[User:DinJerr|DinJerr]]||4||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||Painted people||300K~||4||384||1K||Selected concept art||[https://1drv.ms/u/s!Aip-EMByJHY23ii1LoVMFNVOprBG?e=u2YxRU BigFace]
+
| [https://cdn.discordapp.com/attachments/579685650824036387/812414843939455036/2X_DigitalFilmV5_Lite.pth DigitalFilmV5 Lite]
 +
| OptimusPrimal
 +
| 2x
 +
| WTFPL
 +
| ESRGAN
 +
| Traditional Animation
 +
| 2021-02-19
 +
| Upscaling Dragon Ball Z DBox DVD's.  - grainy sources. It keeps some grain, but also doing some cleaning, sharpening, and fixing.
 +
| none
 +
| https://imgsli.com/NDE0MzQ https://imgsli.com/NDE0MzU https://imgsli.com/NDE0MzY https://imgsli.com/NDE0Mzc https://imgsli.com/NDE0Mzg https://imgsli.com/NDE0Mzk
 
|-
 
|-
|[https://1drv.ms/u/s!Aip-EMByJHY200v-vXPezsCsUd5T?e=r7mBNn BigFArt Suite]||[[User:DinJerr|DinJerr]]||4||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||Larger-scaled pixels to digital painting||800+||6||192||~12K||DIV2K, FatalityFaces, ArtStation paintings||Face Focus
+
 
 +
| [https://mega.nz/file/GFFkSL5R#C-dDxaxTZpSPUh_heAUw_idGIF8Xizdr0ktyGi05yFk 4x_HellinaCel]
 +
| VGDCKeroro
 +
| 4x
 +
| fuckin do whatever
 +
| ESRGAN
 +
| Traditional Animation
 +
| 2021-03-21
 +
| A rougher alternative to 4xCelFrames with a focus on realistic looking cels over nice looking cels. It's trained on DetoriationFrames LRs, so if you give it an image straight from the source it will go twice as hard on it. This can be used to your advantage, though. I recommend cleaning it up before running DetoriationFrames, or else it will come out rough.
 +
| 4xESRGAN
 +
| https://imgsli.com/NDU2MjU
 
|-
 
|-
|[https://1drv.ms/u/s!Aip-EMByJHY22BhfdJ1Epkfc3ugq?e=yVfXkz FArtDIV3 Suite]||[[User:DinJerr|DinJerr]]||4||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||Pixels to digital painting||700K~||4||128||~10K||DIV2K, FatalityFaces, ArtStation paintings||ArtStation1337
+
|}
 +
 
 +
 
 +
===Image Restoration===
 +
====Image Compression====
 +
=====JPEG Artifacts=====
 +
{| class="wikitable sortable"
 
|-
 
|-
|[https://drive.google.com/open?id=1BzT-KwUBiZzACxGdIN6w930aOVvvfhg7 Faithful]||Joey||2||[https://creativecommons.org/publicdomain/zero/1.0/ CC0]||General small pixel textures||130K||80||32||2.858K||Faithful 32x32 (HR) / default Minecraft 1.13 and 1.14 (LR)||Private model trained from 2xESRGAN
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 
|-
 
|-
|[https://drive.google.com/open?id=1Uc9RUc2YpZKpPoGQeGxNUb3Ro-U720cH SmoothRealism]||Joey||4||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||Pixel art, rocky/grainy textures||140K||2||64||679||R3DCraft Smooth Realism Texture Pack 64x||RRDB_PSNR_x4
+
|[https://drive.google.com/drive/folders/1HWokMsUwsR_Mw-NOJgc8OdS8mkdIje_C JPG (20-40%)]
 +
| |[[User:BlueAmulet|BlueAmulet]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| JPEG
 +
|  
 +
|  
 +
| Trained on Custom (CC0 Textures)
 +
| JPEG models by Alsa
 
|-
 
|-
|[https://drive.google.com/u/1/uc?id=1WXJQzqVGTKaX_8_Ma1hJ45W5nUkZBGFu&export=download Rebout]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Character Sprites||325K||8||128||23.808K||Custom prepared sprites from kof 94 rebout, now updated with cx loss||Detoon
+
 
 +
 
 +
|[https://drive.google.com/drive/folders/1HWokMsUwsR_Mw-NOJgc8OdS8mkdIje_C JPG (40-60%)]
 +
| |[[User:BlueAmulet|BlueAmulet]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| JPEG
 +
|  
 +
|  
 +
| Trained on Custom (CC0 Textures)
 +
| JPEG models by Alsa
 
|-
 
|-
|[https://drive.google.com/u/1/uc?id=1h-bY4gq_61sRF_xK3F4OiVK1cWRX0Q9w&export=download Rebout blend]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Character Sprites||325K||8||128||23.808K||Custom prepared sprites from kof 94 rebout, which with gradients blending||Detoon
+
 
 +
|[https://drive.google.com/drive/folders/1HWokMsUwsR_Mw-NOJgc8OdS8mkdIje_C JPG (60-80%)]
 +
| |[[User:BlueAmulet|BlueAmulet]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| JPEG
 +
|  
 +
|  
 +
| Trained on Custom (CC0 Textures)
 +
| JPEG models by Alsa
 
|-
 
|-
|[https://drive.google.com/open?id=1jE2le5Lsab-AcMUMm0Zr9L-OvFNhnRAG ScaleNX]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Scalenx style pixel art upscaler||80K||8||128||1.070K||custom scalenx up-scaled from retroarch shader||RRDB_PSNR_x4
+
 
 +
 
 +
| [https://drive.google.com/drive/folders/1HWokMsUwsR_Mw-NOJgc8OdS8mkdIje_C JPG (80-100%)]
 +
| |[[User:BlueAmulet|BlueAmulet]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| JPEG
 +
|  
 +
|  
 +
| Trained on Custom (CC0 Textures)
 +
| JPEG models by Alsa
 
|-
 
|-
|[https://drive.google.com/open?id=1LFd4BqZ2N8p21JzjLX6hGdm7RpVIkH7s Xbrz]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Xbrz style pixel art upscaler||90K||8||128||1.897K||custom xbrz up-scaled||RRDB_PSNR_x4
+
 
 +
 
 +
|[https://mega.nz/#!OzpFHYAD!0swA_J18bSygyVgMHac3P4kkBx6ZYUHNnL9qXhiu-9I JPG (20-40%)]
 +
| |[[User:Alsa|Alsa]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| JPEG
 +
|  
 +
|  
 +
| Trained on Custom (Photos / Manga)
 +
|  
 
|-
 
|-
|[https://drive.google.com/open?id=1VDbjRii9zyyUhyqnQd5H8OP8d3AuwjTe Xbrz+DD]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Xbrz style pixel art upscaler with de-dithering||90K||8||128||1.523K||custom de-dithered xbrz||xbrz
+
 
|-|-
+
 
|[https://de-next.owncube.com/index.php/s/gPjswdm6gCegQdz Fatality]||[[User:Twittman|Twittman]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||(dithered) spirites||265K||10||128||19.7K||?||[https://de-next.owncube.com/index.php/s/YbAqNMMTtxrajF6 Face]
+
|[https://mega.nz/#!Kr5Q1C7C!yq4910SjvAyMS_40IhrOsShA21OXdP8rxfiMsEuYbW8 JPG (40-60%)]
 +
| |[[User:Alsa|Alsa]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| JPEG
 +
|  
 +
|  
 +
| Trained on Custom (Photos / Manga)  
 +
|  
 
|-
 
|-
|[https://de-next.owncube.com/index.php/s/ECsEHxdoYCnFsZA Fatal Pixels]||[[User:Twittman|Twittman]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Sprites||340K||22||96||49K||Anime, Manga||Fatality_MKII_90k
 
|}
 
  
Fatality is meant to be used for upscaling medium resolution Sprites, dithered or un-dithered, it can also upscale manga/anime and gameboy camera images.
 
  
Rebout is trained to give detail to character models, with faces and hands improved. Based on the snk game kof94 rebout, although best for snk style games, does work on a variety of sprites. Also included is a interpolated version that may provide a cleaner upscale for certain sprites.
+
|[https://mega.nz/#!6j4RRQBD!3CX7XN9ZEAeWR3aXBAsDRpxSfKbM8zR1N9GXgbP38Ig JPG (60-80%)]
 +
| |[[User:Alsa|Alsa]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/  CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| JPEG
 +
|
 +
|
 +
| Trained on Custom (Photos / Manga)
 +
|
 +
|-
 +
 
 +
 
 +
| [https://mega.nz/#!2uxwRYYT!2KgAsRac70jqYYXyOvQ5HSd4ipoqC0WGB4Md2Su_OM8 JPG (80-100%)]
 +
| |[[User:Alsa|Alsa]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/  CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| JPEG
 +
|
 +
|
 +
| Trained on Custom (Photos / Manga)
 +
|
 +
|-
 +
 
 +
| [https://icedrive.net/1/43GNBihZyi 4x NMKD-PatchySharp]
 +
| nmkd
 +
| 4x
 +
| WTFPL
 +
| ESRGAN (Old Arch)
 +
| Art/CGI
 +
| 2020-09-12
 +
| Upscaler for clean images or images with compression artifacts (jpeg quality >75) - Produces very sharp lines/edges due to NN-Filtered HR images. Proven to produce very, very good results on drawings (sharp lines) and CGI, but should also work pretty well for real-world images.
 +
| 4xESRGAN
 +
| https://i.imgur.com/PzFkmAg.png
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/open?id=1HWokMsUwsR_Mw-NOJgc8OdS8mkdIje_C 1x_JPEG (by compression level)]
 +
| |[[User:BlueAmulet|BlueAmulet]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| JPEG
 +
| 2019-08-01
 +
| A collection of models for jpeg artifact removal, examples are included in the provided link
 +
| JPEG models by |[[User:Alsa|Alsa]]
 +
| https://drive.google.com/open?id=1HWokMsUwsR_Mw-NOJgc8OdS8mkdIje_C
 +
|-
 +
 
 +
 
 +
| [https://de-next.owncube.com/index.php/s/w82HLrLWmWi4SQ5 DeJpeg Fatality_PlusULTRA!]
 +
| |[[User:Twittman|Twittman]]
 +
| 1x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0] (?)
 +
| ESRGAN
 +
| JPEG
 +
| 2019-10-29
 +
|
 +
| 1x_DeJpeg_Fatality_01_200000_G.pth
 +
|
 +
|-
 +
 
 +
 
 +
| [https://mega.nz/folder/zUJjnCoB#_zK3vs5iW6atyElO735XDA DeCompress and DeCompress-Strong]
 +
| |[[User:Kim2091|Kim2091]]
 +
| 4x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| JPEG (works on many compression formats)
 +
| 2021-09-07
 +
| This is UniScaleV2, but intended for images with compression. Seems to work best on realistic images.
 +
| 4xESRGAN
 +
| https://cdn.discordapp.com/attachments/884864597310459996/884952891721383936/unknown.png https://cdn.discordapp.com/attachments/884864597310459996/884957054807179274/unknown.png https://cdn.discordapp.com/attachments/884864597310459996/884960697883193354/unknown.png https://cdn.discordapp.com/attachments/884864597310459996/884953810097827850/unknown.png
 +
|-
 +
 
  
Faithful 2x was trained on the faithful 32x32 Minecraft texture/resource pack, using both the 1.13 and 1.14 versions (which have different textures). For those not familiar, this texture pack is meant to upscale the 16x16 textures to 32x32 faithfully, as in make them as close as possible to the original, but higher resolution. The model does a decent job at replicating this.
+
| [https://de-next.owncube.com/index.php/s/w82HLrLWmWi4SQ5 JPG PlusULTRA (1x_jpg_PlusULTRA_130000.pth)]
 +
| |[[User:Twittman|Twittman]]
 +
| 1x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0] (?)
 +
| ESRGAN
 +
| JPEG
 +
| 2019-10-29
 +
|
 +
| 1x_DeJpeg_Fatality_01_200000_G.pth
 +
|
 +
|-
  
*'''NOTE:''' Due to an error in the dataset, sometimes the model turns jagged white lines green. Only encountered this in one texture tried, so it appears unlikely to happen.
 
  
FArtDIV3 Suite is a group of models based on a large image dataset trained using OTF tile generation. Most of the models are based off the Base model, and suite different purposes. Fine is used to generate details, but may be noisy/grainy at times. Blend will attempt to blend colour steps into proper gradients. UnholyFArt is a interpolated model that reduces details in favor of sharp blends.  
+
| [https://f002.backblazeb2.com/file/ESRGAN/_RELEASE/1x_Saiyajin_DeJPEG_300000_G.pth SaiyaJin DeJpeg]
 +
| |[[User:Twittman|Twittman]]
 +
| 1x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0] (?)
 +
| ESRGAN
 +
| JPEG
 +
| 2019-10-29
 +
| Dataset: Anime, real life, manga, generated
 +
| 1x_DeJpeg_Fatality_PlusULTRA_200000_G.pth
 +
|
 +
|-
  
BigFArt Suite is similar to FArtDIV3, but for larger pixel sprites/art in the context of tile size.
+
| [https://drive.google.com/file/d/1C0Lnn3PfXrm4UX9trjQIWsmxtspjQjmm/view?usp=drivesdk 1x_JPEGDestroyer]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 1x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| JPEG
 +
| 2020-02-19
 +
| This model is meant to reduce or eliminate JPEG Compression without making the original images too smooth or killing detail. It manages to do a fairly good job but don't expect overly compressed images to work with this.
 +
| 1xESRGAN + previous attempts
 +
|
 +
|-
  
BigFace_v3 Suite takes the BigFace model from the BigFArt suite, and tries to improve by using double-sized tiles. Main model has good dedithering. _Blend focuses on sharp blends, and _Clear will abstract and sharpen details.
+
| [https://drive.google.com/file/d/17k72r01xTkeOzqsaYCN6ZqnAktKqTLyw/view?usp=sharing 4xJaypeg90]
 +
| Jacob
 +
| 4x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| JPEG compression
 +
| 2020-07-20
 +
| Photos/realistic 3D with JPEG compression, quality 85-95 and 4:2:0 chroma subsampling. - Created for Myst3 images, since all have 4:2:0 chroma subsampling and existing JPEG models did not give good results. Favors smoothing over over-sharpening.
 +
| 4xESRGAN
 +
| https://i.imgur.com/n09m2Rt.png
 +
|-
  
===Photographs and Photorealism===
+
| [https://u.pcloud.link/publink/show?code=kZvfeFXZMyUSYScxAizUmTKjax0JQzTk9Gfk 1x_SBDV-DeJPEG-Lite]
 +
| Joey
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN (lite)
 +
| JPEG compression
 +
| 2020-10-10
 +
|
 +
| 1x_DIV2K-Lite_80k.pth
 +
|
 +
|-
  
A photograph (also known as a photo) is an image created by light falling on a photosensitive surface, usually photographic film or an electronic image sensor, such as a CCD or a CMOS chip. Most photographs are created using a camera, which uses a lens to focus the scene's visible wavelengths of light into a reproduction of what the human eye would see. The process and practice of creating such images is called photography. The word photograph was coined in 1839 by Sir John Herschel and is based on the Greek φῶς (phos), meaning "light," and γραφή (graphê), meaning "drawing, writing," together meaning "drawing with light."
+
| [https://icedrive.net/1/43GNBihZyi NMKD Jaywreck3 & Jaywreck3-Soft (Lite)]
Photorealism is a genre of art that encompasses painting, drawing and other graphic media, in which an artist studies a photograph and then attempts to reproduce the image as realistically as possible in another medium. Although the term can be used broadly to describe artworks in many different media, it is also used to refer specifically to a group of paintings and painters of the American art movement that began in the late 1960s and early 1970s.
+
| |[[User:nmkd|Nmkd]]
 +
| 1x
 +
| WTFPL
 +
| ESRGAN Lite [nf=32 nb=12]
 +
| JPEG compression
 +
| 2020-10-13
 +
| 1xESRGAN
 +
| 1xESRGAN
 +
|
 +
|-
  
====Misc / Kitchen Sink====
+
| [https://mega.nz/folder/fAg21TRI#kBk0synXgNqTGaXiW6nSZA MangaJPEG]
 +
| Bunzero++
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| JPEG
 +
| 2021-06-17
 +
| Remove JPEG artifacts from manga without destroying screentone and other details
 +
| none
 +
| https://cdn.discordapp.com/attachments/579685650824036387/855269193762865152/Example_LQ_Input-comparison.png
 +
|}
  
All kinds of photographs or photorealistic images. Those models aren't specialized.
+
=====Aliasing=====
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 
|-
 
|-
|[https://e.pcloud.link/publink/show?code=XZ6msZu8BOExSFH4SxixhuxoyrmbRYGQQk Misc]||[[User:Alsa|Alsa]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Surface Textures||220K||32||128||20.797K||Custom (Photos)||[http://www.mediafire.com/file/w3jujtm752hvdj1/Manga109Attempt.pth.zip/file Manga109Attempt]
+
 
 
|-
 
|-
|[https://drive.google.com/file/d/1d89zvzC6BKf5EKapBtc4MH2DX5GClKzl/view Nickelback]||[[User:BlackScout|BlackScout]]||4||GNU GPLv3||Photographs||70k||8||128||44.55k||Wallpapers||4xESRGAN
+
| [https://drive.google.com/open?id=11nMqVF9sUN2jRRagYc3wdWNX5acEy0MJ SS Anti Alias 9x]
 +
| |[[User:BlueAmulet|BlueAmulet]]
 +
| 1x
 +
| [https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Anti aliasing
 +
|  
 +
| Dataset: Custom (9x Supersampling AA)
 +
| none (no interpolation)
 +
|  
 
|-
 
|-
|[https://drive.google.com/file/d/1KToK9mOz05wgxeMaWj9XFLOE4cnvo40D/view?usp=sharing 4xBox]||Jacob_ (buildist)||4||GNU GPLv3||Realistic||390K||8||192||11.577K||Flickr2K+Div2K+OST||PSNR model from same data
+
 
 
|-
 
|-
|[https://u.pcloud.link/publink/show?code=kZOhRakZOUkSXYB6at7ndvDxVJBGQLSaIfBk NMKDSuperscale]||[[User:Nmkd|nmkd]]||4||[http://www.wtfpl.net/ WTFPL]||Clean Real-World Images||134k||1/2||448||900||DIV2K Train + Valid||[4xESRGAN]
+
| [https://de-next.owncube.com/index.php/s/mmYCcK4H3rQQR5Y Anti Aliasing]
 +
| |[[User:Twittman|Twittman]]
 +
| 1x
 +
| [https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Anti aliasing / Images with pixelated edges
 +
|  
 +
| Dataset: Custom (?)
 +
| none (no interpolation)
 +
|  
 
|-
 
|-
|[https://drive.google.com/file/d/1dGmhHUPmb3lO9buX_Bt2nq97Nk5MCTb4/view Ground]||ZaphodBreeblebox||4|| ||Ground Textures||305K||?||128||?||Custom (Ground textures Google)||?
+
 
 
|}
 
|}
  
Box was meant to be an improvement on the RRDB_ESRGAN_x4 model ([https://imgsli.com/NDEwMw comparison]). It’s also trained on photos, but with a much larger dataset which was downscaled with linear interpolation (box filter) instead of bicubic.
+
=====GIF=====
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
|-
 +
| [https://icedrive.net/1/43GNBihZyi DeGif]
 +
| |[[User:nmkd|nmkd]]
 +
| 2x
 +
| WTFPL
 +
| ESRGAN
 +
| GIF Restoration
 +
|
 +
| GIF Restoration
 +
| [https://mega.nz/#!vtgSWKQT!K7Asn2zKe4N70R2aV89KEMTKhH3aiyGAAiuQDJF09qs 2xESRGAN]
 +
|
 +
|-
 +
|}
  
Deoldify is intended for denoising and deblurring photos. All outputs are greyscale. This was initially a proof of concept. ''(Need clarification on specific subject matter.)''
+
=====DDS (BC1/DXT1, BC3/DXT5 Compression)=====
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
  
The Ground model was trained on various pictures of '''stones, dirt and grass''' using Google’s image search.
+
|-
 +
| [https://drive.google.com/open?id=1LHplsPRqhmjR28jGgRlEekeP_bvx3nUC 1x_BC1-smooth2.pth]
 +
| |[[User:BlueAmulet|BlueAmulet]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| BC1 Compression
 +
| 2019-09-05
 +
| A model to help remove compression artifacts in BC1-BC3/DXT1-DXT5 compressed images (these all have color encoded the same way)
 +
| none
 +
|
 +
|-
  
The Misc model is trained on various pictures shoot by myself, including '''bricks, stone, dirt, grass, plants, wood, bark, metal''' and a few others.
+
|-
 +
| [https://e.pcloud.link/publink/show?code=XZXbsZK03Y0UsmtR0W7wRMHWGvYkzgPII7 1x_artifacts_bc1_free_alsa.pth]
 +
| |[[User:Alsa|Alsa]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| BC1 Compression
 +
|
 +
|
 +
| [https://mega.nz/#!r2hEAAAb!zdk-Ka6VCqVnKThtfJVYM0NnVBSUyeqsjYs-NgKjLkc BC1 take 2]
 +
|
 +
|-
  
NMKDSuperscale was made to rival the RealSR models and is one of the best upscalers for real-world content. It's trained on PNGs, so it doesn't handle compression artifacts well.
+
| [https://drive.google.com/drive/u/1/folders/1pnyPklpLPtMAHeNC5NVU1mV_Qh61wWnx 1x_BCGone_Smooth_110000_G]
 +
| |[[User:Mutin_Choler|Mutin_Choler]]
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| BC1 Compression
 +
| 2020-08-02
 +
| Attempts to remove the damages done by BC1 compression.
 +
| 1xESRGAN
 +
| https://imgsli.com/MjU5MzQ/4/3
 +
|-
  
====Characters and Faces====
+
| [https://drive.google.com/drive/folders/1pnyPklpLPtMAHeNC5NVU1mV_Qh61wWnx?usp=sharing 1x_BCGone-DetailedV2_40-60_115000_G]
 +
| |[[User:Mutin_Choler|Mutin_Choler]]
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| BC1 Compression
 +
| 2021-03-18
 +
|
 +
| 1xESRGAN
 +
|
 +
|-
 +
|}
  
For images of humans, creatures, faces, ...
+
=====Dithering=====
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
 
 +
|-
 +
| [https://e.pcloud.link/publink/show?code=XZ5bsZtd0ldzEF2UFLSYqIBNhqNH21slxX 1x_artifacts_dithering_alsa.pth]
 +
| [[User:Alsa|Alsa]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Dithering
 +
|
 +
| Dithered Images
 +
| [https://mega.nz/#!7io2gSQR!UB9u2k51daixTgC2H0LdOWzNlkDyIDHwxBX4BVY2J3k JPG (0-20%)]
 +
|
 +
|-
 +
 
 +
 
 +
|-
 +
| [https://drive.google.com/file/d/1H4KQyhcknOoExjvDdsoxAgTBMO7JuJ3w/view 4xFSDedither]
 +
| Jacob
 +
| 4x
 +
| GNU GPL3
 +
| ESRGAN
 +
| Dithering
 +
| 2020-01-29
 +
| For photos/realistic images, but worth trying on other images that have reduced colors and dithering along with fine details. Trained using the ESRGAN-FS code (https://github.com/ManuelFritsche/real-world-sr/tree/master/esrgan-fs/codes) for better details compared to plain ESRGAN.
 +
| RRDB_ESRGAN_x4
 +
| https://imgsli.com/MTI1NTY/
 
|-
 
|-
|[https://drive.google.com/file/d/1HIBRKFs7s-XhpN1p7rwAWcMTHwFRqn3n/view Trixie]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Star Wars||275K||8||192||19.814K||?||None
+
 
 
|-
 
|-
|[https://drive.google.com/open?id=19ICMKNuS4PbhmtA7Be9lUE6v8NHDDEzP Face Focus]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Face De-blur||275K||8||192||4.157K||Custom (Faces)||RRDB_PSNR_x4
+
| [https://drive.google.com/open?id=1Vtwt9kgnmju1edibl07WI6Rg7CrAlHIx 4xFSDedither_Manga]
 +
| Jacob
 +
| 4x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN-FS
 +
| Dithering
 +
| 2020-04-21
 +
| Cartoons/pixel art/other non-realistic stuff with dithering
 +
| RRDB_ESRGAN_x4.pth
 +
| https://imgsli.com/MTQ3Nzc
 
|-
 
|-
|[https://de-next.owncube.com/index.php/s/YbAqNMMTtxrajF6 Face]||[[User:Twittman|Twittman]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Face Upscaling||250K||10||128||3.765K||Custom (Faces)||[https://mega.nz/#!uhAVEaAA!qfwIQ44Ba3rXMAb2-M3aM3zFBCwzmyQ64IO_0O-csJE 4xESRGAN]
+
 
 +
| [https://buildism.net/files/4xFSDedither_Riven.pth 4xFSDedither_Riven]
 +
| Jacob
 +
| 4x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN-FS
 +
| Dithering
 +
| 2020-07-11
 +
| Fine-tuned 4xFSDedither to upscale images from the game Riven, but should be better in general, particularly on ordered dithering. I adjusted the dataset to have a better variety of dithering parameters, and turned up the HFEN and pixel loss to get better details and color restoration with less noise.
 +
| 4xESRGAN
 +
| https://imgsli.com/MTg5NTM https://imgsli.com/MTg5NTQ https://imgsli.com/MTg5NTU https://i.imgur.com/j7Wtn0G.png
 
|-
 
|-
|[https://de-next.owncube.com/index.php/s/mZRG4HB3KdP2iP6 Face-Ality V1]||[[User:Twittman|Twittman]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Face Upscaling||310k||10||128||13.3k||Custom (Faces)||4x_Faces_04_N_180000_G.pth
+
 
 +
| [https://drive.google.com/drive/folders/1XKREcpHnaYz_dcmkMPDbyETcXzDcQsR2?usp=sharing 1x_DitherDeleter-Smooth_104000_G]
 +
| |[[User:Mutin_Choler|Mutin_Choler]]
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| Dithering
 +
| 2021-01-23
 +
| 1xESRGAN
 +
| https://imgsli.com/Mzg0MTk/1/2
 +
|-
 +
 
 +
| [https://drive.google.com/drive/folders/1XKREcpHnaYz_dcmkMPDbyETcXzDcQsR2?usp=sharing 1x_DitherDeleterV3-Smooth]
 +
| |[[User:Mutin_Choler|Mutin_Choler]]
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| Dithering
 +
| 2021-04-18
 +
| Attempts to remove the damages done by dithering. 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 32-bit Riemersma to every image in the dataset.
 +
| 1xESRGAN
 +
| https://imgsli.com/NTA5MjU/1/0
 
|-
 
|-
|[https://drive.google.com/open?id=1OyOJIW224hBhb-aTCbuUQb0qzKmE4oH6 TGHQFace8x]||[[User:Torrentguy_(tg)|Torrentguy]]||8||GNU GPL3||Face Upscaling||500k||8||128||70k||Flickr Cropped Faces||[https://mega.nz/#!6kwQiCCS!v2uN8R44vVrlzmSqffGaCnzgogkPhhl67myJbuG45SA 8xESRGAN]
 
 
|}
 
|}
  
Trixie was made to bring balance to the force… Also to upscale '''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''' textures.
+
====Blurring====
  
The Face Focus modes was designed for '''slightly out of focus / blurred images of faces'''. It is aimed at '''faces''' / '''hair''', but it can help to '''improve other out of focused images too''' as always just try it.
+
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
  
===Specialized===
+
|-
 +
| [https://mega.nz/file/CYoXCAKR#eRKwpP9rCL9vFCsO41oVImvmVwAEOtYUlp2CquX0Fw8 1x_ThePi7on-Solidd_Deborutify_UltraLite_260k_G]
 +
| ThePi7on
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Deblur
 +
| 2021-05-09
 +
| Sharpening, line darkening and slight line thinning, specifically made for the Boruto anime.
 +
|
 +
|
 +
|-
 +
 
 +
| [https://cloud.owncube.com/s/p3w7M2sfaWWYCK9/download?path=%2F&files=1x_mdeblur.pth mdeblur]
 +
| LyonHrt
 +
| 1x
 +
|UNKNOWN
 +
| ESRGAN
 +
| Blurring
 +
|
 +
| Strong deblurring model
 +
|
 +
|
 +
|-
 +
 
 +
| [https://1drv.ms/u/s!Aip-EMByJHY27TDhiFPB39jM0pwq?e=5zAFtO 1x_PixelSharpen_100000]
 +
| DinJerr
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Pixel Art
 +
| 2021-03-19
 +
| Restores blurry/upscaled pixel art.
 +
| 1xESRGAN
 +
| https://imgsli.com/NDUxNDQ/5/4
 +
|-
  
For Purposes that didn't fit anywhere else (for now).
+
| [https://1drv.ms/u/s!Aip-EMByJHY28w0Zkd9fdANYH3j6?e=9zwxII 1x_ArtClarity]
 +
| DinnJerr
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| Pixel Art
 +
| 2021-08-05
 +
| Texture retaining denoiser and sharpener for digital artwork
 +
| 4xPSNR
 +
|
 +
|-
 +
 
 +
| [https://de-next.owncube.com/index.php/s/aAojXwLTPZto8rP 1x_Fatality_DeBlur]
 +
| |[[User:Twittman|Twittman]]
 +
| 1x
 +
| Your soul now belongs to me
 +
| ESRGAN
 +
| Deblur
 +
| 2019-10-16
 +
| Dataset: Mix of anime, manga, and photos
 +
| 1x_DeJpeg_Fatality_01_175000_G.pth
 +
|
 +
|-
 +
 
 +
| [https://de-next.owncube.com/index.php/s/nmNfcd33mnLLwEC UnResize V3 (1x_UnResize_V3_200000_G.pth)]
 +
| |[[User:Twittman|Twittman]]
 +
| 1x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0] (?)
 +
| ESRGAN
 +
| Deblur / Unresize
 +
|
 +
| Dataset: Anime, manga, and photos
 +
| 1x_UnResize_MKII_030000_G.pth
 +
|
 +
|-
 +
 
 +
| [https://mega.nz/folder/OVomUZyT#vDyNntGY1MirBEACNjpqVg 1x-Focus and 1x-Focus_Moderate]
 +
| |[[User:Kim2091|Kim2091]]
 +
| 1x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Deblur
 +
|
 +
| 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. Dataset: The UniScale Dataset + My Fabric dataset
 +
| 1xESRGAN
 +
| [https://cdn.discordapp.com/attachments/893483065664483338/893483645803847690/unknown.png Sample 1] [https://cdn.discordapp.com/attachments/893483065664483338/893497416207188028/unknown.png Sample 2] [https://cdn.discordapp.com/attachments/893483065664483338/893483280895193118/unknown.png Sample 3] [https://cdn.discordapp.com/attachments/893483065664483338/893496207832408135/unknown.png Sample 4]
 +
|-
 +
 
 +
|}
 +
 
 +
====Banding====
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
|-  
+
! Author
|[https://e.pcloud.link/publink/show?code=XZGmsZo1yNrot19O4R5SrPVD1GWpRy1MKX Skyrim Armory]||[[User:Alsa|Alsa]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Armor, Clothes and Weapons||80K||26||128||0.8K||Skyrim Mod textures||[http://www.mediafire.com/file/w3jujtm752hvdj1/Manga109Attempt.pth.zip/file Manga109Attempt]
+
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://drive.google.com/file/d/1GNguVMV4E5t_4dn23w6UMXVKN6Ff9XPt/view?usp=sharing 1x_N64clean]
 +
| |[[User:BlueAmulet|BlueAmulet]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Banding
 +
| 2020-07-16
 +
| N64 textures use a color depth of 5-bits per channel, this model attempts to clean them, restoring smooth gradients in textures
 +
| 1x_BC1-smooth2.pth
 +
|
 
|-
 
|-
|[https://drive.google.com/file/d/1zlc8BWOcpCbSZpwf7ArMCqpb0Tf9DlZk/view BS_Wolly]||[[User:BlackScout|BlackScout]]||2||GNU GPLv3||Pixar Movies / Wall-E||38k||1||256||9.0k||BD 1080p Wall-E Frames||2xESRGAN
+
 
 
|-
 
|-
|[https://drive.google.com/file/d/1zC97RLUg5ejqb5-4Dj5q-SzdLPLiMozH/view Nickelfront]||[[User:BlackScout|BlackScout]]||4||GNU GPLv3||Money, Coins||14k||8||128||1.176k||Images of Coins||4xESRGAN
+
| [https://drive.google.com/file/d/14YW1z12CG7n4-g4_nxpX8SfvqN9Yssry/view?usp=drivesdk 1xBS_DebandizerSPSRV2]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 1x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| SPSR
 +
| Banding
 +
| 2020-07-21
 +
| mostly ends up dithering the image slightly but it has the potential to recover detail.
 +
| 1xBS_DebandizerSPSRV1
 +
|  
 
|-
 
|-
|[https://1drv.ms/u/s!AiWox1lAWLoTg1bUeJouJNOFZ_Jj Fallout 4 Weapons]||Bob||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Fallout Weapon Diffuse Textures||120K||13||128||532(OTF)||Fallout 4 HDDLC Weapon Diffuse Textures||[http://www.mediafire.com/file/w3jujtm752hvdj1/Manga109Attempt.pth.zip/file Manga109Attempt]
+
 
 +
| [https://drive.google.com/drive/folders/1WD2RqtER_jk0QkPFUySeXhDV2aAO8_nr?usp=sharing 1x_Bandage-Smooth]
 +
| |[[User:Mutin_Choler|Mutin_Choler]]
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| Banding
 +
| 2021-04-16
 +
| 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.
 +
| 1xESRGAN
 +
| https://imgsli.com/NTA1NTk/1/0
 
|-
 
|-
|[https://1drv.ms/u/s!AiWox1lAWLoThANuXjxIR-hqA6os Fallout Weapons V2]||Bob||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Video game textures, mostly metal rusty, clean or painted.||180K||13||128||1.999K(OTF)||Fallout 4 HD DLC(Weapon,Armor/Clothes,Vehicle and Interior/Architecture textures to be exact)||[https://1drv.ms/u/s!AiWox1lAWLoTg1bUeJouJNOFZ_Jj Fallout 4 Weapons]
+
 
 
|-
 
|-
|[https://drive.google.com/file/d/1RjVWNUFtVyz4ykqu6Pm9wmO03pPEBGqg/view Skyrim Misc]||Deorder||4||[https://creativecommons.org/publicdomain/zero/1.0/ CC0]||Skyrim Diffuse Textures||105K||?||128||?||Skyrim Diffuse Textures||?
+
| [https://f002.backblazeb2.com/file/ESRGAN/_RELEASE/1x_Debandurh_FS_lite_140000_G.pth Debandurh_FS Ultra-lite (1x_Debandurh_FS_lite_140000_G.pth)]
 +
| |[[User:Twittman|Twittman]]
 +
| 1x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0] (?)
 +
| ESRGAN
 +
| Debanding images
 +
|  
 +
| Dataset: Anime, real life, manga
 +
| None
 +
|  
 
|-
 
|-
|[https://drive.google.com/file/d/1waC7a63nh5qkrLQe95sMcN4HRpaqhD9r/view Skyrim Wood]||Laeris||4|| ||Wood||75K||?||?||?||?||?
+
 
 +
|}
 +
 
 +
====Halo Removal====
 +
{| class="wikitable sortable"
 
|-
 
|-
|[https://drive.google.com/open?id=12fR-pWw6YL2ZbS6EDvrAeOVoQHWkWl5L Forest]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Wood / Leaves||160K||8||192||2.2K||Custom(?)||none
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 
|-
 
|-
|[https://drive.google.com/open?id=1xPzqzTG5L6y5I0U3W0oQjexwGF5zfG32 Map]||[[User:LyonHrt|LyonHrt]]||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Map / Old Paper with text||120K||8||192||2.311K||Custom(Scans)||none
+
| [https://drive.google.com/drive/u/1/folders/1pT75GdIU4JAH75eJzpxsaHfIoJ1a_gXB 1x_DeEdge_105000_G]
 +
| |[[User:Mutin_Choler|Mutin_Choler]]
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| Halo remover
 +
| 2020-11-03
 +
|  
 +
| 1xESRGAN
 +
| https://imgsli.com/MjgxMDU/3/0
 
|-
 
|-
|[https://mega.nz/folder/tFhl0L5b#CK4WLHYxjX7KFXU1PLNDuQ Morrowind Mixed]||mkultra||4||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Morrowind Mod Textures||115K-130K||16||128||56K||Morrowind Mod Textures||RRDB_PSNR_x4/RRDB_ESRGAN_x4
 
 
|}
 
|}
  
The map model was trained on '''maps, old documents, papers and various styles of typefaces/fonts'''. Based on a dataset contributed by alsa. [https://imgsli.com/MzMwNw Sample]
+
====Noise====
  
The Forest model is focused on '''trees, leaves, bark and stone''' can be used for double upscaling for even more detail. [https://imgsli.com/MzI2Nw Sample]
+
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
  
The Armory model was trained with '''modded textures form Skyrim''', including '''Clothing, Armor and Weapons'''. ('''Leather, Canvas and Metal''' should all work - maybe too sharp so interpolate)
+
|-
 +
| [https://drive.google.com/file/d/1GoUY7t5kE0Ubi-NDvlMB8lUs-_u_f6tS/view?usp=sharing LADDIER1]
 +
| Alexander Syring
 +
| 4x
 +
| Unknown
 +
| ESRGAN
 +
| Denoise
 +
| 2019-11-13
 +
| Remove noise, grain, box blur, lens blur and gaussian blur and increase overall image quality.
 +
| RRDB_ESRGAN_x4.pth
 +
|
 +
|-
  
The wood model was trained for Skyrim by Laeris.
+
| [https://drive.google.com/drive/u/1/folders/12j6BvuR7SU48ui9DHjBPB1vzPpQri9bD 1x_NoiseToner-Poisson-Detailed_108000_G]
 +
| |[[User:Mutin_Choler|Mutin_Choler]]
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| Noise remover
 +
| 2021-10-08
 +
| Attempts to remove the damages done from noise. Successor of sorts to Noisetoner_Poisson_150000_G
 +
| 1xESRGAN
 +
| https://imgsli.com/NzQ5MzM/2/0
 +
|-
  
The Skyrim Diffuse models is supposed to be used with Skyrim’s diffuse textures. It is a bit too sharp so I recommend to interpolating with the RDDB_ESRGAN_x4 model or the mangaAttempt109 model, look in [https://drive.google.com/drive/folders/1m1sgHiSZkmI4NbiXeBEZasf94WPqEsNF Deorder’s Skyrim Model Google Drive] for an already interpolated version.
+
| [https://drive.google.com/drive/u/1/folders/12j6BvuR7SU48ui9DHjBPB1vzPpQri9bD 1x_NoiseToner_Poisson_150000_G]
 +
| |[[User:Mutin_Choler|Mutin_Choler]]
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| Noise remover
 +
| 2020-10-14
 +
|
 +
| 1xESRGAN
 +
| https://imgsli.com/MjU1ODU/3/1
 +
|-
  
Fallout 4 weapons was trained using Fallout 4’s official HDarmor/weapon textures but could be used on other weapon and armor textures.
+
| [https://drive.google.com/drive/u/1/folders/12j6BvuR7SU48ui9DHjBPB1vzPpQri9bD 1x_NoiseToner_Uniform_100000_G]
 +
| |[[User:Mutin_Choler|Mutin_Choler]]
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| Noise remover
 +
| 2020-10-14
 +
|
 +
| 1xESRGAN
 +
| https://imgsli.com/MjU1Nzg/2/1
 +
|-
  
===Grayscale===
+
|-
 +
| [https://drive.google.com/file/d/1f5kIr3gG5GjbN_EM96CCB0nqu_2_56gh/view 1x_ISO_denoise_v1]
 +
| Alpha
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| denoise
 +
| not on discord
 +
| Remove high ISO noise
 +
| 1xESRGAN
 +
 
 +
|
 +
|-
 +
| [https://drive.google.com/file/d/1HSUvnQm56_CmVAAMjTfVn_Hi6a4Bm2h0/view 1x_ISO_denoise_v2]
 +
| Alpha
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| denoise
 +
| not on discord
 +
| Remove high ISO noise
 +
| ISO denoise v1
  
In digital photography, computer-generated imagery, and colorimetry, a grayscale or greyscale image is one in which the value of each pixel is a single sample representing only an amount of light, that is, it carries only intensity information. Grayscale images, a kind of black-and-white or gray monochrome, are composed exclusively of shades of gray. The contrast ranges from black at the weakest intensity to white at the strongest.[1]  
+
|
 +
|-
 +
| [https://drive.google.com/file/d/1kO3fx9FL5rKhoDk2n4kiiPWuCNHojkIR/view Film-Degrainer_1-000]
 +
| Tika
 +
| 1x
 +
| CC0
 +
| ESRGAN
 +
| denoise
 +
| not on discord
 +
| Remove film grain/noise
 +
| none
 +
|
 +
|}
 +
 
 +
 
 +
====Oversharpening====
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
|-  
+
! Author
|[https://drive.google.com/file/d/1trYs4AuC9s2JWAbryHdNyy5cgYV-V8cH/view Skyrim Alpha]||Deorder||4||[https://creativecommons.org/publicdomain/zero/1.0/ CC0]||Alpha Channel||105K||?||128||?||Alpha Channels from Skyrim||?
+
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://mega.nz/#!qRZD3SLL!RqP7cISIcoW5YakPya9CXEWSEHWqUSKdWLQSdYKGa14 1x_DeSharpen]
 +
| Loinne
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Denoise
 +
| 2019-06-03
 +
| Made for rare particular cases when the image was destroyed by applying noise, i.e. game textures or any badly exported photos. If your image does not have any oversharpening, it won't hurt them, leaving as is. In theory, this model knows when to activate and when to skip, also can successfully remove artifacts if only some parts of the image are oversharpened, for example in image consisting of several combined images, 1 of them with sharpen noise.
 +
| 1st attempt on random sharpening with the same dataset at 200000 iterations, which was trained on non-random desharp model, total ~600000 iterations on 3 models.
 +
|  
 
|-
 
|-
|[https://drive.google.com/open?id=1-mxmDF1Dh-PnQqRz_PeCrvsTkHjYCbi3 Deoldify]||TheAtheistGod||4||[https://creativecommons.org/publicdomain/zero/1.0/ CC0]||B/W Photo Restoration||790K||16||128||2.931M||[https://groups.csail.mit.edu/vision/datasets/ADE20K/ ADE20K], [https://data.vision.ee.ethz.ch/cvl/DIV2K/ DIV2K], [http://www.loc.gov/pictures/ Library of Congress]||Falcon Fanart (?)
 
 
|}
 
|}
  
Trained to upscale grayscale images, like specular or alpha etc.
+
====DeToon====
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
  
==Artifact Removal==
 
  
The models in this section were made to remove compression artifacts in images and textures.
+
|-
 +
| [https://drive.google.com/open?id=1uJvdx3g3GEY0VxMnHb0ItBvoc6pmGvuH detoon]
 +
| |[[User:LyonHrt|LyonHrt]]
 +
|
 +
|
 +
| ESRGAN
 +
| Detooning
 +
| 2019-06-24
 +
| A toon to realistic shading style model to wiki under drawings
 +
|
 +
|
 +
|-
  
===Blur===
+
| [https://drive.google.com/file/d/12vkDn35cuVnq2KYpkaA3XfCmk6zY_u4_/view?usp=sharing 1xDoubleDetoon]
 +
| Joey
 +
| 1x
 +
| CC BY-NC-SA
 +
| ESRGAN
 +
| Detooning
 +
| 2020-07-31
 +
| An attempt to detoon images/drawings of people
 +
| 1xESRGAN
 +
|
 +
|-
 +
|}
 +
 
 +
 
 +
 
 +
 
 +
====Image De/Colorization====
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://drive.google.com/file/d/1UgxnymTfLaVhY3aaDuBRnTZ9ehckKVKJ BS_Colorizer/Vapourizer]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 1x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| Colorization
 +
| 2020-01-30
 +
| Colorize Grayscale or Desaturated images. - This model is a partially failed attempt at restoring color from Grayscale | B/W | 100% Desaturated images. It mostly results in Blue and Yellow images with slight hints of Green, Orange and Magenta. You are free to use this as a pretrain to achieve better results.
 +
| 1xESRGAN
 +
|  
 
|-
 
|-
|[https://drive.google.com/file/d/1GoUY7t5kE0Ubi-NDvlMB8lUs-_u_f6tS/view?usp=sharing LADDIER1]||Alexander Syring||4||[https://creativecommons.org/publicdomain/zero/1.0/ CC0]||Remove noise, grain, box/lens/guassian blur||282K||8||128||12.7K||Mostly images of Nirvana, some of other images||RRDB_ESRGAN_x4.pth
+
 
 +
| [https://u.pcloud.link/publink/show?code=kZpAGFXZARxWIu9Pp4YDLUSIN8I8aFuJ5TKV 1x_SpongeColor-Lite]
 +
| Joey
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN (lite) [nf=32 nb=12]
 +
| Colorization
 +
| 2020-10-15
 +
| The first attempt at ESRGAN colorization that produces more than 2 colors. Doesn't work that great but it was a neat experiment.
 +
| none
 +
|  
 +
|-
 +
 
 +
|-
 +
| [https://drive.google.com/open?id=1-mxmDF1Dh-PnQqRz_PeCrvsTkHjYCbi3 Deoldify]
 +
| Rastrum
 +
| 4x
 +
| CC0
 +
| ESRGAN
 +
| Photos
 +
| 2019-08-29
 +
| Old black and white photo restoration.
 +
| Falcon Fanart
 +
|
 
|-
 
|-
|[https://de-next.owncube.com/index.php/s/aAojXwLTPZto8rP Fatality DeBlur]||[[User:Twittman|Twittman]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Deblurring||270K||1||128||41K||Mix of anime, manga, and photos||1x_DeJpeg_Fatality_01_175000_G.pth
 
 
|}
 
|}
  
Fatality DeBlur is intended for general deblurring of images, and has some robustness against compression and noise.
+
===Stylization===
 +
====Images====
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
  
LADDIER1 upscales images with noise, grain and different types of blur.
+
|-
 +
| [https://u.pcloud.link/publink/show?code=XZbO5pXZTEQNLwBzQjQCo1g8havjhSHCCSsV Rek's Effeks Photoanime v2]
 +
| Rek
 +
| 4x
 +
| GNU GPL3
 +
| ESRGAN
 +
| Stylization
 +
| 2020-10-17
 +
| Photo stylization from JPEGs. Trained on images upscaled by ISO Denoise v2 -> DeJPEG Fatality PlusULTRA -> NMKD Yan2. Essentially a combination of that model chain into one. Use if you're looking for a stylized output, not photo quality.
 +
| NMKD Yandere2
 +
|
 +
|-
 +
|}
  
===Noise===
+
==Specialized Models==
 +
===Text===
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 
|-
 
|-
|[https://drive.google.com/open?id=1f5kIr3gG5GjbN_EM96CCB0nqu_2_56gh ISO denoise v1]||[https://github.com/alpha0010/ Alpha]||1||[https://creativecommons.org/publicdomain/zero/1.0/ CC0]||Remove high ISO noise||372K||1||128||170K||Custom (DSLR photos)||1xESRGAN.pth
+
| [https://drive.google.com/file/d/15ovbadCoYs7q8nSd5Mq02PqBOpwiBkoS/view 2x_BSTexty]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 2x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| Text
 +
| 2020-03-04
 +
| As the name might suggest, this model aims to upscale text with less distortion that other models. It seems to do a good job generally, but don't expect it to be a state of the art model that can upscale magazines and stuff. It makes things more readable but since it was train on B/W pictures it desaturates them.
 +
| 2x_ESRGAN
 +
|  
 +
 
 
|-
 
|-
|[https://drive.google.com/open?id=1HSUvnQm56_CmVAAMjTfVn_Hi6a4Bm2h0 ISO denoise v2]||[https://github.com/alpha0010/ Alpha]||1||[https://creativecommons.org/publicdomain/zero/1.0/ CC0]||Remove high ISO noise||308K||1||128||239K||Custom (DSLR photos)||1x_ISO_denoise_v1.pth
+
| [https://icedrive.net/1/43GNBihZyi NMKD Typescale]
 +
| |[[User:nmkd|Nmkd]]
 +
| 8x
 +
| WTFPL
 +
| ESRGAN
 +
| Text
 +
| 2020-11-04
 +
| Low-resolution text/typography and symbols
 +
| 8xESRGAN
 
|-
 
|-
|[https://drive.google.com/file/d/1hmWB6EV1DXYt9N_ofbO4XGUCJVKZZXwl/view NoiseToner]||[[User:Mutin Choler|Mutin Choler]]||1||[http://www.wtfpl.net/ WTFPL]||Remove high ISO noise||110K||1||128||150||Custom (Photos)||1xESRGAN
 
 
|}
 
|}
High ISO is required to capture images at very high shutter speeds and/or in poor lighting. However, increasing ISO also results in noise that is challenging to remove without also losing fine details. To remove this noise without damaging details, one can apply the technique of median stacking: combine 10-100 photos of the exact same object to separate the signal (clear photo) from noise.
 
  
ISO denoise v1 is trained on a handcraft set of pairs between original noisy photos and median stacked counterparts. It tends to be conservative, avoiding modifying anything that does not closely resemble camera ISO noise. ISO denoise v2 uses a larger dataset, handling some cases better and some cases worse than v1. If results are unsatisfactory with one model, try the other model.
+
===Inpainting===
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
  
===JPG Compression===
+
|-
 +
| [https://e.pcloud.link/publink/show?code=kZQOu7ZldzmFyMPUcFNGkEvwqOxQ8Bl3CeX 1x_sudo_inpaint_PartialConv2D_424000_G.pth]
 +
| sudo rm -rf / --no-preserve-root#8353
 +
| 1x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Inpainting
 +
| 2020-12-05
 +
| Experimental PartialConv2D attempt to paint with ESRGAN. Took ~10.4 days of training on a P100 and around 1.5 months in total due to Colab limits. Not sure if I will continue training it since training is very slow, but may get better.. Warning: Result can vary with different tilesizes. Try not to tile your data.
 +
| None
 +
| [https://e.pcloud.link/publink/show?code=kZQOu7ZldzmFyMPUcFNGkEvwqOxQ8Bl3CeX Samples]
  
 +
|-
 +
| [https://icedrive.net/1/43GNBihZyi 1x_NMKD-YandereInpaint_375000_G.pth]
 +
| [[User:nmkd|Nmkd]]
 +
| 1x
 +
| Unknown
 +
| ESRGAN
 +
| Inpainting
 +
| Unknown
 +
|
 +
| None
 +
| [https://icedrive.net/1/43GNBihZyi Samples]
 +
|-
 +
 +
|}
 +
 +
===Fabric/Cloth===
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
|-
+
! Author
|[https://e.pcloud.link/publink/show?code=XZvmsZo4qORoatgHXm4A1CooSUnuy5YD5X jpg (0-20%) alsa]||[[User:Alsa|Alsa]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||JPG compressed Images||178K||2||128||6.23K||Custom (Photos / Manga)||[https://mega.nz/#!OzpFHYAD!0swA_J18bSygyVgMHac3P4kkBx6ZYUHNnL9qXhiu-9I JPG (20-40%)]
+
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 
|-
 
|-
|[https://e.pcloud.link/publink/show?code=XZimsZmfeBi2HJp9H00wvCRISpnuSRrjgy jpg (20-40%) alsa]||[[User:Alsa|Alsa]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||JPG compressed Images||141K||2||128||6.23K||Custom (Photos / Manga)||[https://mega.nz/#!Kr5Q1C7C!yq4910SjvAyMS_40IhrOsShA21OXdP8rxfiMsEuYbW8 JPG (40-60%)]
+
| [https://mega.nz/folder/6EJjwADL#oDvv9p0z1t9nQvObbvBRBQ 4x-Fabric and Fabric-Alt]
 +
| |[[User:Kim2091|Kim2091]]
 +
| 4x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Fabric
 +
| 2021-09-15
 +
| This model set upscales fabric or cloth textures (works on cats too!). The Alt model is just an earlier iteration version. It may work better on some images.The images need to be minimally compressed or passed through a decompression model first. It works with DDS compression though.
 +
| 4xESRGAN
 +
| [https://cdn.discordapp.com/attachments/887850596214902835/887852703873638410/unknown.png Sample 1] [https://cdn.discordapp.com/attachments/887850596214902835/887852170156847124/unknown.png Sample 2] [https://cdn.discordapp.com/attachments/887850596214902835/887856392269094952/unknown.png Sample 3] [https://cdn.discordapp.com/attachments/887850596214902835/887853344545194084/unknown.png Sample 4]
 +
 
 +
|}
 +
 
 +
 
 +
===Alphas===
 +
{| class="wikitable sortable"
 
|-
 
|-
|[https://e.pcloud.link/publink/show?code=XZrmsZbOaINRer4xRn6UWBtGgRK5r7biWy jpg (40-60%) alsa]||[[User:Alsa|Alsa]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||JPG compressed Images||100K||2||128||~6.5K||Custom (Photos / Manga)||[https://mega.nz/#!6j4RRQBD!3CX7XN9ZEAeWR3aXBAsDRpxSfKbM8zR1N9GXgbP38Ig JPG (60-80%)]
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 
|-
 
|-
|[https://e.pcloud.link/publink/show?code=XZcmsZASeN84hQXCLfhYzUogomG5EdkwPV jpg (60-80%) alsa]||[[User:Alsa|Alsa]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||JPG compressed Images||91K||2||128||~6.5K||Custom (Photos / Manga)||[https://mega.nz/#!2uxwRYYT!2KgAsRac70jqYYXyOvQ5HSd4ipoqC0WGB4Md2Su_OM8 JPG (80-100%)]
+
|[https://drive.google.com/open?id=192Mw2_yUwCgqt3tAJ2sRxZ8hYHe4CKrZ FireAlpha]
 +
| |[[User:BlueAmulet|BlueAmulet]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Alpha (4 channel)
 +
| 2019-11-12
 +
|  
 +
| none
 +
|  
 
|-
 
|-
|[https://e.pcloud.link/publink/show?code=XZomsZwGOr2Jb4lLXGopIwu8UtNQqpuqyX jpg (80-100%) alsa]||[[User:Alsa|Alsa]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||JPG compressed Images||162K||2||128||~6.5K||Custom (Photos / Manga)||[https://mega.nz/#!emAAQa6B!xItl6e7WIyq1ZbXXWtLaKn7M2it7j8Rx_-wvxDjWdQQ BC1 take 1]
+
 
 +
| [https://u.pcloud.link/publink/show?code=kZQfN4XZmIrkODabBWhtmmA95c0GMb19WUuy 4x_1ch-Alpha-Lite]
 +
| Joey
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Alpha
 +
| 2020-12-15
 +
| Obsoleted by Joey's Fork - Alpha channels of PNGs
 +
| none
 +
|  
 
|-
 
|-
|[https://drive.google.com/file/d/1AjVnJCne4_JNYKGfzeogNxXo5zXMCGLe/view jpg (20-40%) BlueAmulet]||[[User:BlueAmulet|BlueAmulet]]||1||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||JPG compressed Images||535K||1||128||52.789K||Custom (CC0 Textures)||[https://mega.nz/#!Kr5Q1C7C!yq4910SjvAyMS_40IhrOsShA21OXdP8rxfiMsEuYbW8 JPG (40-60%)]
+
 
 +
| [https://u.pcloud.link/publink/show?code=kZkR7hXZhfCA4WvVQvbxXkNN50tazuxj73uX 2x_Gen5-Alpha]
 +
| Joey
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Pixel Art with Tranparency / Alpha Channel
 +
| 2021-02-03
 +
|  
 +
| 4xFireAlpha
 +
|  
 
|-
 
|-
|[https://drive.google.com/file/d/1maYmC5yyzWCC42X5O0HeDuepsLFh7AV4/view jpg (0-20%) BlueAmulet]||[[User:BlueAmulet|BlueAmulet]]||1||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||JPG compressed Images||610K||1||128||52.789K||Custom (CC0 Textures)||[https://mega.nz/#!OzpFHYAD!0swA_J18bSygyVgMHac3P4kkBx6ZYUHNnL9qXhiu-9I JPG (20-40%)]
+
 
 +
| [https://u.pcloud.link/publink/show?code=kZeNFhXZbuw2jGJOGqQnKecb8Moo1ha47W57 8x_Sphax-Alpha-NN]
 +
| Joey
 +
| 8x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Pixel Art with Tranparency / Alpha Channel
 +
| 2021-02-04
 +
| Replica of sphax with transparency
 +
| 4xFireAlpha
 +
|  
 
|-
 
|-
|[https://drive.google.com/file/d/1lgpo60okKC_9D6mzymHOvwdJDsOqxi7j/view jpg (40-60%) BlueAmulet]||[[User:BlueAmulet|BlueAmulet]]||1||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||JPG compressed Images||550K||1||128||52.789K||Custom (CC0 Textures)||[https://mega.nz/#!6j4RRQBD!3CX7XN9ZEAeWR3aXBAsDRpxSfKbM8zR1N9GXgbP38Ig JPG (60-80%)]
+
 
 +
| [https://u.pcloud.link/publink/show?code=kZrIFhXZxnpi72FuwgLz7FIDw8kdrp2suIEk 4x_PocketMonsters-Alpha]
 +
| Joey
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Pixel Art with Tranparency / Alpha Channel
 +
| 2021-02-04
 +
| upscaling pixel art with alpha channels that should perform better than any other. It should work well on both cartoon and 3D styled content.
 +
| 4xFireAlpha
 +
|  
 
|-
 
|-
|[https://drive.google.com/file/d/1V2PTYzMMDIB7NNCp-ZXhIf26a0xHO2b2/view jpg (60-80%) BlueAmulet]||[[User:BlueAmulet|BlueAmulet]]||1||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||JPG compressed Images||545K||1||128||52.789K||Custom (CC0 Textures)||[https://mega.nz/#!2uxwRYYT!2KgAsRac70jqYYXyOvQ5HSd4ipoqC0WGB4Md2Su_OM8 JPG (80-100%)]
+
 
 +
| [https://drive.google.com/file/d/1trYs4AuC9s2JWAbryHdNyy5cgYV-V8cH/view Skyrim Alpha]
 +
| Deorder
 +
| 4x
 +
|[https://creativecommons.org/publicdomain/zero/1.0/ CC0]
 +
| ESRGAN
 +
| Pixel Art with Tranparency / Alpha Channel
 +
|  
 +
| Dataset: Alpha Channels from Skyrim
 +
| Unknown
 +
|  
 
|-
 
|-
|[https://drive.google.com/file/d/17ocFMDz4jfYH73mT_4i1099JCGVnOHd2/view jpg (80-100%) BlueAmulet]||[[User:BlueAmulet|BlueAmulet]]||1||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||JPG compressed Images||550K||1||128||52.789K||Custom (CC0 Textures)||[https://mega.nz/#!emAAQa6B!xItl6e7WIyq1ZbXXWtLaKn7M2it7j8Rx_-wvxDjWdQQ BC1 take 1]
+
|}
 +
 
 +
===CGI===
 +
{| class="wikitable sortable"
 
|-
 
|-
|[https://de-next.owncube.com/index.php/s/jetoMQkKNLfRkYY JPG PlusULTRA]||[[User:Twittman|Twittman]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||JPG compressed Images||130K||1||?||0.937K||Custom (Manga)||Failed Attempts
+
! Model Name
|-  
+
! Author
|[https://de-next.owncube.com/index.php/s/w82HLrLWmWi4SQ5 DeJpeg Fatality PlusULTRA]||[[User:Twittman|Twittman]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||JPG compressed Images||200K||1||128||26K||Real life, Manga and digital text||1x_DeJpeg_Fatality_01_200000_G.pth
+
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
|-
 +
 
 +
| [https://1drv.ms/u/s!Aip-EMByJHY20wpGoLuSRzjdqh0T WaifuGAN_v3_30000]
 +
| DinnJerr
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| CGI
 +
| 2019-07-12
 +
| Upscaling CG-painted anime with variable outlines.
 +
| Manga109v2.pth
 +
|  
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/file/d/1zlc8BWOcpCbSZpwf7ArMCqpb0Tf9DlZk/view?usp=drivesdk 2xBS_Wolly]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 2x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| CGI Animation
 +
| 2020-02-07
 +
| Pixar Movies or Wall-E pictures/frames
 +
| 2xESRGAN
 +
|
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/1kNSz5f2_krdlsJ700DwH78OEPYkkcjW5/view?usp=sharing 4xSGI]
 +
| ChrisNonyminus
 +
| 4x
 +
| GNU GPL3
 +
| ESRGAN
 +
| CGI
 +
| 2020-12-17
 +
| Upscaling and dedithering pre-rendered sprites, images and textures made in the 90s. Basically vintage CGI.
 +
| 4xESRGAN
 +
| https://imgur.com/a/iwLTjeB
 +
|-
 +
 
 +
| [https://lbry.tv/@Madiator2011:e/x2_CGIMaster_v1:6 CGIMaster_v1]
 +
| Madiator
 +
| 2x
 +
| GNU GPL3
 +
| ESRGAN
 +
| CGI Animation
 +
| 2021-01-14
 +
| mixed 3D/2D CGI animations on some 2D animations it might sharpen the edges. General usage is to upscale CGI animations compressed by YouTube.
 +
| Sharp_Anime_v2
 +
| https://imgsli.com/Mzc1NTM
 
|-
 
|-
|[https://u.pcloud.link/publink/show?code=kZuDPakZRh7Wrg6YSBkUdHPm3NsyJ5GtI570 NMKDJaywreck]||[[User:Nmkd|nmkd]]||1||[http://www.wtfpl.net/ WTFPL]||JPG compressed Images||190k||1/2||132||900||DIV2K Train + Test||4xESRGAN
 
 
|}
 
|}
  
JPG gets compressed with a Quality Percentage between 0 and 100. So depending on how bad your JPEGs are compressed, choose the model of your choice. You can use [https://imagemagick.org/index.php ImageMagick] to guess the Quality percentage, but keep in mind that it might be wrong, since the image might have been re-saved.
+
===Luminance/Chroma===
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
  
JPG PlusULTRA, while not considered successful in its initial purpose, may find some use on certain unique images.
+
|-
 +
| [https://drive.google.com/file/d/1FDb9H6GOmE3aRvZbx_-kTiCLS77WyjgL/view 1x_BSLuma]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 1x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| Luma
 +
| 2020-02-28
 +
| Fix Luminance issues?? LumaSharpen ESRGAN Edition? - This model mostly does what "Lumasharpen" algorithms do. It may help fixing images with Luminance images issues? Like old DVD rips? I am not sure, didn't test.
 +
| none
 +
|
 +
|-
  
DeJpeg Fatality PlusULTRA is its burly strongman big brother. Anything and everything that is JPG will tremble before you!
+
| [https://drive.google.com/file/d/12v_2OwrB_rr6_0tMshHaHgD_XWRNgIyF/view 1x_BSChroma]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 1x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| Sharpen
 +
| 2020-02-29
 +
| ChromaSharpen - makes the colors slightly more vibrant with a sideeffect of possibly adding Chromatic Abberation to the image. I am not sure about the usage of this model on real case scenarios but anything blurry or with fuzzy colors could work
 +
| none
 +
|
 +
|-
 +
|}
  
NMKDJaywreck is trained to handle any amount of JPEG compression, even removing artifacts of quality 5 JPEGs. Its only weakness is a slight tendency to oversharpen certain textures. It's recommended to not use this model for very small images (<256px due to the large HR size it was trained on.
+
===Cats===
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
  
===DDS Files with BC1/DXT1, BC3/DXT5 Compression===
+
|-
 +
| |[https://f002.backblazeb2.com/file/ESRGAN/_RELEASE/4x_cat_patch_325000_G.pth Cat_Patch]
 +
| |[[User:Twittman|Twittman]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0] (?)
 +
| ESRGAN
 +
| Cats
 +
| not on discord
 +
|
 +
| previous attempt
 +
|
 +
|-
 +
|}
  
 +
===Coins===
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
|-
+
! Author
|[https://e.pcloud.link/publink/show?code=XZXbsZK03Y0UsmtR0W7wRMHWGvYkzgPII7 bc1 sharp 3.0]||[[User:Alsa|Alsa]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||BC1 Compression||400K||2||128||28.985K||Custom (just about everything)||[https://mega.nz/#!r2hEAAAb!zdk-Ka6VCqVnKThtfJVYM0NnVBSUyeqsjYs-NgKjLkc BC1 take 2]
+
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 
|-
 
|-
|[https://drive.google.com/open?id=1LHplsPRqhmjR28jGgRlEekeP_bvx3nUC bc1 smooth 2.0]||[[User:BlueAmulet|BlueAmulet]]||1||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||BC1 Compression||1M||20||32||4767||Custom (? including normal maps)||none (no interpolation)
+
| [https://drive.google.com/file/d/1zC97RLUg5ejqb5-4Dj5q-SzdLPLiMozH/view 4x_Nickelfront]
 +
| BlackScout
 +
| 4x
 +
| GNU GPLv3
 +
| ESRGAN
 +
| Coins
 +
| 2020-02-13
 +
| Upscale coins. That's it. If you were mad at me because Nickelback doesn't make any sense. Now you have the perfect solution to your problems. If you want to upscale nickels or anything with similar texture made out of metal, now you can. It works pretty well for a joke.
 +
| 4xESRGAN
 +
|  
 
|-
 
|-
|[https://drive.google.com/file/d/1ZZJQjzW18MQfIVcNzQshYx1JBlwAlPYE/view?usp=sharing BCGone]||[[User:Mutin Choler|Mutin Choler]]||1||[http://www.wtfpl.net/ WTFPL]||BC1 Compression||205K||1||128||250||Custom (Photos)||1xESRGAN
 
 
|}
 
|}
  
BC1 (DXT1) compression is commonly used in dds textures, which are utilized in most PC games today, it allows to shrink the texture to 1/6 of the original size, reducing VRAM usage. There is also BC3 (DXT5) which uses BC1 compression for the color channels and leaves the alpha channel uncompressed, this one reduces the file size to 1/3 of the original. But this compression comes at a cost. The BC1 models are designed to reverse the damage done by the compression. This is a must if you want to upscale a dds file that uses either BC1 or BC3 compression. The free variant has more freedom when dealing with the images and should lead to better results. The restricted version only deals with perfect images compressed once (ideal case) so will perform worse in any other scenario, but it tries to preserve the original colors more. You can interpolate between restricted and unrestricted if you want.
+
===Faces===
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://de-next.owncube.com/index.php/s/PF5GTJ9jix4Log8 4x_Faces_N_250000.pth]
 +
| |[[User:Twittman|Twittman]]
 +
| 4x
 +
|
 +
| ESRGAN
 +
| Faces
 +
| 2019-07-18
 +
| Upscales images of faces of different scales, sometimes resulting in monsters.
 +
| 4xESRGAN
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://de-next.owncube.com/index.php/s/PF5GTJ9jix4Log8 4x_Faces_04_N_180000_G]
 +
| |[[User:Twittman|Twittman]]
 +
| 4x
 +
|
 +
| ESRGAN
 +
| Faces
 +
| 2019-07-23
 +
| Upscale faces both pixelized and real
 +
| 4x_Faces_N_250000.pth
 +
|
 +
|-
  
===Cinepak, msvideo1 and Roq===
+
|-
 +
| [https://de-next.owncube.com/index.php/s/mZRG4HB3KdP2iP6 Face-Ality V1 (4x_Fatality_Faces_310000_G.pth)]
 +
| |[[User:Twittman|Twittman]]
 +
| 4x
 +
| [https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0] (?)
 +
| ESRGAN
 +
| Faces
 +
|
 +
| Dataset: Custom (Faces)
 +
| 4x_Faces_04_N_180000_G.pth
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://drive.google.com/open?id=1OyOJIW224hBhb-aTCbuUQb0qzKmE4oH6 TGHQFace8x]
 +
| tg
 +
| 8x
 +
| GNU GPL3
 +
| ESRGAN
 +
| Faces
 +
| 2019-11-27
 +
| Upscales blurry 128px faces, usefull for enhancing that someone in a small picture.
 +
| 8xESRGAN
 +
| https://imgsli.com/OTM1NQ
 +
|-
 +
 
 +
| [https://onedrive.live.com/?authkey=%21AP69c97OwKxR3lM&id=36762472C0107E2A%2110699&cid=36762472C0107E2A FArtFace]
 +
| |[[User:DinJerr|DinJerr]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]
 +
| ESRGAN
 +
| Faces
 +
| 2019-11-28
 +
|
 +
|
 +
|
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/14daAyYuoX-nZ_Lo1U6oekbFqrZTQlQkG/view?usp=drivesdk 4x_BS_SbeveHarvey]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 4x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| Faces
 +
| 2020-07-24
 +
| Upscale Steve Harvey, but maybe other things, somehow??
 +
| 4xESRGAN
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://drive.google.com/file/d/19ICMKNuS4PbhmtA7Be9lUE6v8NHDDEzP/view Face Focus]
 +
| |[[User:LyonHrt|LyonHrt]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Faces
 +
| not on discord
 +
| Face De-blur - slightly out of focus / blurred images of faces. It is aimed at faces / hair
 +
| 4xPSNR
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://drive.google.com/file/d/1OyOJIW224hBhb-aTCbuUQb0qzKmE4oH6/view TGHQFace8x]
 +
| |[[User:Torrentguy|Torrentguy]]
 +
| 8x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]]
 +
| ESRGAN
 +
| Face Upscaling
 +
|
 +
|
 +
| 8xESRGAN
 +
|
 +
|-
 +
|}
 +
 
 +
===Foliage/Ground===
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://drive.google.com/drive/folders/1ZcMD3hy1YCm-hsrT6xYGvhboxSzhrJKg 1x_Plants_400000_G.pth]
 +
| Muf
 +
| 1x
 +
| Public Domain
 +
| ESRGAN
 +
| bad upscale
 +
| 2021-06-23
 +
| 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.
 +
| 1x_NMKD-h264Texturize_500k.pth
 +
| https://imgsli.com/NTg2MDk https://imgsli.com/NTg2MDg https://imgsli.com/NTg2MTA
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/1dGmhHUPmb3lO9buX_Bt2nq97Nk5MCTb4/view Ground]
 +
| ZaphodBreeblebox
 +
| 4x
 +
|  
 +
| ESRGAN
 +
| Upscales ground textures
 +
| 2021-06-23
 +
| Dataset: Custom (Ground textures Google)
 +
|  
 +
|  
 
|-
 
|-
|[https://drive.google.com/open?id=1TMhjBAKVuDivz7FrAt-Qu7wufEJV6VUq Cinepak_alt]||buildist||1||GNU GPLv3||Cinepak (only)||240K||1||128||2,640||Flickr2K||none (no interpolation)
 
|-
 
|[https://de-next.owncube.com/index.php/s/wKjLmYsq7M5JAmx Cinepak]||[[User:Twittman|Twittman]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Cinepak, msvideo1 and Roq||200K||1||128||~8K||Custom (Manga)||none (no interpolation)
 
 
|}
 
|}
  
The Cinepak model removes movie compressions artifacts from older video compression methods like Cinepak, msvideo1 and Roq. Cinepak_alt may work better for video frames with realistic content.
+
===Video Games===
 +
====Game Screenshots====
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://drive.google.com/file/d/1DbbM4saRpJu0dmgvccQFwfF4zI2rjiQ_ Minepack]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 4x
 +
| CC BY-NC-SA
 +
| ESRGAN
 +
| Upscaling pack.png
 +
| 2020-01-26
 +
| Upscales Minecraft screenshots by 4x. May suffer from haloing, weird patterns on blocks and JPEG-like artifacts.
 +
| 4xESRGAN.pth
 +
|
 +
|-
 +
 
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/1Xe1JorGFJzPClR9tUuGmpuMyLhTA-d2T/view?usp=sharing 4xPackCraft_v4]
 +
| Joey
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Upscaling pack.png
 +
| 2020-09-05
 +
| Designed to upscale one specific minecraft screenshot. Results on dissimilar screenshots may be poor.
 +
| 4xESRGAN/previous versions
 +
| https://cdn.discordapp.com/attachments/436411385673547787/750481717307113543/pack.png
 +
|-
 +
 
 +
|-
 +
| [https://drive.google.com/drive/folders/1XsOFqGx_cGMWQTBuE9K9smwULg_wiaWc?usp=sharing MinecraftAlphaUpscaler with Good data]
 +
| Washed Up
 +
| 4x
 +
| [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| Upscaling pack.png
 +
| 2020-01-29
 +
| Designed to upscale one specific minecraft screenshot. Results on dissimilar screenshots may be poor.
 +
| RRDB_PNSR_x4.pth
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://drive.google.com/file/d/1MkqAuELmbhrEGcD55IUJhDFFNniOmNWN ScreenBooster V2]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 4x
 +
| CC BY-NC-SA
 +
| ESRGAN
 +
| CGI
 +
| 2020-01-29
 +
| Game Screenshots
 +
| none
 +
|
 +
|-
  
===Color Reduction===
+
|-
 +
| [https://drive.google.com/file/d/1JI8VZSSHpH9u7HzE8MvuNG351Dgn4jwU/view?usp=sharing BS_ScreenBooster_SPSR]
 +
| |[[User:BlackScout|BlackScout]]
 +
| 4x
 +
| CC BY-NC-SA
 +
| SPSR
 +
| CGI
 +
| 2020-07-18
 +
| This model is designed to upscale game screenshots (3D Games) by 4 times. The SPSR version is an improvement over the ESRGAN based V2.
 +
| Screenbooster V2
 +
|
 +
|-
 +
|}
  
====Dithering====
+
====Normal Map/Bump Map Generation====
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
|-
+
! Author
|[https://e.pcloud.link/publink/show?code=XZ5bsZtd0ldzEF2UFLSYqIBNhqNH21slxX dithering]||[[User:Alsa|Alsa]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Dithered Images||127K||2||128||4.7K||Custom (Photos / Manga)||[https://mega.nz/#!7io2gSQR!UB9u2k51daixTgC2H0LdOWzNlkDyIDHwxBX4BVY2J3k JPG (0-20%)]
+
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 
|-
 
|-
|[https://drive.google.com/file/d/1H4KQyhcknOoExjvDdsoxAgTBMO7JuJ3w/view FSDedither]||buildist (Jacob_)||4||GNU GPLv3||Photos/realistic images with dithering||55K||16||128||~20K||Flickr2K+DIV2K dithered with GIMP||4xESRGAN
+
| [https://u.pcloud.link/publink/show?code=kZEdNHXZ3bpVwUoge94d9igFWxbjQQrcbpny 1x_NormalMapGenerator-CX-Lite]
 +
| Joey
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN Lite [nf=32 nb=12]
 +
| Map Generation - normal maps
 +
| 2020-11-04
 +
| Generating normal maps from textures
 +
| 1x_DIV2K-Lite_450k.pth
 +
|
 
|-
 
|-
|[https://buildism.net/files/4xFSDedither_Riven.pth FSDedither Riven]||buildist (Jacob_)||4||GNU GPLv3||Photos/realistic images with dithering||200K||24||128||~20K||Flickr2K+DIV2K with different types of dithering applied||4xESRGAN
+
 
 +
| [https://u.pcloud.link/publink/show?code=kZecVzXZEO6fAyO6w25YDc43BkSVHRgFdOwX 1x_FrankenMapGenerator-CX-Lite]
 +
| Joey
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN Lite [nf=32 nb=12]
 +
| Map Generation - roughness and displacement maps
 +
| 2020-11-07
 +
| This model generates "Franken Maps" (named after Frankenstein), which is a custom material map combination I made. Basically, the Red channel of RGB is just the texture converted to grayscale, the Green channel is the roughness map, and the Blue channel is the displacement map. I had to do this to get around the current limitation of CX loss where it requires a 3 channel output (otherwise I would have just made a 2 channel model, or separate single channel models). As of right now the channels need to be manually split from each other but I will be making a tool for doing this automatically in the coming days.
 +
| 1x_DIV2K-Lite_450k.pth
 +
|  
 
|-
 
|-
|[https://buildism.net/files/4xFSDedither_Riven_Smooth.pth FSDedither Riven Smooth]||buildist (Jacob_)||4||GNU GPLv3||Photos/realistic images with dithering||191K||24||128||~40K||Flickr2K+DIV2K with different types of dithering applied||4xFSDedither_Riven
+
 
 +
| [https://drive.google.com/file/d/1uksv1uyyZjQcU4567OrfU0w2NECcG8dY/view 1x_normals_generator_general_215k]
 +
| [[User:LyonHrt|LyonHrt]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Map Generation - Normal Maps
 +
|  
 +
| This model generates "Franken Maps" (named after Frankenstein), which is a custom material map combination I made. Basically, the Red channel of RGB is just the texture converted to grayscale, the Green channel is the roughness map, and the Blue channel is the displacement map. I had to do this to get around the current limitation of CX loss where it requires a 3 channel output (otherwise I would have just made a 2 channel model, or separate single channel models). As of right now the channels need to be manually split from each other but I will be making a tool for doing this automatically in the coming days.
 +
| none (no interpolation)
 +
|  
 +
|-
 +
 
 
|}
 
|}
  
Dithering is an older compression method, where the amount of colors gets reduced, if your image has few colors and have a noise like pattern in them try a De-Dither model.
+
====Video Game Textures====
Ordered dithering is a less common form of dithering that results in distinctive checkerboard/crosshatch patterns, which are misinterpreted as texture by models not trained on it. It’s often used on GIFs because the pattern is stable between frames.
+
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
 
 +
|-
 +
| [https://1drv.ms/u/s!AiWox1lAWLoTg1bUeJouJNOFZ_Jj Fallout Weapons (Fallout 4 Weapons?)]
 +
| Bob
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Game textures
 +
| 2019-08-05
 +
| Video game textures, mostly metal rusty, clean or painted
 +
| Manga109Attempt
 +
|
 +
|-
 +
 
 +
| [https://1drv.ms/u/s!AiWox1lAWLoThANuXjxIR-hqA6os Fallout Weapons V2]
 +
| Bob
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Game textures
 +
| 2019-08-23
 +
| Video game textures, mostly metal rusty, clean or painted
 +
| Fallout 4 Weapons
 +
|
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/file/d/1y9nYjuy8vG7_LHpveYTj0ihK_6fE2XKF/view?usp=sharing 4x_ThiefGoldMod_100000]
 +
| Akven
 +
| 4x
 +
| no idea
 +
| ESRGAN
 +
| Game textures
 +
| 2020-05-15
 +
| Version of the previous model but based on Manga109 pretrained model and with slightly different dataset. Sometimes gives better results especially for wood and metal, sometimes worse. Sometime generates the same dotted artifacts on very bright/white images.
 +
| 4x_Manga109Attempt
 +
| https://imgsli.com/MTYzNjI
 +
|-
  
4sFSDedither is made for photos/realistic images, but worth trying on other images that have reduced colors and dithering along with fine details. Trained using the ESRGAN-FS code for better details compared to plain ESRGAN.
 
  
4xFSDedither_Riven is a remake of 4xFSDedither that is fine-tuned to upscale images from the game Riven, but should be better in general, particularly on ordered dithering. I adjusted the dataset to have a better variety of dithering parameters, and turned up the HFEN and pixel loss to get better details and color restoration with less noise. 4xFSDedither_Riven_Smooth adds images with nearest-neighbor downscaling to the dataset for a smoother (but possibly less detailed) result.
+
| [https://drive.google.com/file/d/1L8reADxi5Nt-8Tki0oY5jkQlv6kJg6w4/view?usp=sharing 4x_ThiefGold_110000]
 +
| Akven
 +
| 4x
 +
| no idea
 +
| ESRGAN
 +
| Game textures
 +
| 2020-05-15
 +
| Various game textures. Primary wood, metal, stone
 +
| RRDB_ESRGAN_x4
 +
| https://imgsli.com/MTYzNjI
 +
|-
  
====Banding====
+
| [https://mega.nz/folder/HNh0hLzD#vUuFhp2ZAeNi_5shZfCC0g 4x-VolArt]
{| class="wikitable sortable"
+
| |[[User:Kim2091|Kim2091]]
 +
| 4x
 +
| CC BY-NC-SA 4.0
 +
| ESRGAN
 +
| Game textures/Art
 +
| 2021-09-18
 +
| 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.
 +
| 4xESRGAN
 +
| [https://cdn.discordapp.com/attachments/888869052867543060/888869070928248852/unknown.png Sample 1] [https://cdn.discordapp.com/attachments/888869052867543060/888869784169619496/unknown.png Sample 2]
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/file/d/1Ful_AALrK-gxSwsTeMkzvwX5hh1ah8X8/view?usp=sharing 2xFaithfulSPSR]
 +
| Joey
 +
| 2x
 +
| CC BY-NC-SA
 +
| SPSR
 +
| Pixel art
 +
| 2020-07-19
 +
| Mainly just a test for SPSR. Seems to work better than the original 2xFaithful32_1316 that I used as a pretrained, even though it uses the same dataset.
 +
| 2xFaithful32_1316
 +
|
 +
|-
 +
 
 +
| [https://u.pcloud.link/publink/show?code=kZUMKFXZUG6BpzHR6wFGack19pvWgbQQ9OA7 2x_FakeFaith-Lite]
 +
| Joey
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN (lite)
 +
| Pixel Art
 +
| 2020-10-12
 +
| An attempt at recreating the "faithful" style without using the faithful dataset -- aka keeping the "pixel art" style of pixel art.
 +
| 2x_Faithful-Lite
 +
|
 +
|-
 +
 
 +
| [https://u.pcloud.link/publink/show?code=XZHawFXZhqD7dF4qtYHnqJVPnQd0ey0vW1JX 2x_Faithful-Lite]
 +
| Joey
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN (lite)
 +
| Pixel Art
 +
| 2020-10-12
 +
| A "lite" model version of my Faithful model
 +
| none
 +
|
 +
|-
 +
 
 +
| [https://u.pcloud.link/publink/show?code=XZTAmsXZzEO8tMJaYAF1MrKKnmOCKu7Ghedy 1x_DXTless_SourceEngine_170000_G]
 +
| Xeller
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| DTX5 Compression
 +
| 2021-04-10
 +
| This model is made for Source Engine textures. It tries to remove compression artifacts such as blockyness, discoloration, green tint. It does pretty well on a lot of things, realistic stuff as well, but it was mostly made to work on TF2 textures. It's made to keep as much detail as possible, without any unnecessary denoising/sharpening. Huge thanks to Twittman for assisting me along this journey.
 +
| 1x_Saiyajin_DeJpeg_300000_G
 +
| https://imgsli.com/NDk1NTk https://imgsli.com/NDk1NjA https://imgsli.com/NDk1NjE https://imgsli.com/NDk1NjI
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/1HIBRKFs7s-XhpN1p7rwAWcMTHwFRqn3n/view Trixie]
 +
| |[[User:LyonHrt|LyonHrt]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Faces / Game Textures
 +
| not on discord
 +
| 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
 +
| none
 +
|
 +
|-
 +
 
 +
| [https://e.pcloud.link/publink/show?code=XZGmsZo1yNrot19O4R5SrPVD1GWpRy1MKX Skyrim Armory]
 +
| |[[User:Alsa|Alsa]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Game textures/equipment
 +
| not on discord
 +
|
 +
| Manga109Attempt
 +
|
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/file/d/1RjVWNUFtVyz4ykqu6Pm9wmO03pPEBGqg/view Skyrim Misc]
 +
| Deorder
 +
| 4x
 +
| CC0
 +
| ESRGAN
 +
| Game textures
 +
| not on discord
 +
| Skyrim Diffuse Textures
 +
| ?
 +
|
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/1RjVWNUFtVyz4ykqu6Pm9wmO03pPEBGqg/view Skyrim Wood]
 +
| Laeris
 +
| 4x
 +
|
 +
| ESRGAN
 +
| Game textures
 +
| not on discord
 +
| Wood
 +
| ?
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://mega.nz/folder/fcp2SLKC#tF3vG7zjvfpnXK7OLUaFRA 4x-SkyrimTexV2.1 and V2_Fabric]
 +
| [[User:Kim2091|Kim2091]]
 +
| 4x
 +
| CC BY-NC-SA 4.0
 +
| ESRGAN
 +
| Game textures
 +
| 2021-09-25
 +
| This model set upscales most Skyrim textures. I hope it helps 🙂 The base model (2.1) works well on stone, wood, metals, and most other textures. The Fabric model is a 50/50 interpolation with a stronger iteration of this model and my Fabric model. As you can tell by the name, it's intended for Fabric textures. If you want to upscale Alpha textures, use a model dedicated to it. There's an INFO file in the folder, it just explains the extra models
 +
| 4xESRGAN
 +
| [https://cdn.discordapp.com/attachments/891300021453070387/891392169926098974/unknown.png Sample 1] [https://cdn.discordapp.com/attachments/891393393849147423/891397870266224731/unknown.png Sample 2] [https://cdn.discordapp.com/attachments/891300021453070387/891395469387890738/unknown.png Sample 3] [https://cdn.discordapp.com/attachments/891393393849147423/891398051325960202/unknown.png Sample 4]
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/12fR-pWw6YL2ZbS6EDvrAeOVoQHWkWl5L/view Forest]
 +
| |[[User:LyonHrt|LyonHrt]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Game textures
 +
| not on discord
 +
| Wood / Leaves
 +
| none
 +
|
 +
|-
 +
 
 +
| [https://mega.nz/folder/tFhl0L5b#CK4WLHYxjX7KFXU1PLNDuQ Morrowind Mixed]
 +
| mkultra
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Game textures
 +
| not on discord
 +
| Morrowind Mod Textures
 +
| 4xESRGAN
 +
|
 +
|-
 +
 
 +
| [https://drive.google.com/file/d/1xPzqzTG5L6y5I0U3W0oQjexwGF5zfG32/view Map]
 +
| |[[User:LyonHrt|LyonHrt]]
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| Game textures
 +
| not on discord
 +
| Map / Old Paper with text
 +
| none
 +
|  
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
 
|-
+
 
|[https://drive.google.com/file/d/1wQ4QxTaVAszCnDuRPGOtbLoWcJHh0GIm/view BS_DeBandizer]||[[User:BlackScout|BlackScout]]||1||GNU GPLv3||Images with Banding||34k||1||128||changing ~900||Custom (Wallpapers)||old attempts based on 1xESRGAN
 
 
|}
 
|}
  
Banding is like dithering, but instead of adding patterns of pixels to simulate missing colors, it just clips them off.
 
  
====Color Removal / Grayscale====
+
==Video Restoration==
 +
===Video Compression===
 +
 
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
|-  
+
! Author
|[https://drive.google.com/file/d/1UgxnymTfLaVhY3aaDuBRnTZ9ehckKVKJ BS_Colorizer]||[[User:BlackScout|BlackScout]]||1||GNU GPLv3||Coloring B/W images||22k||1||128||4.5045k||Custom (800 Wallpapers)||1xESRGAN
+
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://de-next.owncube.com/index.php/s/wKjLmYsq7M5JAmx 1x_cinepak_200000]
 +
| |[[User:Twittman|Twittman]]
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0] (?)
 +
| ESRGAN
 +
| Compression
 +
| 2019-07-03
 +
| Removal of Compression such as Cinepak, msvideo1 and Roq
 +
| none
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://de-next.owncube.com/index.php/s/wKjLmYsq7M5JAmx 1x_cinepak_alt.pth]
 +
| |buildist
 +
| 1x
 +
|[https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3]
 +
| ESRGAN
 +
| Compression
 +
|  
 +
| Cinepak (only)
 +
| none
 +
|  
 +
|-
 +
 
 +
|-
 +
| [https://drive.google.com/drive/folders/1qn1LeYI93HDKHxREEK4EYsDB6LDsZ_dI?usp=sharing DeBink v4/v5/v6]
 +
| |[[User:Kim2091|Kim2091]]
 +
| 1x
 +
| CC BY-NC-SA 4.0
 +
| ESRGAN
 +
| Compression
 +
| 8.6.21
 +
| This model removes early 2000s Bink and other compression artifacts. Works well on almost any image or video compression type.
 +
| none
 +
|
 +
|-
 +
 
 +
| [https://icedrive.net/1/43GNBihZyi NMKD h264Texturize]
 +
| |[[User:nmkd|Nmkd]]
 +
| 1x
 +
| WTFPL
 +
| ESRGAN
 +
| Texturizing
 +
| 2020-10-20
 +
| Tries to reverse heavy h264 compression. Fails. Can be used to texturize images though.
 +
| 4x ESRGAN
 +
|
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/drive/folders/1ZcMD3hy1YCm-hsrT6xYGvhboxSzhrJKg 1x_Filmify4K_v2_325000_G.pth]
 +
| Muf
 +
| 1x
 +
| Public Domain
 +
| ESRGAN
 +
| artifact
 +
| 2021-07-19
 +
| This model attempts to make films upscaled to 4K with Topaz Gaia-HQ look more natural and filmic. It sharpens, adds film grain, and smooths out small artefacts from the upscaling process. I recommend adding a tiny amount of grain to the input to seed the model (you can do this in VEAI), otherwise the film grain will remain static across frames that don't move much. Pretrain model used with permission to relicense from Twittman.
 +
| 1x_UnResize_V3_110000_G.pth
 +
| https://imgsli.com/NjE5MTE https://imgsli.com/NjE5MTI https://imgsli.com/NjE5MTM https://imgsli.com/NjE5MTQ
 +
|-
 +
 
 +
|-
 +
| [https://drive.google.com/file/d/1-lfgZ_6vtS9DsWU-57ig8UJExH26XmCv/view?usp=sharing DeIndeo]
 +
| Wild West Quest#7975
 +
| 4x
 +
| WTFPL
 +
| ESRGAN
 +
| Indeo Compression Artifacts
 +
|  
 +
| Dataset: Custom
 +
| [https://mega.nz/#!uhAVEaAA!qfwIQ44Ba3rXMAb2-M3aM3zFBCwzmyQ64IO_0O-csJE 4xESRGAN]
 +
|  
 +
|-
 +
 
 
|}
 
|}
Just removes all colors and makes the image grayscale, the models here should restore some color to them, should also work for old black and white images.
 
  
===Over-Sharpening===
+
===VHS Tapes===
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
|-  
+
! Author
|[https://mega.nz/#!qRZD3SLL!RqP7cISIcoW5YakPya9CXEWSEHWqUSKdWLQSdYKGa14 DeSharpen]||loinne||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Oversharpened Images||310K||1||128||~3K||Custom (?)||Failed Attempts
+
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://icedrive.net/0/d3bwO9Byjo 1xBaldrickVHSFix_180000_G_V0.2]
 +
| NimRodZorg
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| VHS
 +
| 2021-03-03
 +
| Fixing minor VHS Chroma and Pattern Noise - NOTE: only works on deinterlaced sources
 +
| 1xESRGAN
 +
|  
 +
|-
 +
 
 +
| [https://drive.google.com/drive/folders/1NVT-5hmcrXc1d_DFjzNf-z-VfOa_xhwI?usp=sharing 2x_VHS-upscale-and-denoise_Film_477000_G]
 +
| Itewreed
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| VHS
 +
| 2021-03-28
 +
| VHS captures of Film material, but may work on VHS recorded native SD-TV material as well. Also useable for cleaned up source material
 +
| none
 +
|  
 +
|-
 +
 
 +
| [https://mega.nz/file/Z5IXBSrA#bE9VasE60zLqZ_NggOhs40Z9l2z8DapROZb5VX0F3h0 VHS-Sharpen-1x]
 +
| RTX 2080 ti hoarder
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN
 +
| VHS
 +
| 2021-03-19
 +
| Make old VHS footage crispy. This model will not work on video and images with noticeable JPEG/Video compression artifacts, noticeable interlacing or haloing, heavy tape distortion/artifacts and scenes with tons of detail. For best results, use a downscaled HD capture of the VHS tape you intend to use it on.
 +
| 1xESRGAN
 +
| https://imgsli.com/NDUxNDY/2/3
 +
|-
 +
 
 
|}
 
|}
  
The De-Sharpen model was made for rare particular cases when the image was destroyed by applying noise, i.e. game textures or any badly exported photos. If your image does not have any over-sharpening, it won’t hurt them, leaving as is. In theory, this model knows when to activate and when to skip, also can successfully remove artifacts if only some parts of the image are over-sharpened, for example in image consisting of several combined images, 1 of them with sharpen noise. It is made to remove sharpen noise, particularly made with Photoshop “sharpen” or “sharpen more” filters OR ImageMagick’s -sharpen directive with several varying parameters of Radius and Sigma, from subtle 0.3x0.5 to something extreme like 8x2, somewhere about that.
+
==Pretrained Models==
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://mega.nz/#!D940CAKR!-BAx7tSj1CgeopGkaMW31VuPsC3hvNBL35TEVAj4LIo 1xESRGAN]
 +
| victorca25
 +
| 1x
 +
| Apache License 2.0
 +
| ESRGAN
 +
| Pretrained
 +
| 2019-07-06
 +
|
 +
| RRDB_ESRGAN_x4.pth
 +
|
 +
|-
 +
 
 +
 
 +
| [https://mega.nz/#!vtgSWKQT!K7Asn2zKe4N70R2aV89KEMTKhH3aiyGAAiuQDJF09qs 2xESRGAN]
 +
| victorca25
 +
| 2x
 +
| Apache License 2.0
 +
| ESRGAN
 +
| Pretrained
 +
| 2019-07-06
 +
|
 +
| RRDB_ESRGAN_x4.pth
 +
|
 +
|-
 +
 
 +
| [https://mega.nz/#!uhAVEaAA!qfwIQ44Ba3rXMAb2-M3aM3zFBCwzmyQ64IO_0O-csJE 4xESRGAN]
 +
| xinntao
 +
| 4x
 +
| Apache License 2.0
 +
| ESRGAN
 +
| Pretrained
 +
| 2019-07-06
 +
|
 +
| RRDB_ESRGAN_x4.pth
 +
|
 +
|-
 +
 
 +
 
 +
| [https://mega.nz/#!6kwQiCCS!v2uN8R44vVrlzmSqffGaCnzgogkPhhl67myJbuG45SA 8xESRGAN]
 +
| victorca25
 +
| 8x
 +
| Apache License 2.0
 +
| ESRGAN
 +
| Pretrained
 +
| 2019-07-06
 +
|
 +
| RRDB_ESRGAN_x4.pth
 +
|
 +
|-
 +
 
 +
 
 +
| [https://mega.nz/#!btwEXAoI!nNxWI89OdQCEkcRoPEFwj6GoFN8uzZyZFaCn1wbhzKY 16xESRGAN]
 +
| victorca25
 +
| 16x
 +
| Apache License 2.0
 +
| ESRGAN
 +
| Pretrained
 +
| 2019-07-06
 +
|
 +
| RRDB_ESRGAN_x4.pth
 +
|
 +
|-
 +
 
 +
|-
 +
| [https://drive.google.com/open?id=1ldwajXL50uC7PCS63B4Wato6Dnk-svNL 1x PSNR Pretrained Model]
 +
| BlueAmulet
 +
| 1x
 +
| Apache License 2.0 (ESRGAN's license)
 +
| ESRGAN
 +
| Pretrained
 +
| 2020-04-20
 +
| The original RRDB_PSNR_x4.pth model converted to 1x, 2x, 8x and 16x scales, intended to be used as pretrained models for new models at those scales. These are compatible with victor's 4xESRGAN.pth conversions
 +
| RRDB_PSNR_x4.pth
 +
|
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/open?id=1ldwajXL50uC7PCS63B4Wato6Dnk-svNL 2x PSNR Pretrained Model]
 +
| BlueAmulet
 +
| 2x
 +
| Apache License 2.0 (ESRGAN's license)
 +
| ESRGAN
 +
| Pretrained
 +
| 2020-04-20
 +
| The original RRDB_PSNR_x4.pth model converted to 1x, 2x, 8x and 16x scales, intended to be used as pretrained models for new models at those scales. These are compatible with victor's 4xESRGAN.pth conversions
 +
| RRDB_PSNR_x4.pth
 +
|
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/open?id=1ldwajXL50uC7PCS63B4Wato6Dnk-svNL 4x PSNR Pretrained Model]
 +
| BlueAmulet
 +
| 4x
 +
| Apache License 2.0 (ESRGAN's license)
 +
| ESRGAN
 +
| Pretrained
 +
| 2020-04-20
 +
| The original RRDB_PSNR_x4.pth model converted to 1x, 2x, 8x and 16x scales, intended to be used as pretrained models for new models at those scales. These are compatible with victor's 4xESRGAN.pth conversions
 +
| RRDB_PSNR_x4.pth
 +
|
 +
|-
 +
 
 +
 
 +
| [https://drive.google.com/open?id=1ldwajXL50uC7PCS63B4Wato6Dnk-svNL 8x PSNR Pretrained Model]
 +
| BlueAmulet
 +
| 8x
 +
| Apache License 2.0 (ESRGAN's license)
 +
| ESRGAN
 +
| Pretrained
 +
| 2020-04-20
 +
| The original RRDB_PSNR_x4.pth model converted to 1x, 2x, 8x and 16x scales, intended to be used as pretrained models for new models at those scales. These are compatible with victor's 4xESRGAN.pth conversions
 +
| RRDB_PSNR_x4.pth
 +
|
 +
|-
 +
 
  
===Aliasing===
+
| [https://drive.google.com/open?id=1ldwajXL50uC7PCS63B4Wato6Dnk-svNL 16x PSNR Pretrained Model]
 +
| BlueAmulet
 +
| 16x
 +
| Apache License 2.0 (ESRGAN's license)
 +
| ESRGAN
 +
| Pretrained
 +
| 2020-04-20
 +
| The original RRDB_PSNR_x4.pth model converted to 1x, 2x, 8x and 16x scales, intended to be used as pretrained models for new models at those scales. These are compatible with victor's 4xESRGAN.pth conversions
 +
| RRDB_PSNR_x4.pth
 +
|
 +
|-
 +
|}
 +
 
 +
==Pretrained Discriminators==
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
 
 +
|-
 +
| [https://u.pcloud.link/publink/show?code=kZkLGpXZLPOptIrA1fjXvFdIS0NpdzuWSfkk 1x Pretrained Discriminator Pack]
 +
| Joey
 +
| 1x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| VGG
 +
| Pretrained discriminators
 +
| 2020-10-26
 +
| Most of these are my spongebob dataset so they will be more useful for cartoons but I did include my original faithful model discriminator.
 +
| none
 +
|
 
|-
 
|-
|[https://drive.google.com/open?id=11nMqVF9sUN2jRRagYc3wdWNX5acEy0MJ SS Anti Alias 9x]||[[User:BlueAmulet|BlueAmulet]]||1||[https://creativecommons.org/licenses/by-nc/4.0/ CC BY-NC 4.0]||Anti aliasing||125K~||12||32||4096||Custom (9x Supersampling AA)||none (no interpolation)
 
|-
 
|[https://de-next.owncube.com/index.php/s/mmYCcK4H3rQQR5Y Anti Aliasing]||[[User:Twittman|Twittman]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Images with pixelated edges||200K||1||128||0.656K||Custom (?)||none (no interpolation)
 
|}
 
  
AntiAliasing is for smoothing jagged edges in images and textures.
 
  
==Image Generation==
+
| [https://u.pcloud.link/publink/show?code=kZkLGpXZLPOptIrA1fjXvFdIS0NpdzuWSfkk 2x Pretrained Discriminator Pack]
 +
| Joey
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| VGG
 +
| Pretrained discriminators
 +
| 2020-10-26
 +
| Most of these are my spongebob dataset so they will be more useful for cartoons but I did include my original faithful model discriminator.
 +
| none
 +
|
 +
|-
  
===Texture Maps===
 
  
{| class="wikitable sortable"
+
| [https://u.pcloud.link/publink/show?code=kZkLGpXZLPOptIrA1fjXvFdIS0NpdzuWSfkk 4x Pretrained Discriminator Pack]
 +
| Joey
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| VGG
 +
| Pretrained discriminators
 +
| 2020-10-26
 +
| Most of these are my spongebob dataset so they will be more useful for cartoons but I did include my original faithful model discriminator.
 +
| none
 +
|
 +
|-
 +
| [https://u.pcloud.link/publink/show?code=kZkLGpXZLPOptIrA1fjXvFdIS0NpdzuWSfkk 8x Pretrained Discriminator Pack]
 +
| Joey
 +
| 8x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| VGG
 +
| Pretrained discriminators
 +
| 2020-10-26
 +
| Most of these are my spongebob dataset so they will be more useful for cartoons but I did include my original faithful model discriminator.
 +
| none
 +
|
 +
|-
 +
 
 +
| [https://u.pcloud.link/publink/show?code=kZPxrYXZOBnSmRzYywHg9heV55yt0JvKC3gk 4x_RRDB-G_ResNet-D (Both G and D)]
 +
| Joey
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| ESRGAN (G) / ResNet (D)
 +
| Pretrained
 +
| 2021-01-17
 +
| Clean bicubic downscales / Pretrained models (G/D)
 +
| RRDB_ESRGAN_x4_old_arch.pth
 +
|
 
|-
 
|-
{{ModelDBColumns|Name|Author|Scale|License|Purpose|Iterations|Batch Size|HR Size|Dataset Size|Dataset|Pretrained Model}}
 
|-
 
|[https://drive.google.com/file/d/1uksv1uyyZjQcU4567OrfU0w2NECcG8dY/view normal generator]||[[User:LyonHrt|LyonHrt]]||1||[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]||Diffuse to Normal||215K||1||128||4.536K||Custom (?)||none (no interpolation)
 
 
|}
 
|}
  
The model was trained on pairs of diffuse textures and normal maps.
+
=SOFVSR Models=
 +
These models are for SOFVSR, they will not work in Cupscale or the main ESRGAN forks. You need this to use it: https://github.com/JoeyBallentine/Video-Inference
  
==Pretrained models for different scales==
 
 
{| class="wikitable sortable"
 
{| class="wikitable sortable"
 
|-
 
|-
!Name!!Author!!Scale!!License!!Dataset Size!!Dataset!!Pretrained Model
+
! Model Name
|-
+
! Author
|[https://mega.nz/#!D940CAKR!-BAx7tSj1CgeopGkaMW31VuPsC3hvNBL35TEVAj4LIo 1xESRGAN]||[https://github.com/victorca25 victorca25]||1||Apache License 2.0||65k||Combination of DIV2K, Flickr2K and GOPRO||4xPSNR
+
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 
|-
 
|-
|[https://mega.nz/#!vtgSWKQT!K7Asn2zKe4N70R2aV89KEMTKhH3aiyGAAiuQDJF09qs 2xESRGAN]||[https://github.com/victorca25 victorca25]||2||Apache License 2.0||65k||Combination of DIV2K, Flickr2K and GOPRO||4xPSNR
+
 
 +
| [https://u.pcloud.link/publink/show?code=XZMmozXZjW4hHqJu7ikbQpyeqUItTh7QJO6k 3x_Video_TSSM]
 +
| Joey
 +
| 3x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| SOFVSR
 +
| Animation
 +
| 2020-11-17
 +
| none
 +
|  
 +
|
 
|-
 
|-
|[https://mega.nz/#!uhAVEaAA!qfwIQ44Ba3rXMAb2-M3aM3zFBCwzmyQ64IO_0O-csJE 4xESRGAN]||[https://github.com/victorca25 victorca25]||4||Apache License 2.0||65k||Combination of DIV2K, Flickr2K and GOPRO||4xPSNR
+
 
 +
 
 +
| [https://u.pcloud.link/publink/show?code=XZ2AERXZ9YpzzV4rRvySFiq3MsrTEYdEjtkV 3x_Video_TSSM_RRDB]
 +
| Joey
 +
| 3x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| SOFVSR RRDB / VESRGAN
 +
| Animation
 +
| 2020-11-25
 +
| none
 +
|  
 +
|
 
|-
 
|-
|[https://mega.nz/#!6kwQiCCS!v2uN8R44vVrlzmSqffGaCnzgogkPhhl67myJbuG45SA 8xESRGAN]||[https://github.com/victorca25 victorca25]||8||Apache License 2.0||65k||Combination of DIV2K, Flickr2K and GOPRO||4xPSNR
+
 
 +
| [https://u.pcloud.link/publink/show?code=kZ5QKLXZ5mPYmsGpGU75DLNII9AOlYQNqMjk 2x_SBS11-RRDB]
 +
| Joey
 +
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| SOFVSR RRDB / SOFVESRGAN
 +
| Animation
 +
| 2020-12-03
 +
| none
 +
|  
 +
|
 
|-
 
|-
|[https://mega.nz/#!btwEXAoI!nNxWI89OdQCEkcRoPEFwj6GoFN8uzZyZFaCn1wbhzKY 16xESRGAN]||[https://github.com/victorca25 victorca25]||16||Apache License 2.0||65k||Combination of DIV2K, Flickr2K and GOPRO||4xPSNR
+
 
 +
| [https://u.pcloud.link/publink/show?code=kZojwLXZfeqA3Eoyv6SKXXt01AlSeuHH0WKX 4x_REDSVAL-7f-RRDB-Lite (both G and D)]
 +
| Joey
 +
| 4x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
| SOFVSR RRDB / SOFVESRGAN Lite [nf=32, nb=12]
 +
| IRL videos
 +
| 2020-12-03
 +
| none
 +
|  
 +
|
 
|-
 
|-
|[https://drive.google.com/drive/folders/1ldwajXL50uC7PCS63B4Wato6Dnk-svNL 1xPSNR]||[[User:BlueAmulet|BlueAmulet]]||1||Apache License 2.0||65k||Combination of DIV2K, Flickr2K and GOPRO||none
+
 
 +
| [https://mega.nz/file/bpA2QTxI#j_ALxzI5rNjt-T5XcOu8P6ogtAjmFHJeggJbXLGy_Nc SOFVSR_REDS_F3_V1]
 +
|Sunseille
 +
| 4x
 +
| WTFPL
 +
| RRDB
 +
| IRL videos
 +
| 2021-02-26
 +
| upscale IRL videos. Use not recommended by creator
 +
| none
 +
| https://cdn.discordapp.com/attachments/547949806761410560/813134983236419664/100k_iter.mp4
 
|-
 
|-
|[https://drive.google.com/drive/folders/1ldwajXL50uC7PCS63B4Wato6Dnk-svNL 2xPSNR]||[[User:BlueAmulet|BlueAmulet]]||2||Apache License 2.0||65k||Combination of DIV2K, Flickr2K and GOPRO||none
+
 
 +
| [https://mega.nz/folder/qslgTZYQ#wE9l53sTH78B6wjPX5GRwQ 2x_VimeoScale_Unet]
 +
| Sazoji
 +
| 2x
 +
| CC BY-SA 4.0
 +
| SOFVSR-RRDB (light arch, 3 frames, nf=32, nb=12)
 +
| Upscaling video content
 +
| 2021-09-09
 +
| This model is meant to surpass VEAI 2x while being efficient to run quickly with fp16. The real-esrgan/BSRGAN augmentation and Unet should help with videos where the resolution is not ideal and can reconstruct details without effecting blurs in most cases. This model SHOULD run faster than real-esrgan while matching the resolving and enabling some multiframe feature extraction. No major denoising/compression/blurring effects (or artifacts) should be found.
 +
| Self-Trained Base for the Unet finalisation with vgg_fea discrim
 +
| [https://imgsli.com/NzAyMTc Sample 1] [https://imgsli.com/NzAyMTg Sample 2] [https://imgsli.com/NzAyMTk Sample 3]
 
|-
 
|-
|[https://drive.google.com/drive/folders/1ldwajXL50uC7PCS63B4Wato6Dnk-svNL 4xPSNR]||[[User:BlueAmulet|BlueAmulet]]||4||Apache License 2.0||65k||Combination of DIV2K, Flickr2K and GOPRO||none
+
 
 +
| [https://mega.nz/folder/b8MTgYhA#CkKajnw0fPu5BVynl-caOQ 4x_VimeoScale]
 +
| Sazoji
 +
| 4x
 +
| CC BY-SA 4.0
 +
| SOFVSR-RRDB (5 frames)
 +
| Upscaling IRL video content
 +
| 2021-10-08
 +
| This model is one of the longest I have trained and tuned, includes some noise training but this is not intended for deblocking/decompression. Combined with https://github.com/JoeyBallentine/Video-Inference 's fp16 mode, this should handle most SD and 720p content at or faster than ESRGAN, with a significant bump in quality.
 +
| Self-Trained Base for the Unet finalisation with vgg_fea discrim
 +
| [https://imgsli.com/NzUwODU Sample 1] [https://imgsli.com/NzUwODQ Sample 2] [https://imgsli.com/NzUwODc Sample 3] [https://imgsli.com/NzUwODY Sample 4]
 
|-
 
|-
|[https://drive.google.com/drive/folders/1ldwajXL50uC7PCS63B4Wato6Dnk-svNL 8xPSNR]||[[User:BlueAmulet|BlueAmulet]]||8||Apache License 2.0||65k||Combination of DIV2K, Flickr2K and GOPRO||none
+
|}
 +
 
 +
==Pretrained SOFVSR Models==
 +
{| class="wikitable sortable"
 
|-
 
|-
|[https://drive.google.com/drive/folders/1ldwajXL50uC7PCS63B4Wato6Dnk-svNL 16xPSNR]||[[User:BlueAmulet|BlueAmulet]]||16||Apache License 2.0||65k||Combination of DIV2K, Flickr2K and GOPRO||none
+
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
|-
 +
 
 +
| [https://mega.nz/file/28JmyLrK#xhRP-EZKR7Vg7UjIRZQqotiFLix21JaGGLSvZq7cjt4 video_G]
 +
| victorca25
 +
| 4x
 +
| Unknown
 +
| SOFVSR net
 +
|  
 +
|  
 +
| Trained on REDS' size dataset
 +
| none
 +
|  
 +
|-
 +
 
 +
| [https://mega.nz/file/TwwEWD7Q#wCfUvVudI17weYc1JLeM3nTeK2xiMlVdc_JN1Nov3ac VESRGAN_G]
 +
| victorca25
 +
| 4x
 +
| Unknown
 +
| RRDB
 +
|  
 +
|
 +
| Trained on REDS' size dataset
 +
| none
 +
|
 
|-
 
|-
 
|}
 
|}
https://drive.google.com/drive/folders/1ldwajXL50uC7PCS63B4Wato6Dnk-svNL
 
  
These models were transformed from the original RRDB_ESRGAN_x4.pth model into the other scales, in order to be used as pretrained models for new models in those scales.
+
=CAIN Models=
 +
{| class="wikitable sortable"
 +
|-
 +
! Model Name
 +
! Author
 +
! Scale
 +
! License
 +
! Architecture
 +
! Purpose (short)
 +
! Date Posted
 +
! Purpose (Full)
 +
! Pretrained_Model_G
 +
! sample
 +
|-
 +
 
 +
CAIN is a video frame rate interpolation AI. These models are intended for use with CAIN only. These CANNOT be used with Cupscale or ESRGAN, you need this: https://gitlab.com/hubert.sontowski2007/cainapp
  
More information can be found [https://github.com/victorca25/BasicSR/wiki/Interpolation here].
+
| [http://91.232.191.56/models/190581.pth 190562_vimeo_enchanced.pth]
 +
| hubert
 +
| 2x
 +
| MIT
 +
|[https://gitlab.com/hubert.sontowski2007/cainapp CAIN]
 +
| RL videos - interpolation
 +
| 2021-07-13
 +
|
 +
|
 +
|
 +
|-
  
=Licenses Links=
 
  
*[https://github.com/alsa64/AI-wiki/blob/master/LICENSE GNU GPLv3]:
+
| [https://cdn.discordapp.com/attachments/873173887427416114/874695897257246770/726770_JIT.pth cainliteanime.pth]
**If you modify, interpolate or use the model as a pretrained model for your own model and share results of your resulting model, it will have to be under the same license.
+
| hubert
**You have to state that you used the model and its author for your results.
+
| 2x
**You have to state any changes you made to the model.
+
| MIT
**There are other points, but those are the main ones.
+
|[https://gitlab.com/hubert.sontowski2007/cainapp CAIN]
 +
| Anime - interpolation
 +
| 2021-08-06
 +
|
 +
|
 +
| [https://cdn.discordapp.com/attachments/724353640521007145/873861876352704533/1.webm Sample]
 +
|-
  
-----
+
| [https://e.pcloud.link/publink/show?code=kZhh05ZMvnTmaKOepQPfMoQlv9sMRD3nQw7 rvpV1]
Testing captcha. Again.
+
| sudo rm -rf / --no-preserve-root#8353
Testing again with basic account.
+
| 2x
 +
|[https://creativecommons.org/licenses/by-nc-sa/4.0/ CC BY-NC-SA 4.0]
 +
|[https://gitlab.com/hubert.sontowski2007/cainapp CAIN]
 +
| Video Frame Interpolation for anime openings
 +
| 2021-09-14
 +
|
 +
| My ~~first~~ (ok technically second) attempt to create a video frame interpolation model and I like how it turned out. To use it, you can either use https://gitlab.com/hubert.sontowski2007/cainapp, https://github.com/styler00dollar/Colab-CAIN or the bot in [Game Upscale] (model called rvpv1 there, just use --model rvpv1). Some demo videos in pcloud, but you need to download them. The web player seems to playback in low fps. The architecture is mainly the same to the original CAIN, but i modified the padding to be zero padding instead. ``.pt`` means JIT model, `.pth`, means normal pytorch model. Architecture file is in pcloud as well. And no, no cupscale or flowframes. Dataset: Modified Animeinterp dataset
 +
| https://files.catbox.moe/xiq9vi.mp4
 +
|-
 +
 
 +
| [https://files.catbox.moe/nxh1cv.pth cvpv6.pth]
 +
| hubert
 +
| 2x
 +
| MIT
 +
|[https://gitlab.com/hubert.sontowski2007/cainapp CAIN]
 +
| Anime - interpolation
 +
| 2021-09-21
 +
|
 +
|
 +
|
 +
|-
 +
|}

Latest revision as of 03:49, 20 October 2021

If a model has no license, that means all rights reserved. You will need a private license or explicit permission from the creator to use it commercially or with modifications. However you may use all model here on non-commercial projects, that may not in any way cost money. If you gain permission to use a model in another way including commercially, you should still credit the author and link to the original model source.

ESRGAN ("old Architecture") Models

Models that use the "old" ESRGAN architecture. They can be used either with the official ESRGAN repository (old arch tag) and BasicSR (old arch or preferably victorc's traiNNer version). You can also use tools that wrap around one of them, like IEU from Honh or Cupscale by Nmkd.

Image scaling and Video upscaling

Universal Models

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
CountryRoads EzoGaming 4x WTFPL ESRGAN Universal Upscaler 2021-08-26 Streets with dense foliage in the background. Outdoor scenes. 4xPSNR https://cdn.discordapp.com/attachments/547949806761410560/880291337373618236/unknown.png, https://media.discordapp.net/attachments/547949806761410560/880290211026853918/unknown.png, https://media.discordapp.net/attachments/547949806761410560/880299665428447232/unknown.png, https://cdn.discordapp.com/attachments/880291340301254657/880303552315146340/unknown.png
Remacri Foolhardy 4x CC BY-NC-SA 4.0 General Upscaler 2021-04-09 A creation of BSRGAN with more details and less smoothing, made by interpolating IRL models such as Siax, Superscale, Superscale Artisoft, Pixel Perfect, etc. This was, things like skin and other details don't become mushy and blurry. none - interpolated
UniScale-Balanced/Strong (Includes Interp) Kim2091 4x CC BY-NC-SA 4.0 ESRGAN Universal Upscaler 2021-08-23 UniScale strikes a nice balance between sharpness and realism. This model can upscale almost anything well. It was originally intended to upscale game textures, but was expanded into a universal upscaler. Interp is these two models interpolated. 4xESRGAN https://slow.pics/c/i75q0yN1
UniScaleNR-Balanced/Strong Kim2091 4x CC BY-NC-SA 4.0 ESRGAN Universal Upscaler 2021-08-23 Version of UniScale trained with camera noise injection (NR = Noise Removal). This model removes noise from images while upscaling. 4xESRGAN https://slow.pics/c/UkCwdK13
UniScale_Restore Kim2091 4x CC BY-NC-SA 4.0 ESRGAN Universal Upscaler 2021-08-27 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. 4xESRGAN https://cdn.discordapp.com/attachments/880826637543964712/880934732748169226/unknown.png, https://cdn.discordapp.com/attachments/880826637543964712/880932754102026290/unknown.png
UniScaleV2_Soft/Moderate/Sharp Kim2091 4x CC BY-NC-SA 4.0 ESRGAN Universal Upscaler 2021-09-06 This model set is much sharper overall than UniScale V1. These models work great on game textures when interpolated 50/50 with UniScale_Restore, and work amazingly on uncompressed images. DO NOT USE FOR COMPRESSED IMAGES, use the original UniScale for that. 4xESRGAN https://cdn.discordapp.com/attachments/884239326471393331/884296266857713704/unknown.png https://cdn.discordapp.com/attachments/884239326471393331/884294468709257216/unknown.png https://cdn.discordapp.com/attachments/884239326471393331/884298572894441512/unknown.png https://cdn.discordapp.com/attachments/884239326471393331/884302370136289323/unknown.png
Misc Alsa 4x CC BY-NC-SA 4.0 ESRGAN General Upscaler The Misc model is trained on various pictures shot by myself (Alsa), including bricks, stone, dirt, grass, plants, wood, bark, metal and a few others. Manga109Attempt
FuzzyBox BlueAmulet 4x CC BY-NC 4.0 ESRGAN General upscaler 2020-07-21 Photographs, Artwork, Textures, Anything really - Tried out a new pixel loss idea based on ensuring the HR downscaled matches the LR. Colors are pretty good as well as edges, but generated details seem slightly fuzzy hence the name. RRDB_ESRGAN_x4
Lollypop LyonHrt 4x CC BY-NC-SA 4.0 ESRGAN General upscaler 2020-09-11 A universal model, that is aimed at prerendered images, but handles realistic faces, manga, pixel art and dedithering as well. Trained using the patchgan discriminator, with cx loss, cutmixup and frequency separation, it produces good results with a slight grain due to patchgan, with some sharpening using cutmixup. 4X_esrgan.pth
UniversalUpscalerV2 Mutin_Choler 4x WTFPL ESRGAN General Upscaler 2021-04-01 General Upscaler 1xESRGAN https://imgsli.com/NDc3ODA/2/1
NMKD Siax ("CX") Nmkd 4x WTFPL ESRGAN General upscaler 2020-11-06 Universal upscaler for clean and slightly compressed images (JPEG quality 75 or better) 4xPSNR

Realistic Photos

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
4x-Valar musl 4x CC0 ESRGAN+ Realistic Photos 2021-09-16 Meant as an experiment to test latest techniques implemented on traiNNer, including: AdaTarget, KernelGAN, UNet discriminator, nESRGAN+ arch, noise patches, camera noise, isotropic/anisotropic/sinc blur, frequency separation, contextual loss, mixup, clipL1 pixel loss, AdamP optimizer, etc. The config file is provided on the download link above. I encourage everybody to mirror the model, distribute and modify it in anywway you want. 4x_RRDB_ESRGAN Sample 1
4x_Box buildist 4x GNU GPLv3 ESRGAN Realistic Photos 2019-06-20 RRDB_ESRGAN_x4 replacement for stuff that's supposed to look realistic. none
Nickelback BlackScout 4x GNU GPLv3 ESRGAN Realistic Photos 2020-02-12 this model aims to improve further on what has been achieved by the regular 4xESRGAN and also 4xBox. It can upscale most pictures/photos (granted they are clean enough) without destroying as much detail as the aforementioned models. It generates less moiré like patterns and keeps details without oversharpening or blurring the image too much. 4xESRGAN
NickelbackFS BlackScout 4x GNU GPLv3 ESRGAN-FS Realistic Photos 2020-07-10 This model aims to improve further on what has been achieved by the old Nickelback which was an improvement attempt over 4xESRGAN and also 4xBox. It can upscale most pictures/photos (granted they are clean enough) without destroying as much detail as Box and basic ESRGAN. 4xESRGAN
4x NMKD Superscale Nmkd 4x WTFPL ESRGAN Clean Real-World Images 2020-07-22 Upscaling of realistic images/photos with noise and compression artifacts 4xESRGAN


Art/Pixel Art

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
4x_xbrz_90k LyonHrt 4x CC BY-NC 4.0 ESRGAN Pixel Art 2019-06-05 Xbrz style pixel art upscaler 4xPSNR
Rebout LyonHrt 4x CC BY-NC-SA 4.0 ESRGAN Pixel Art/Sprites 2019-08-04 For upscaling character sprites Detoon
Rebout Blend LyonHrt 4x CC BY-NC-SA 4.0 ESRGAN Pixel Art/Sprites Dataset: Custom prepared sprites from kof 94 rebout, which with gradients blending Detoon
Arzenal (v1.1) ComputerK 8x CC BY-NC-SA 4.0 ESRGAN Pixel Art Smooth general pixel art, Minecraft textures Interpolated from nmkd's pixel art upscaling models with different interpolation settings and de-dithered versions
4x_scalenx_90k LyonHrt 4x CC BY-NC 4.0 ESRGAN Pixel Art 2019-06-15 Scalenx style pixel art upscaler 4xPSNR
4x_xbrz+dd_260k LyonHrt 4x CC BY-NC 4.0 ESRGAN Pixel Art 2019-06-17 xbrz plus dedithering style pixel-art upscaling model to wiki under specialised 4x_xbrz_90k
Lady0101_208000.pth DinnJerr 4x ESRGAN Pixel Art/Paintings 2019-07-25 Upscale pixel art/paintings to digital painting style WaifuGAN_v3_30000.pth
Fatality (4x_Fatality_01.pth) twittman 4x ESRGAN Pixel Art/Sprites 2019-07-29 Upscales medium resolution Sprites, dithered or undithered, can also upscale manga/anime and gameboy camera images. 4x_Faces_04_N_180000_G.pth
Fatality MK2 (4x_Fatality_MKII_90000_G.pth) twittman 4x ESRGAN Pixel Art/Sprites Dataset: Anime, Manga and some real life A previously attempted MK2
Fatal Pixels (4x_FatalPixels_340000_G.pth) twittman 4x ESRGAN Pixel Art/Sprites Dataset: Anime, Manga Fatality_MKII_90k
Faithful 2x Joey 2x CC-BY-NC 4.0 ESRGAN Pixel Art 2019-09-08 2xESRGAN
deviantPixelHD raulsangonzalo 4x You're free to use this model for all non-commercial projects and interpolation, please give credit if featured in any projects ESRGAN Pixel Art 2019-09-09 Similar to Manga109, can be used as a general digital upscaler as well as with pixel art RRDB_PSNR_x4 https://www.youtube.com/channel/UCwBfuiHdSPQ-zslOmiW8OHg
4x_BS_Deviance systemd-resolved/BlackScout 4x GNU GPLv3 ESRGAN Art 2020-02-25 This model upscales Digital Drawings. It was trained on random drawings found on DeviantArt. Mostly Landscape and Scenery and Illustrations of Characters. It does fairly well and works on many different styles. 4xESRGAN
4xSmoothRealism Joey 4x CC BY-NC 4.0 ESRGAN Pixel Art 2020-03-04 Pixel art, rocky/grainy textures? Quantization smoothing, adding detail. 4x_RRDB_PSNR_old_arch.pth
8x_HugePeeps_v1 DinJerr 8x CC BY-NC 4.0 ESRGAN Art/People 2020-06-16 Painted humans TGHQFace8x
BigFace_v3_Clear DinJerr 4x CC BY-NC 4.0 ESRGAN Art/People 2020-07-22 4x_BigFace
4x_BS_DevianceV2 systemd-resolved/BlackScout 4x GNU GPLv3 ESRGAN-FS Art 2020-07-25 upscales Digital Drawings. It was trained on random drawings found on DeviantArt. Mostly Landscape and Scenery and Illustrations of Characters. It does fairly well and works on many different styles. 4xESRGAN
4x_BS_DevianceMIP systemd-resolved/BlackScout 4x GNU GPLv3 ESRGAN-FS Art 2020-07-25 upscales Digital Drawings. It was trained on random drawings found on DeviantArt. Mostly Landscape and Scenery and Illustrations of Characters. It does fairly well and works on many different styles. 4xESRGAN
4x_Struzan Laserschwert 4x CC BY-NC-SA 4.0 ESRGAN Art 2020-10-12 Upscaling airbrush/pencil-based artwork 4xPSNR https://drive.google.com/drive/folders/1fyeIWInDrM6r-xxrCW4U09oafWw08u9S?usp=sharing
4x_PixelPerfectV4_137000_G Mutin Choler 4x WTFPL ESRGAN Pixel Art/Sprites 2020-11-16 Sprite Upscaler 4xESRGAN https://imgsli.com/MzgxMTc/1/2
BigFArt DinJerr 4x CC BY-NC 4.0 ESRGAN Pixel art 2020-15-31 Larger-scaled pixels to digital painting Face Focus
MS Unpainter FoolhardyVEVO 8x CC BY-NC-SA 4.0 ESRGAN Pixel Art 2021-03-24 Low-resolution MS Paint drawings, general pixel art, and general dithered pixel art, all kinds of pixel art A mix of: 8x_glasshopper_ArzenalV1.1, 8x_glasshopper_MS-Unpainter, 8x_NMKD-Sphax + Sphax de-dither, and 8x_NMKD-YanderePixelArt4 + Yandere De-Dither, all interpolated with adjustments using the interpolate function in Cupscale
MS Unpainter De-Dither FoolhardyVEVO 8x CC BY-NC-SA 4.0 ESRGAN Pixel Art 2021-03-24 Low-resolution MS Paint drawings, general pixel art, and general dithered pixel art, all kinds of pixel art A mix of: 8x_glasshopper_ArzenalV1.1, 8x_glasshopper_MS-Unpainter, 8x_NMKD-Sphax + Sphax de-dither, and 8x_NMKD-YanderePixelArt4 + Yandere De-Dither, all interpolated with adjustments using the interpolate function in Cupscale
UltraFArt_v3 / FArtDIV3 Suite DinJerr 4x CC BY-NC-SA 4.0 ESRGAN Art 2021-05-14 Painting style with larger shaped features (?). 4x_UltraFArt https://1drv.ms/u/s!Aip-EMByJHY27UIFr1mk87zFytap?e=ZZliII
NXbrz Archerpolation 4x CC BY-NC-SA 4.0 ESRGAN Pixel Art 2021-06-09 Basic pixel art upscaling, for people who want a more simpler style and lightweight pixel art upscaling model. https://drive.google.com/drive/folders/1mYTMpwDlKQulBmjgKpcxL3-T6xAGXVxl?usp=sharing

Drawn Material

Anime

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample


Sol Levante NTSC2HD Phoenix 4x UNLICENSE ESRGAN Anime/Pretrained 2020-04-08 NTSC DVD-spec encode x4 scale super-resolution for Anime Drawing style content. The dataset has a LOT of data throughout almost every frame, so it had a lot of stuff to learn. The resulting DVD-spec encode also had some blocking at times so it also learned to fight off blocking. RRDB_PSNR_x4
2x_Byousoku_5_Centimeter.pth Mystery_Bullet#0642 (Shady Adel) 2x GNU GPLv3 ESRGAN Anime/Pretrained 2020-04-08 Anime landscape upscale. Trained on Frames from BluRay of Byousoku 5 Centimeter 2xESRGAN
4x_OLDIES_290000_G_FINAL solidd93110 4x WTFPL ESRGAN Anime 2020-08-16 i made this model to upscale old anime and denoise. RRDB_PSNR_x4.pth
fidelbd_pokemodel Neo-Raws#4055 2x WTFPL ESRGAN Anime 2020-08-29 Made this model to upscale old anime that looks blurry. 2xESRGAN https://imgsli.com/MjExMjQ/
4x_OLDIES_ALTERNATIVE_FINAL.pth solidd93110 4x CC BY-NC-SA 4.0 ESRGAN Anime 2020-09-01 This model was made for my project captain tsubasa anime so i don't know if it works good for anything else. just try it ;) RRDB_PSNR_x4.pth https://imgsli.com/MjEzMDU
2x_SHARP_ANIME_V1 solidd93110 2x CC BY-NC-SA 4.0 ESRGAN Anime 2020-09-12 this model has been trained to work on lines and details - works well on animes which have fairly fine lines at the base but also the video must be progressive or deinterlaced 2xPSNR.pth https://imgsli.com/MjIwMDY
MeguUp /katoumegumi_#3231 GNU GPLv3. ESRGAN Anime 2020-09-16 Upscaling of lossless (uncompressed) anime art. LyonHrt (bloc97 dataset, MIT license). Fatal Pixels, Fatality Anime: Twittman (CC BY-NC-SA 4.0, acquired special permission to relicense. https://s.katou.pw/Discord_dPUiI1x3Pf.png). Deviance: |BlackScout (GNU GPLv3)
NMKD UltraYandere Nmkd 4x WTFPL ESRGAN Art/Anime 2020-10-08 Highly flexible 2D Art upscaling 4xESRGAN
NMKD UltraYandere Lite Nmkd 4x WTFPL ESRGAN Lite [nf=32 nb=12] Anime 2020-10-15 Fast Anime/Art upscaling 4x_DIV2K-Lite
2x_pokemodel_lite_100000_G Neo-Raws#4055 2x WTFPL ESRGAN Anime 2020-11-01 Upscale old anime like pokemon none https://imgsli.com/Mjc3Nzk https://imgsli.com/Mjc3Nzg https://imgsli.com/Mjc3ODA https://imgsli.com/Mjc3ODE https://imgsli.com/Mjc3ODI
2x_SHARP_ANIME_V2 solidd93110 2x CC BY-NC-SA 4.0 ESRGAN Anime 2020-12-09 2x_PSNR.pth https://imgsli.com/MzI0MDk
2x_BIGOLDIES_415000_G.pth solidd93110 2x CC BY-NC-SA 4.0 ESRGAN Anime 2020-12-09 upscaling old anime. help to denoise and find lines and dehalo 2x_PSNR.pth https://imgsli.com/MzI0MDc
NMKD YandereNeo Nmkd 2x WTFPL ESRGAN (Lite) Anime 2021-01-26 https://i.imgur.com/oxs71v5.png


NMKD YandereNeo Nmkd 4x WTFPL ESRGAN (Lite) Anime 2021-01-26 4x_DIV2K-Lite_1M https://i.imgur.com/oxs71v5.png
2x_Waifaux-NL3-SuperLite Joey 2x CC BY-NC-SA 4.0 ESRGAN 2021-02-23 Trained this model to see how it would work trying to essentially get the same results as Waifu2x but with ESRGAN none
2x_Waifaux-NL3-SRResNet Joey 2x CC BY-NC-SA 4.0 EDSR (SRResNet) 2021-02-25 Emulating Waifu2x at Noise Level 3 NOTE: You can't use this with regular esrgan forks or the bot, it has to be run through basicsr none
4x_Training4Melozard_Anime Joey 4x Whatever @B.Melozard2 wants ESRGAN Anime 2021-03-17 RRDB_ESRGAN_x4_old_arch
2x_LD-Anime_Skr_v1.0 Skr 2x CC BY-NC-SA 4.0 ESRGAN Denoise/Dehalo 2021-04-17 Denoise, dehalo, derainbow old anime 2xESRGAN https://imgsli.com/NTA3MDU/
2x_KemonoScale_v2 EzoGaming 2x CC BY-NC-SA 4.0 ESRGAN Anime 2021-06-05 Upscaling frames from Irodori anime (namely kemono friends) from 540p (the source render resolution) to 1080p, low resolution flat shaded art, de-JPEG of the aforementioned x2_CGIMaster_v1 https://cdn.discordapp.com/attachments/705815801290293329/850614850735439892/unknown.png
4x_muy4_035_1.pth katoumegumi_ 4x WTFPL ESRGAN Anime 2021-07-18 Upscaling of anime art (Specifically visual novel CG art) https://cdn.knightlab.com/libs/juxtapose/latest/embed/index.html?uid=278999ec-e802-11eb-abb7-b9a7ff2ee17c (Hakurei Reimu from Touhou Project illustrated by "okawa friend") https://cdn.knightlab.com/libs/juxtapose/latest/embed/index.html?uid=f3d4781a-e801-11eb-abb7-b9a7ff2ee17c (Kitaooji Karen from Making * Lovers developed by SMEE.)(edited)
Falcon Fanart LyonHrt 4x CC BY-NC-SA 4.0 ESRGAN Anime not on discord 4xPSNR

Manga

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
FSMangaV2 Jacob_ 4x CC BY-NC-SA 4.0 ESRGAN Manga 2020-12-14 Manga-style images with or without dithering - cartoons, maybe pixel art, etc RRDB_PSNR_x4 https://i.imgur.com/oVBVthF.png
MangaScaleV3 Bunzero++ 2x CC BY-NC-SA 4.0 ESRGAN+ Manga 2021-05-24 To upscale manga including halftones, instead of trying to smooth them out. unreleased model https://imgsli.com/NTUyMjg

Cartoons

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
8x_BoyMeBob-Redux Joey 8x CC BY-NC-SA 4.0 ESRGAN+ (Joey's fork, eFonte fork, or iNNfer required to use) Animation 2021-08-19 Upscaling cartoons 8xBoyMeBob (unreleased) which used 8xESRGAN Examples
SpongeBob Joey 4x CC-BY-NC 4.0 ESRGAN Animation 2019-09-12 4xESRGAN
Spongebob De-Quantize Joey 1x CC-BY-NC 4.0 ESRGAN Animation - Quantized 2019-11-02 Removed color quantization/indexing and dithering from cartoon style images and textures 1x_1xDEDITHER_32_512_126900_G
4x Spongebob v6 Deblur Joey 4x CC-BY-NC 4.0 ESRGAN Animation 2019-11-08 After not being entirely happy with the main Spongebob v6 model, I trained a new one with blurring OTF options and two different downscale types. This one is much better in my opinion. 4x Spongebob v6
4x Spongebob v6 De-Quantize Joey 4x CC-BY-NC 4.0 ESRGAN Animation - Quantized 2019-11-08 A model I trained to do both de-quantizing as well as upscaling. The results are pretty blurry but it works decently for what it is. 4x Spongebob v6
4x Spongebob v6 Joey 4x CC-BY-NC 4.0 ESRGAN Animation 2019-11-08 New version of the Spongebob model. Ideally it's a lot sharper and cleaner but I'm still not sure if it works better than the old one. From what I can tell it's better in many cases. 4xESRGAN
SpongeBob.CEL.2.HD.125ki.499e-PHOENiX.pth Phoenix 4x GPLv3 - SHARE YOUR CHANGES - If you use this as a pretrained model, share your new model!!! ESRGAN Animation 2019-12-24 Restorative CEL Animation MPEG-1 and 2 Model specifically crafted for SpongeBob S01. RRDB_PSNR_x4.pth
1x_SpongeBC1-Lite Joey 1x CC BY-NC-SA 4.0 BC1/DXT1 compression 2020-11-01 First ever lite BC1/DXT1 model. Probably only useful for cartoony textures like those in spongebob games or other cartoon licensed games. 1x_DIV2K-Lite_80k
4x_SpongeBob-Reloaded Joey 4x CC BY-NC-SA 4.0 ESRGAN Animation, Pixel Art 2020-12-11 4xSpongeBob
4x_SpongeBob-Reloaded-SWAG Joey 4x CC BY-NC-SA 4.0 ESRGAN Animation, Pixel Art 2020-12-11 4xSpongeBob
2x-UniScale_CartoonRestore-lite Kim2091 2x CC BY-NC-SA 4.0 ESRGAN Animation, Pixel Art 2021-08-31 This model has VERY strong compression removal and line restructuring that allows it to restore any heavily compressed drawings, animation, cartoons, or anime. Also works on games as well as DDS compression. It renders frames very quickly and is very viable for restoring videos. 4x-MMScale Comparisons:

https://cdn.discordapp.com/attachments/880826637543964712/882136618461458462/unknown.png https://cdn.discordapp.com/attachments/880826637543964712/882136455999262750/unknown.png https://cdn.discordapp.com/attachments/880826637543964712/882136979410673684/unknown.png https://cdn.discordapp.com/attachments/649861104645701637/882121519973666886/unknown.png https://cdn.discordapp.com/attachments/649861104645701637/882124248368427078/unknown.png Video Example: https://cdn.discordapp.com/attachments/880826637543964712/882110147676221480/Spongebob_UniScale_CartoonRestore.mp4 Original for comparison: https://cdn.discordapp.com/attachments/547949806761410560/881971445813633044/Spongebob_Original.mp4

2x_ATLA_KORRA_336200_G.pth aptitude 2x ESRGAN Animation 2021-07-22 Upscaling of Animation based on The Legend of Korra. 2xESRGAN.pth https://imgsli.com/NjIzMzU https://imgsli.com/NjIzMTY https://imgsli.com/NjIzMTc https://imgsli.com/NjIzMTg https://imgsli.com/NjIzMTk https://imgsli.com/NjIzMjA https://imgsli.com/NjIzMjE https://imgsli.com/NjIzMjQ https://imgsli.com/NjIzMjc https://imgsli.com/NjIzMjY https://imgsli.com/NjIzMjU

Digital Animation

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
4x_DigitalFake-2.1 Joey 4x CC BY-NC-SA 4.0 ESRGAN Digital Animation 2021-02-18 Replica of DigitalFrames 2.1 but interpolatable RRDB_ESRGAN_x4_old_arch.pth
4X_KCJPUNK_1.0233089 G.pth KCJPUNK 4x CC BY-NC-SA 4.0 ESRGAN Digital Animation 2021-03-23 Up-scaling Digital Animation 4x_fatal_Anime_500000_G
2X_KcjpunkAnime_2.0_Lite_196496_G KCJPUNK 2x CC BY-NC-SA 4.0 ESRGAN-light Digital Animation 2021-03-23 Up-scaling Digital Animation This is my first attempt to make Light model so I started with 2x version. This model is much faster and give better results than my previous one.

Drawings

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample


KDM003_scans_1x.pth BoxDrop 1x ESRGAN Art 2019-07-29 Clean up model for scanned illustrations. - Made to remove moire patterns, reduce small imperfections, and correct mild compression artifacts in scanned Kingdom Death: Monster illustrations. CMYK printing often shifts colors, so this is intended to reverse that color shifting as well. Failed attempts based on ESRGAN_1x_JPEG_80to100
DigiPaint Rastrum 4x CC0 ESRGAN Art 2019-09-07 Digital Art Upscaler 4xfalcoon300(manga).pth

General Animation

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
American Dad 2 (American.Dad.2.HD.150ki.5e-PHOENiX.pth) PHEONiX (?) 4x ESRGAN Animation American Dad
FatalimiX Twittman 4x CC BY-NC-SA 4.0 (?) ESRGAN Animation 2019-10-29 Comic and Cartoon style images 4x_Fatality_MKII_90000_G_02.pth
Comic Book LyonHrt 4x CC BY-NC-SA 4.0 ESRGAN Animation Comic / Drawings. Trained on Custom (Spider-Man) dataset none (no interpolation)
Fatal_Anime Twittman 4x CC BY-NC-SA 4.0 (?) ESRGAN Animation Trained on Anime and Manga images none (no interpolation)
HugePaint DinJerr 8x CC BY-NC 4.0 ESRGAN Digital Illustrations Trained on a variety of images from ArtStation HugePeeps
4x_AbeScale mitch#1337 4x GNU ESRGAN Linework Cartoons Dataset: LR: Clone High DVD, HR: Re-illustrated Vectors from Frames 4xESRGAN
2x_Loyaldk-SuperPony_370000 V1.0 ChaseMMD 2x CC BY-NC-SA 4.0 ESRGAN Animation 2021-02-24 Upscale MLP episodes 2x_ERGAN https://imgsli.com/NDIwNTY https://imgsli.com/NDIwNTg https://imgsli.com/NDIwNjE https://imgsli.com/NDIwNjI https://imgsli.com/NDIwNjM
2x_Loyaldk-LitePony_380500 V1.0 ChaseMMD 2x CC BY-NC-SA 4.0 ESRGAN Animation 2021-03-01 Upscale MLP episodes. Liter version. 2x_ESRGAN
2x_Loyaldk-LitePony_500000_V2.0 ChaseMMD#6957 2x CC BY-NC-SA 4.0 ESRGAN (NF=32, NB=12) Animation 2021-04-06 Upscale MLP episodes. Liter version. Able to handle compression better compared to V1.0 and no longer creates halo's/rainbows. Good for Vector 2D art however converts detail to blobs. none
2x_Loyaldk-MediumPony_500000_V2.0 ChaseMMD 2x ESRGAN (NF=48, NB=18) Animation 2021-04-11 Upscale MLP episodes. Liter version. Able to handle compression better compared to V1.0 and no longer creates halo's/rainbows. Good for Vector 2D art however converts detail to blobs. Leaves more blobs when converting detail to blobs compared to litepony none
4x_Loyaldk-LitePony_500000_V2.0 ChaseMMD 4x CC BY-NC-SA 4.0 ESRGAN (NF=32, NB=12) Animation 2021-04-12 Good for Vector 2D art however converts detail to blobs. Quality seems weak with this one. However posting anyways to see if a use is found. none
2x_Loyaldk-SuperPony_500000_V2.0 ChaseMMD 2x CC BY-NC-SA 4.0 ESRGAN Animation 2021-04-30 Upscale MLP episodes. Full version. Able to handle compression better compared to V1.0 and no longer creates halo's/rainbows. Good for Vector 2D art however converts detail to blobs. none
4x_Loyaldk-SuperPony_500000_V2.0 ChaseMMD 4x CC BY-NC-SA 4.0 ESRGAN Animation 2021-04-30 Upscale MLP episodes. Full version. Able to handle compression better compared to V1.0 and no longer creates halo's/rainbows. Good for Vector 2D art however converts detail to blobs. none
4x_Loyaldk-MediumPony_500000_V2.0 ChaseMMD 4x CC BY-NC-SA 4.0 ESRGAN Animation 2021-04-30 Upscale MLP episodes. Full version. Able to handle compression better compared to V1.0 and no longer creates halo's/rainbows. Good for Vector 2D art however converts detail to blobs. none
Platoon Model Set ChaseMMD 4x CC BY-NC-SA 4.0 ESRGAN Animation 2021-06-07 Upscale Anime while keeping as much of the original detail as possible. Isn't among the sharpest models and if the anime is somewhat blurry it will retain that detail but add more pixels to give a smoother edge. Doesn't change the color very much and may make some scene's very slightly darker. Pony Models https://mega.nz/folder/5UAlQCRJ#2Bj1lq8PYeB3P9k5UKSvkQ


Traditional Animation

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
DigitalFilmV5 Lite OptimusPrimal 2x WTFPL ESRGAN Traditional Animation 2021-02-19 Upscaling Dragon Ball Z DBox DVD's. - grainy sources. It keeps some grain, but also doing some cleaning, sharpening, and fixing. none https://imgsli.com/NDE0MzQ https://imgsli.com/NDE0MzU https://imgsli.com/NDE0MzY https://imgsli.com/NDE0Mzc https://imgsli.com/NDE0Mzg https://imgsli.com/NDE0Mzk
4x_HellinaCel VGDCKeroro 4x fuckin do whatever ESRGAN Traditional Animation 2021-03-21 A rougher alternative to 4xCelFrames with a focus on realistic looking cels over nice looking cels. It's trained on DetoriationFrames LRs, so if you give it an image straight from the source it will go twice as hard on it. This can be used to your advantage, though. I recommend cleaning it up before running DetoriationFrames, or else it will come out rough. 4xESRGAN https://imgsli.com/NDU2MjU


Image Restoration

Image Compression

JPEG Artifacts
Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
JPG (20-40%) BlueAmulet 1x CC BY-NC 4.0 ESRGAN JPEG Trained on Custom (CC0 Textures) JPEG models by Alsa
JPG (40-60%) BlueAmulet 1x CC BY-NC 4.0 ESRGAN JPEG Trained on Custom (CC0 Textures) JPEG models by Alsa
JPG (60-80%) BlueAmulet 1x CC BY-NC 4.0 ESRGAN JPEG Trained on Custom (CC0 Textures) JPEG models by Alsa
JPG (80-100%) BlueAmulet 1x CC BY-NC 4.0 ESRGAN JPEG Trained on Custom (CC0 Textures) JPEG models by Alsa
JPG (20-40%) Alsa 1x CC BY-NC-SA 4.0 ESRGAN JPEG Trained on Custom (Photos / Manga)
JPG (40-60%) Alsa 1x CC BY-NC-SA 4.0 ESRGAN JPEG Trained on Custom (Photos / Manga)
JPG (60-80%) Alsa 1x CC BY-NC-SA 4.0 ESRGAN JPEG Trained on Custom (Photos / Manga)
JPG (80-100%) Alsa 1x CC BY-NC-SA 4.0 ESRGAN JPEG Trained on Custom (Photos / Manga)
4x NMKD-PatchySharp nmkd 4x WTFPL ESRGAN (Old Arch) Art/CGI 2020-09-12 Upscaler for clean images or images with compression artifacts (jpeg quality >75) - Produces very sharp lines/edges due to NN-Filtered HR images. Proven to produce very, very good results on drawings (sharp lines) and CGI, but should also work pretty well for real-world images. 4xESRGAN https://i.imgur.com/PzFkmAg.png
1x_JPEG (by compression level) BlueAmulet 1x CC BY-NC 4.0 ESRGAN JPEG 2019-08-01 A collection of models for jpeg artifact removal, examples are included in the provided link Alsa https://drive.google.com/open?id=1HWokMsUwsR_Mw-NOJgc8OdS8mkdIje_C
DeJpeg Fatality_PlusULTRA! Twittman 1x CC BY-NC-SA 4.0 (?) ESRGAN JPEG 2019-10-29 1x_DeJpeg_Fatality_01_200000_G.pth
DeCompress and DeCompress-Strong Kim2091 4x CC BY-NC-SA 4.0 ESRGAN JPEG (works on many compression formats) 2021-09-07 This is UniScaleV2, but intended for images with compression. Seems to work best on realistic images. 4xESRGAN https://cdn.discordapp.com/attachments/884864597310459996/884952891721383936/unknown.png https://cdn.discordapp.com/attachments/884864597310459996/884957054807179274/unknown.png https://cdn.discordapp.com/attachments/884864597310459996/884960697883193354/unknown.png https://cdn.discordapp.com/attachments/884864597310459996/884953810097827850/unknown.png
JPG PlusULTRA (1x_jpg_PlusULTRA_130000.pth) Twittman 1x CC BY-NC-SA 4.0 (?) ESRGAN JPEG 2019-10-29 1x_DeJpeg_Fatality_01_200000_G.pth
SaiyaJin DeJpeg Twittman 1x CC BY-NC-SA 4.0 (?) ESRGAN JPEG 2019-10-29 Dataset: Anime, real life, manga, generated 1x_DeJpeg_Fatality_PlusULTRA_200000_G.pth
1x_JPEGDestroyer BlackScout 1x GNU GPLv3 ESRGAN JPEG 2020-02-19 This model is meant to reduce or eliminate JPEG Compression without making the original images too smooth or killing detail. It manages to do a fairly good job but don't expect overly compressed images to work with this. 1xESRGAN + previous attempts
4xJaypeg90 Jacob 4x GNU GPLv3 ESRGAN JPEG compression 2020-07-20 Photos/realistic 3D with JPEG compression, quality 85-95 and 4:2:0 chroma subsampling. - Created for Myst3 images, since all have 4:2:0 chroma subsampling and existing JPEG models did not give good results. Favors smoothing over over-sharpening. 4xESRGAN https://i.imgur.com/n09m2Rt.png
1x_SBDV-DeJPEG-Lite Joey 1x CC BY-NC-SA 4.0 ESRGAN (lite) JPEG compression 2020-10-10 1x_DIV2K-Lite_80k.pth
NMKD Jaywreck3 & Jaywreck3-Soft (Lite) Nmkd 1x WTFPL ESRGAN Lite [nf=32 nb=12] JPEG compression 2020-10-13 1xESRGAN 1xESRGAN
MangaJPEG Bunzero++ 1x CC BY-NC-SA 4.0 ESRGAN JPEG 2021-06-17 Remove JPEG artifacts from manga without destroying screentone and other details none https://cdn.discordapp.com/attachments/579685650824036387/855269193762865152/Example_LQ_Input-comparison.png
Aliasing
Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
SS Anti Alias 9x BlueAmulet 1x CC BY-NC 4.0 ESRGAN Anti aliasing Dataset: Custom (9x Supersampling AA) none (no interpolation)
Anti Aliasing Twittman 1x CC BY-NC 4.0 ESRGAN Anti aliasing / Images with pixelated edges Dataset: Custom (?) none (no interpolation)
GIF
Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
DeGif nmkd 2x WTFPL ESRGAN GIF Restoration GIF Restoration 2xESRGAN
DDS (BC1/DXT1, BC3/DXT5 Compression)
Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1x_BC1-smooth2.pth BlueAmulet 1x CC BY-NC 4.0 ESRGAN BC1 Compression 2019-09-05 A model to help remove compression artifacts in BC1-BC3/DXT1-DXT5 compressed images (these all have color encoded the same way) none
1x_artifacts_bc1_free_alsa.pth Alsa 1x CC BY-NC-SA 4.0 ESRGAN BC1 Compression BC1 take 2
1x_BCGone_Smooth_110000_G Mutin_Choler 1x WTFPL ESRGAN BC1 Compression 2020-08-02 Attempts to remove the damages done by BC1 compression. 1xESRGAN https://imgsli.com/MjU5MzQ/4/3
1x_BCGone-DetailedV2_40-60_115000_G Mutin_Choler 1x WTFPL ESRGAN BC1 Compression 2021-03-18 1xESRGAN
Dithering
Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample


1x_artifacts_dithering_alsa.pth Alsa 1x CC BY-NC-SA 4.0 ESRGAN Dithering Dithered Images JPG (0-20%)
4xFSDedither Jacob 4x GNU GPL3 ESRGAN Dithering 2020-01-29 For photos/realistic images, but worth trying on other images that have reduced colors and dithering along with fine details. Trained using the ESRGAN-FS code (https://github.com/ManuelFritsche/real-world-sr/tree/master/esrgan-fs/codes) for better details compared to plain ESRGAN. RRDB_ESRGAN_x4 https://imgsli.com/MTI1NTY/
4xFSDedither_Manga Jacob 4x GNU GPLv3 ESRGAN-FS Dithering 2020-04-21 Cartoons/pixel art/other non-realistic stuff with dithering RRDB_ESRGAN_x4.pth https://imgsli.com/MTQ3Nzc
4xFSDedither_Riven Jacob 4x GNU GPLv3 ESRGAN-FS Dithering 2020-07-11 Fine-tuned 4xFSDedither to upscale images from the game Riven, but should be better in general, particularly on ordered dithering. I adjusted the dataset to have a better variety of dithering parameters, and turned up the HFEN and pixel loss to get better details and color restoration with less noise. 4xESRGAN https://imgsli.com/MTg5NTM https://imgsli.com/MTg5NTQ https://imgsli.com/MTg5NTU https://i.imgur.com/j7Wtn0G.png
1x_DitherDeleter-Smooth_104000_G Mutin_Choler 1x WTFPL ESRGAN Dithering 2021-01-23 1xESRGAN https://imgsli.com/Mzg0MTk/1/2
1x_DitherDeleterV3-Smooth Mutin_Choler 1x WTFPL ESRGAN Dithering 2021-04-18 Attempts to remove the damages done by dithering. 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 32-bit Riemersma to every image in the dataset. 1xESRGAN https://imgsli.com/NTA5MjU/1/0

Blurring

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1x_ThePi7on-Solidd_Deborutify_UltraLite_260k_G ThePi7on 1x CC BY-NC-SA 4.0 ESRGAN Deblur 2021-05-09 Sharpening, line darkening and slight line thinning, specifically made for the Boruto anime.
mdeblur LyonHrt 1x UNKNOWN ESRGAN Blurring Strong deblurring model
1x_PixelSharpen_100000 DinJerr 1x CC BY-NC-SA 4.0 ESRGAN Pixel Art 2021-03-19 Restores blurry/upscaled pixel art. 1xESRGAN https://imgsli.com/NDUxNDQ/5/4
1x_ArtClarity DinnJerr 1x WTFPL ESRGAN Pixel Art 2021-08-05 Texture retaining denoiser and sharpener for digital artwork 4xPSNR
1x_Fatality_DeBlur Twittman 1x Your soul now belongs to me ESRGAN Deblur 2019-10-16 Dataset: Mix of anime, manga, and photos 1x_DeJpeg_Fatality_01_175000_G.pth
UnResize V3 (1x_UnResize_V3_200000_G.pth) Twittman 1x CC BY-NC-SA 4.0 (?) ESRGAN Deblur / Unresize Dataset: Anime, manga, and photos 1x_UnResize_MKII_030000_G.pth
1x-Focus and 1x-Focus_Moderate Kim2091 1x CC BY-NC-SA 4.0 ESRGAN Deblur 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. Dataset: The UniScale Dataset + My Fabric dataset 1xESRGAN Sample 1 Sample 2 Sample 3 Sample 4

Banding

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1x_N64clean BlueAmulet 1x CC BY-NC 4.0 ESRGAN Banding 2020-07-16 N64 textures use a color depth of 5-bits per channel, this model attempts to clean them, restoring smooth gradients in textures 1x_BC1-smooth2.pth
1xBS_DebandizerSPSRV2 BlackScout 1x GNU GPLv3 SPSR Banding 2020-07-21 mostly ends up dithering the image slightly but it has the potential to recover detail. 1xBS_DebandizerSPSRV1
1x_Bandage-Smooth Mutin_Choler 1x WTFPL ESRGAN Banding 2021-04-16 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. 1xESRGAN https://imgsli.com/NTA1NTk/1/0
Debandurh_FS Ultra-lite (1x_Debandurh_FS_lite_140000_G.pth) Twittman 1x CC BY-NC-SA 4.0 (?) ESRGAN Debanding images Dataset: Anime, real life, manga None

Halo Removal

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1x_DeEdge_105000_G Mutin_Choler 1x WTFPL ESRGAN Halo remover 2020-11-03 1xESRGAN https://imgsli.com/MjgxMDU/3/0

Noise

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
LADDIER1 Alexander Syring 4x Unknown ESRGAN Denoise 2019-11-13 Remove noise, grain, box blur, lens blur and gaussian blur and increase overall image quality. RRDB_ESRGAN_x4.pth
1x_NoiseToner-Poisson-Detailed_108000_G Mutin_Choler 1x WTFPL ESRGAN Noise remover 2021-10-08 Attempts to remove the damages done from noise. Successor of sorts to Noisetoner_Poisson_150000_G 1xESRGAN https://imgsli.com/NzQ5MzM/2/0
1x_NoiseToner_Poisson_150000_G Mutin_Choler 1x WTFPL ESRGAN Noise remover 2020-10-14 1xESRGAN https://imgsli.com/MjU1ODU/3/1
1x_NoiseToner_Uniform_100000_G Mutin_Choler 1x WTFPL ESRGAN Noise remover 2020-10-14 1xESRGAN https://imgsli.com/MjU1Nzg/2/1
1x_ISO_denoise_v1 Alpha 1x WTFPL ESRGAN denoise not on discord Remove high ISO noise 1xESRGAN
1x_ISO_denoise_v2 Alpha 1x WTFPL ESRGAN denoise not on discord Remove high ISO noise ISO denoise v1
Film-Degrainer_1-000 Tika 1x CC0 ESRGAN denoise not on discord Remove film grain/noise none


Oversharpening

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1x_DeSharpen Loinne 1x CC BY-NC-SA 4.0 ESRGAN Denoise 2019-06-03 Made for rare particular cases when the image was destroyed by applying noise, i.e. game textures or any badly exported photos. If your image does not have any oversharpening, it won't hurt them, leaving as is. In theory, this model knows when to activate and when to skip, also can successfully remove artifacts if only some parts of the image are oversharpened, for example in image consisting of several combined images, 1 of them with sharpen noise. 1st attempt on random sharpening with the same dataset at 200000 iterations, which was trained on non-random desharp model, total ~600000 iterations on 3 models.

DeToon

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample


detoon LyonHrt ESRGAN Detooning 2019-06-24 A toon to realistic shading style model to wiki under drawings
1xDoubleDetoon Joey 1x CC BY-NC-SA ESRGAN Detooning 2020-07-31 An attempt to detoon images/drawings of people 1xESRGAN



Image De/Colorization

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
BS_Colorizer/Vapourizer BlackScout 1x GNU GPLv3 ESRGAN Colorization 2020-01-30 B/W | 100% Desaturated images. It mostly results in Blue and Yellow images with slight hints of Green, Orange and Magenta. You are free to use this as a pretrain to achieve better results. 1xESRGAN
1x_SpongeColor-Lite Joey 1x CC BY-NC-SA 4.0 ESRGAN (lite) [nf=32 nb=12] Colorization 2020-10-15 The first attempt at ESRGAN colorization that produces more than 2 colors. Doesn't work that great but it was a neat experiment. none
Deoldify Rastrum 4x CC0 ESRGAN Photos 2019-08-29 Old black and white photo restoration. Falcon Fanart

Stylization

Images

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
Rek's Effeks Photoanime v2 Rek 4x GNU GPL3 ESRGAN Stylization 2020-10-17 Photo stylization from JPEGs. Trained on images upscaled by ISO Denoise v2 -> DeJPEG Fatality PlusULTRA -> NMKD Yan2. Essentially a combination of that model chain into one. Use if you're looking for a stylized output, not photo quality. NMKD Yandere2

Specialized Models

Text

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
2x_BSTexty BlackScout 2x GNU GPLv3 ESRGAN Text 2020-03-04 As the name might suggest, this model aims to upscale text with less distortion that other models. It seems to do a good job generally, but don't expect it to be a state of the art model that can upscale magazines and stuff. It makes things more readable but since it was train on B/W pictures it desaturates them. 2x_ESRGAN
NMKD Typescale Nmkd 8x WTFPL ESRGAN Text 2020-11-04 Low-resolution text/typography and symbols 8xESRGAN

Inpainting

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1x_sudo_inpaint_PartialConv2D_424000_G.pth sudo rm -rf / --no-preserve-root#8353 1x CC BY-NC-SA 4.0 ESRGAN Inpainting 2020-12-05 Experimental PartialConv2D attempt to paint with ESRGAN. Took ~10.4 days of training on a P100 and around 1.5 months in total due to Colab limits. Not sure if I will continue training it since training is very slow, but may get better.. Warning: Result can vary with different tilesizes. Try not to tile your data. None Samples
1x_NMKD-YandereInpaint_375000_G.pth Nmkd 1x Unknown ESRGAN Inpainting Unknown None Samples

Fabric/Cloth

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
4x-Fabric and Fabric-Alt Kim2091 4x CC BY-NC-SA 4.0 ESRGAN Fabric 2021-09-15 This model set upscales fabric or cloth textures (works on cats too!). The Alt model is just an earlier iteration version. It may work better on some images.The images need to be minimally compressed or passed through a decompression model first. It works with DDS compression though. 4xESRGAN Sample 1 Sample 2 Sample 3 Sample 4


Alphas

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
FireAlpha BlueAmulet 4x CC BY-NC 4.0 ESRGAN Alpha (4 channel) 2019-11-12 none
4x_1ch-Alpha-Lite Joey 4x CC BY-NC-SA 4.0 ESRGAN Alpha 2020-12-15 Obsoleted by Joey's Fork - Alpha channels of PNGs none
2x_Gen5-Alpha Joey 2x CC BY-NC-SA 4.0 ESRGAN Pixel Art with Tranparency / Alpha Channel 2021-02-03 4xFireAlpha
8x_Sphax-Alpha-NN Joey 8x CC BY-NC-SA 4.0 ESRGAN Pixel Art with Tranparency / Alpha Channel 2021-02-04 Replica of sphax with transparency 4xFireAlpha
4x_PocketMonsters-Alpha Joey 4x CC BY-NC-SA 4.0 ESRGAN Pixel Art with Tranparency / Alpha Channel 2021-02-04 upscaling pixel art with alpha channels that should perform better than any other. It should work well on both cartoon and 3D styled content. 4xFireAlpha
Skyrim Alpha Deorder 4x CC0 ESRGAN Pixel Art with Tranparency / Alpha Channel Dataset: Alpha Channels from Skyrim Unknown

CGI

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
WaifuGAN_v3_30000 DinnJerr 4x CC BY-NC 4.0 ESRGAN CGI 2019-07-12 Upscaling CG-painted anime with variable outlines. Manga109v2.pth
2xBS_Wolly BlackScout 2x GNU GPLv3 ESRGAN CGI Animation 2020-02-07 Pixar Movies or Wall-E pictures/frames 2xESRGAN
4xSGI ChrisNonyminus 4x GNU GPL3 ESRGAN CGI 2020-12-17 Upscaling and dedithering pre-rendered sprites, images and textures made in the 90s. Basically vintage CGI. 4xESRGAN https://imgur.com/a/iwLTjeB
CGIMaster_v1 Madiator 2x GNU GPL3 ESRGAN CGI Animation 2021-01-14 mixed 3D/2D CGI animations on some 2D animations it might sharpen the edges. General usage is to upscale CGI animations compressed by YouTube. Sharp_Anime_v2 https://imgsli.com/Mzc1NTM

Luminance/Chroma

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample


1x_BSLuma BlackScout 1x GNU GPLv3 ESRGAN Luma 2020-02-28 Fix Luminance issues?? LumaSharpen ESRGAN Edition? - This model mostly does what "Lumasharpen" algorithms do. It may help fixing images with Luminance images issues? Like old DVD rips? I am not sure, didn't test. none
1x_BSChroma BlackScout 1x GNU GPLv3 ESRGAN Sharpen 2020-02-29 ChromaSharpen - makes the colors slightly more vibrant with a sideeffect of possibly adding Chromatic Abberation to the image. I am not sure about the usage of this model on real case scenarios but anything blurry or with fuzzy colors could work none

Cats

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
Cat_Patch Twittman 4x CC BY-NC-SA 4.0 (?) ESRGAN Cats not on discord previous attempt

Coins

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
4x_Nickelfront BlackScout 4x GNU GPLv3 ESRGAN Coins 2020-02-13 Upscale coins. That's it. If you were mad at me because Nickelback doesn't make any sense. Now you have the perfect solution to your problems. If you want to upscale nickels or anything with similar texture made out of metal, now you can. It works pretty well for a joke. 4xESRGAN

Faces

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
4x_Faces_N_250000.pth Twittman 4x ESRGAN Faces 2019-07-18 Upscales images of faces of different scales, sometimes resulting in monsters. 4xESRGAN
4x_Faces_04_N_180000_G Twittman 4x ESRGAN Faces 2019-07-23 Upscale faces both pixelized and real 4x_Faces_N_250000.pth
Face-Ality V1 (4x_Fatality_Faces_310000_G.pth) Twittman 4x CC BY-NC-SA 4.0 (?) ESRGAN Faces Dataset: Custom (Faces) 4x_Faces_04_N_180000_G.pth
TGHQFace8x tg 8x GNU GPL3 ESRGAN Faces 2019-11-27 Upscales blurry 128px faces, usefull for enhancing that someone in a small picture. 8xESRGAN https://imgsli.com/OTM1NQ
FArtFace DinJerr 4x CC BY-NC 4.0 ESRGAN Faces 2019-11-28
4x_BS_SbeveHarvey BlackScout 4x GNU GPLv3 ESRGAN Faces 2020-07-24 Upscale Steve Harvey, but maybe other things, somehow?? 4xESRGAN
Face Focus LyonHrt 4x CC BY-NC-SA 4.0 ESRGAN Faces not on discord Face De-blur - slightly out of focus / blurred images of faces. It is aimed at faces / hair 4xPSNR
TGHQFace8x Torrentguy 8x [https://www.gnu.org/licenses/gpl-3.0.en.html GNU GPLv3] ESRGAN Face Upscaling 8xESRGAN

Foliage/Ground

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1x_Plants_400000_G.pth Muf 1x Public Domain ESRGAN bad upscale 2021-06-23 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. 1x_NMKD-h264Texturize_500k.pth https://imgsli.com/NTg2MDk https://imgsli.com/NTg2MDg https://imgsli.com/NTg2MTA
Ground ZaphodBreeblebox 4x ESRGAN Upscales ground textures 2021-06-23 Dataset: Custom (Ground textures Google)

Video Games

Game Screenshots

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
Minepack BlackScout 4x CC BY-NC-SA ESRGAN Upscaling pack.png 2020-01-26 Upscales Minecraft screenshots by 4x. May suffer from haloing, weird patterns on blocks and JPEG-like artifacts. 4xESRGAN.pth
4xPackCraft_v4 Joey 4x CC BY-NC-SA 4.0 ESRGAN Upscaling pack.png 2020-09-05 Designed to upscale one specific minecraft screenshot. Results on dissimilar screenshots may be poor. 4xESRGAN/previous versions https://cdn.discordapp.com/attachments/436411385673547787/750481717307113543/pack.png
MinecraftAlphaUpscaler with Good data Washed Up 4x GNU GPLv3 ESRGAN Upscaling pack.png 2020-01-29 Designed to upscale one specific minecraft screenshot. Results on dissimilar screenshots may be poor. RRDB_PNSR_x4.pth
ScreenBooster V2 BlackScout 4x CC BY-NC-SA ESRGAN CGI 2020-01-29 Game Screenshots none
BS_ScreenBooster_SPSR BlackScout 4x CC BY-NC-SA SPSR CGI 2020-07-18 This model is designed to upscale game screenshots (3D Games) by 4 times. The SPSR version is an improvement over the ESRGAN based V2. Screenbooster V2

Normal Map/Bump Map Generation

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1x_NormalMapGenerator-CX-Lite Joey 1x CC BY-NC-SA 4.0 ESRGAN Lite [nf=32 nb=12] Map Generation - normal maps 2020-11-04 Generating normal maps from textures 1x_DIV2K-Lite_450k.pth
1x_FrankenMapGenerator-CX-Lite Joey 1x CC BY-NC-SA 4.0 ESRGAN Lite [nf=32 nb=12] Map Generation - roughness and displacement maps 2020-11-07 This model generates "Franken Maps" (named after Frankenstein), which is a custom material map combination I made. Basically, the Red channel of RGB is just the texture converted to grayscale, the Green channel is the roughness map, and the Blue channel is the displacement map. I had to do this to get around the current limitation of CX loss where it requires a 3 channel output (otherwise I would have just made a 2 channel model, or separate single channel models). As of right now the channels need to be manually split from each other but I will be making a tool for doing this automatically in the coming days. 1x_DIV2K-Lite_450k.pth
1x_normals_generator_general_215k LyonHrt 1x CC BY-NC-SA 4.0 ESRGAN Map Generation - Normal Maps This model generates "Franken Maps" (named after Frankenstein), which is a custom material map combination I made. Basically, the Red channel of RGB is just the texture converted to grayscale, the Green channel is the roughness map, and the Blue channel is the displacement map. I had to do this to get around the current limitation of CX loss where it requires a 3 channel output (otherwise I would have just made a 2 channel model, or separate single channel models). As of right now the channels need to be manually split from each other but I will be making a tool for doing this automatically in the coming days. none (no interpolation)

Video Game Textures

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample


Fallout Weapons (Fallout 4 Weapons?) Bob 4x CC BY-NC-SA 4.0 ESRGAN Game textures 2019-08-05 Video game textures, mostly metal rusty, clean or painted Manga109Attempt
Fallout Weapons V2 Bob 4x CC BY-NC-SA 4.0 ESRGAN Game textures 2019-08-23 Video game textures, mostly metal rusty, clean or painted Fallout 4 Weapons
4x_ThiefGoldMod_100000 Akven 4x no idea ESRGAN Game textures 2020-05-15 Version of the previous model but based on Manga109 pretrained model and with slightly different dataset. Sometimes gives better results especially for wood and metal, sometimes worse. Sometime generates the same dotted artifacts on very bright/white images. 4x_Manga109Attempt https://imgsli.com/MTYzNjI
4x_ThiefGold_110000 Akven 4x no idea ESRGAN Game textures 2020-05-15 Various game textures. Primary wood, metal, stone RRDB_ESRGAN_x4 https://imgsli.com/MTYzNjI
4x-VolArt Kim2091 4x CC BY-NC-SA 4.0 ESRGAN Game textures/Art 2021-09-18 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. 4xESRGAN Sample 1 Sample 2
2xFaithfulSPSR Joey 2x CC BY-NC-SA SPSR Pixel art 2020-07-19 Mainly just a test for SPSR. Seems to work better than the original 2xFaithful32_1316 that I used as a pretrained, even though it uses the same dataset. 2xFaithful32_1316
2x_FakeFaith-Lite Joey 2x CC BY-NC-SA 4.0 ESRGAN (lite) Pixel Art 2020-10-12 An attempt at recreating the "faithful" style without using the faithful dataset -- aka keeping the "pixel art" style of pixel art. 2x_Faithful-Lite
2x_Faithful-Lite Joey 2x CC BY-NC-SA 4.0 ESRGAN (lite) Pixel Art 2020-10-12 A "lite" model version of my Faithful model none
1x_DXTless_SourceEngine_170000_G Xeller 1x WTFPL ESRGAN DTX5 Compression 2021-04-10 This model is made for Source Engine textures. It tries to remove compression artifacts such as blockyness, discoloration, green tint. It does pretty well on a lot of things, realistic stuff as well, but it was mostly made to work on TF2 textures. It's made to keep as much detail as possible, without any unnecessary denoising/sharpening. Huge thanks to Twittman for assisting me along this journey. 1x_Saiyajin_DeJpeg_300000_G https://imgsli.com/NDk1NTk https://imgsli.com/NDk1NjA https://imgsli.com/NDk1NjE https://imgsli.com/NDk1NjI
Trixie LyonHrt 4x CC BY-NC-SA 4.0 ESRGAN Faces / Game Textures not on discord 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 none
Skyrim Armory Alsa 4x CC BY-NC-SA 4.0 ESRGAN Game textures/equipment not on discord Manga109Attempt
Skyrim Misc Deorder 4x CC0 ESRGAN Game textures not on discord Skyrim Diffuse Textures ?
Skyrim Wood Laeris 4x ESRGAN Game textures not on discord Wood ?
4x-SkyrimTexV2.1 and V2_Fabric Kim2091 4x CC BY-NC-SA 4.0 ESRGAN Game textures 2021-09-25 This model set upscales most Skyrim textures. I hope it helps 🙂 The base model (2.1) works well on stone, wood, metals, and most other textures. The Fabric model is a 50/50 interpolation with a stronger iteration of this model and my Fabric model. As you can tell by the name, it's intended for Fabric textures. If you want to upscale Alpha textures, use a model dedicated to it. There's an INFO file in the folder, it just explains the extra models 4xESRGAN Sample 1 Sample 2 Sample 3 Sample 4
Forest LyonHrt 4x CC BY-NC-SA 4.0 ESRGAN Game textures not on discord Wood / Leaves none
Morrowind Mixed mkultra 4x CC BY-NC-SA 4.0 ESRGAN Game textures not on discord Morrowind Mod Textures 4xESRGAN
Map LyonHrt 4x CC BY-NC-SA 4.0 ESRGAN Game textures not on discord Map / Old Paper with text none


Video Restoration

Video Compression

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1x_cinepak_200000 Twittman 1x CC BY-NC-SA 4.0 (?) ESRGAN Compression 2019-07-03 Removal of Compression such as Cinepak, msvideo1 and Roq none
1x_cinepak_alt.pth buildist 1x GNU GPLv3 ESRGAN Compression Cinepak (only) none
DeBink v4/v5/v6 Kim2091 1x CC BY-NC-SA 4.0 ESRGAN Compression 8.6.21 This model removes early 2000s Bink and other compression artifacts. Works well on almost any image or video compression type. none
NMKD h264Texturize Nmkd 1x WTFPL ESRGAN Texturizing 2020-10-20 Tries to reverse heavy h264 compression. Fails. Can be used to texturize images though. 4x ESRGAN
1x_Filmify4K_v2_325000_G.pth Muf 1x Public Domain ESRGAN artifact 2021-07-19 This model attempts to make films upscaled to 4K with Topaz Gaia-HQ look more natural and filmic. It sharpens, adds film grain, and smooths out small artefacts from the upscaling process. I recommend adding a tiny amount of grain to the input to seed the model (you can do this in VEAI), otherwise the film grain will remain static across frames that don't move much. Pretrain model used with permission to relicense from Twittman. 1x_UnResize_V3_110000_G.pth https://imgsli.com/NjE5MTE https://imgsli.com/NjE5MTI https://imgsli.com/NjE5MTM https://imgsli.com/NjE5MTQ
DeIndeo Wild West Quest#7975 4x WTFPL ESRGAN Indeo Compression Artifacts Dataset: Custom 4xESRGAN

VHS Tapes

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1xBaldrickVHSFix_180000_G_V0.2 NimRodZorg 1x CC BY-NC-SA 4.0 ESRGAN VHS 2021-03-03 Fixing minor VHS Chroma and Pattern Noise - NOTE: only works on deinterlaced sources 1xESRGAN
2x_VHS-upscale-and-denoise_Film_477000_G Itewreed 2x CC BY-NC-SA 4.0 ESRGAN VHS 2021-03-28 VHS captures of Film material, but may work on VHS recorded native SD-TV material as well. Also useable for cleaned up source material none
VHS-Sharpen-1x RTX 2080 ti hoarder 1x CC BY-NC-SA 4.0 ESRGAN VHS 2021-03-19 Make old VHS footage crispy. This model will not work on video and images with noticeable JPEG/Video compression artifacts, noticeable interlacing or haloing, heavy tape distortion/artifacts and scenes with tons of detail. For best results, use a downscaled HD capture of the VHS tape you intend to use it on. 1xESRGAN https://imgsli.com/NDUxNDY/2/3

Pretrained Models

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1xESRGAN victorca25 1x Apache License 2.0 ESRGAN Pretrained 2019-07-06 RRDB_ESRGAN_x4.pth
2xESRGAN victorca25 2x Apache License 2.0 ESRGAN Pretrained 2019-07-06 RRDB_ESRGAN_x4.pth
4xESRGAN xinntao 4x Apache License 2.0 ESRGAN Pretrained 2019-07-06 RRDB_ESRGAN_x4.pth
8xESRGAN victorca25 8x Apache License 2.0 ESRGAN Pretrained 2019-07-06 RRDB_ESRGAN_x4.pth
16xESRGAN victorca25 16x Apache License 2.0 ESRGAN Pretrained 2019-07-06 RRDB_ESRGAN_x4.pth
1x PSNR Pretrained Model BlueAmulet 1x Apache License 2.0 (ESRGAN's license) ESRGAN Pretrained 2020-04-20 The original RRDB_PSNR_x4.pth model converted to 1x, 2x, 8x and 16x scales, intended to be used as pretrained models for new models at those scales. These are compatible with victor's 4xESRGAN.pth conversions RRDB_PSNR_x4.pth
2x PSNR Pretrained Model BlueAmulet 2x Apache License 2.0 (ESRGAN's license) ESRGAN Pretrained 2020-04-20 The original RRDB_PSNR_x4.pth model converted to 1x, 2x, 8x and 16x scales, intended to be used as pretrained models for new models at those scales. These are compatible with victor's 4xESRGAN.pth conversions RRDB_PSNR_x4.pth
4x PSNR Pretrained Model BlueAmulet 4x Apache License 2.0 (ESRGAN's license) ESRGAN Pretrained 2020-04-20 The original RRDB_PSNR_x4.pth model converted to 1x, 2x, 8x and 16x scales, intended to be used as pretrained models for new models at those scales. These are compatible with victor's 4xESRGAN.pth conversions RRDB_PSNR_x4.pth
8x PSNR Pretrained Model BlueAmulet 8x Apache License 2.0 (ESRGAN's license) ESRGAN Pretrained 2020-04-20 The original RRDB_PSNR_x4.pth model converted to 1x, 2x, 8x and 16x scales, intended to be used as pretrained models for new models at those scales. These are compatible with victor's 4xESRGAN.pth conversions RRDB_PSNR_x4.pth
16x PSNR Pretrained Model BlueAmulet 16x Apache License 2.0 (ESRGAN's license) ESRGAN Pretrained 2020-04-20 The original RRDB_PSNR_x4.pth model converted to 1x, 2x, 8x and 16x scales, intended to be used as pretrained models for new models at those scales. These are compatible with victor's 4xESRGAN.pth conversions RRDB_PSNR_x4.pth

Pretrained Discriminators

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
1x Pretrained Discriminator Pack Joey 1x CC BY-NC-SA 4.0 VGG Pretrained discriminators 2020-10-26 Most of these are my spongebob dataset so they will be more useful for cartoons but I did include my original faithful model discriminator. none
2x Pretrained Discriminator Pack Joey 2x CC BY-NC-SA 4.0 VGG Pretrained discriminators 2020-10-26 Most of these are my spongebob dataset so they will be more useful for cartoons but I did include my original faithful model discriminator. none
4x Pretrained Discriminator Pack Joey 4x CC BY-NC-SA 4.0 VGG Pretrained discriminators 2020-10-26 Most of these are my spongebob dataset so they will be more useful for cartoons but I did include my original faithful model discriminator. none
8x Pretrained Discriminator Pack Joey 8x CC BY-NC-SA 4.0 VGG Pretrained discriminators 2020-10-26 Most of these are my spongebob dataset so they will be more useful for cartoons but I did include my original faithful model discriminator. none
4x_RRDB-G_ResNet-D (Both G and D) Joey 4x CC BY-NC-SA 4.0 ESRGAN (G) / ResNet (D) Pretrained 2021-01-17 Clean bicubic downscales / Pretrained models (G/D) RRDB_ESRGAN_x4_old_arch.pth

SOFVSR Models

These models are for SOFVSR, they will not work in Cupscale or the main ESRGAN forks. You need this to use it: https://github.com/JoeyBallentine/Video-Inference

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
3x_Video_TSSM Joey 3x CC BY-NC-SA 4.0 SOFVSR Animation 2020-11-17 none
3x_Video_TSSM_RRDB Joey 3x CC BY-NC-SA 4.0 SOFVSR RRDB / VESRGAN Animation 2020-11-25 none
2x_SBS11-RRDB Joey 2x CC BY-NC-SA 4.0 SOFVSR RRDB / SOFVESRGAN Animation 2020-12-03 none
4x_REDSVAL-7f-RRDB-Lite (both G and D) Joey 4x CC BY-NC-SA 4.0 SOFVSR RRDB / SOFVESRGAN Lite [nf=32, nb=12] IRL videos 2020-12-03 none
SOFVSR_REDS_F3_V1 Sunseille 4x WTFPL RRDB IRL videos 2021-02-26 upscale IRL videos. Use not recommended by creator none https://cdn.discordapp.com/attachments/547949806761410560/813134983236419664/100k_iter.mp4
2x_VimeoScale_Unet Sazoji 2x CC BY-SA 4.0 SOFVSR-RRDB (light arch, 3 frames, nf=32, nb=12) Upscaling video content 2021-09-09 This model is meant to surpass VEAI 2x while being efficient to run quickly with fp16. The real-esrgan/BSRGAN augmentation and Unet should help with videos where the resolution is not ideal and can reconstruct details without effecting blurs in most cases. This model SHOULD run faster than real-esrgan while matching the resolving and enabling some multiframe feature extraction. No major denoising/compression/blurring effects (or artifacts) should be found. Self-Trained Base for the Unet finalisation with vgg_fea discrim Sample 1 Sample 2 Sample 3
4x_VimeoScale Sazoji 4x CC BY-SA 4.0 SOFVSR-RRDB (5 frames) Upscaling IRL video content 2021-10-08 This model is one of the longest I have trained and tuned, includes some noise training but this is not intended for deblocking/decompression. Combined with https://github.com/JoeyBallentine/Video-Inference 's fp16 mode, this should handle most SD and 720p content at or faster than ESRGAN, with a significant bump in quality. Self-Trained Base for the Unet finalisation with vgg_fea discrim Sample 1 Sample 2 Sample 3 Sample 4

Pretrained SOFVSR Models

Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
video_G victorca25 4x Unknown SOFVSR net Trained on REDS' size dataset none
VESRGAN_G victorca25 4x Unknown RRDB Trained on REDS' size dataset none

CAIN Models

CAIN is a video frame rate interpolation AI. These models are intended for use with CAIN only. These CANNOT be used with Cupscale or ESRGAN, you need this: https://gitlab.com/hubert.sontowski2007/cainapp
Model Name Author Scale License Architecture Purpose (short) Date Posted Purpose (Full) Pretrained_Model_G sample
190562_vimeo_enchanced.pth hubert 2x MIT CAIN RL videos - interpolation 2021-07-13
cainliteanime.pth hubert 2x MIT CAIN Anime - interpolation 2021-08-06 Sample
rvpV1 sudo rm -rf / --no-preserve-root#8353 2x CC BY-NC-SA 4.0 CAIN Video Frame Interpolation for anime openings 2021-09-14 My ~~first~~ (ok technically second) attempt to create a video frame interpolation model and I like how it turned out. To use it, you can either use https://gitlab.com/hubert.sontowski2007/cainapp, https://github.com/styler00dollar/Colab-CAIN or the bot in [Game Upscale] (model called rvpv1 there, just use --model rvpv1). Some demo videos in pcloud, but you need to download them. The web player seems to playback in low fps. The architecture is mainly the same to the original CAIN, but i modified the padding to be zero padding instead. ``.pt`` means JIT model, `.pth`, means normal pytorch model. Architecture file is in pcloud as well. And no, no cupscale or flowframes. Dataset: Modified Animeinterp dataset https://files.catbox.moe/xiq9vi.mp4
cvpv6.pth hubert 2x MIT CAIN Anime - interpolation 2021-09-21