Notice
OpenModelDB is still in alpha and actively being worked on. Please feel free to share your feedback and report any bugs you find.
The best place to find AI Upscaling models
OpenModelDB is a community driven database of AI Upscaling models. We aim to provide a better way to find and compare models than existing sources.
Found 521 models
Compact
2x
AnimeJaNai_HD_V3_Compact
by the database
Real-time 2x Real-ESRGAN Compact/UltraCompact/SuperUltraCompact models designed for upscaling 1080p anime to 4K.
The aim of these models is to address scaling, blur, oversharpening, and compression artifacts while upscaling to deliver a result that appears as if the anime was originally mastered in 4K resolution. Can be set up to run in real-time with mpv on Windows using https://github.com/the-database/mpv-upscale-2x_animejanai
The development of the V3 models spanned over seven months, during which over 100 release candidate models were trained and meticulously refined. The V3 models introduce several improvements compared to V2, including:
More faithful appearance to original source
Improved handling of oversharpening artifacts, ringing, aliasing
Better at preserving intentional blur in scenes using depth of field
More accurate line colors, darkness, and thickness
Better preservation of soft shadow edges
Overall, the V3 models yield significantly more natural and faithful results compared to the V2 models.test
Compact
2x
AnimeJaNai_HD_V3_SuperUltraCompact
by the database
Real-time 2x Real-ESRGAN Compact/UltraCompact/SuperUltraCompact models designed for upscaling 1080p anime to 4K.
The aim of these models is to address scaling, blur, oversharpening, and compression artifacts while upscaling to deliver a result that appears as if the anime was originally mastered in 4K resolution. Can be set up to run in real-time with mpv on Windows using https://github.com/the-database/mpv-upscale-2x_animejanai
The development of the V3 models spanned over seven months, during which over 100 release candidate models were trained and meticulously refined. The V3 models introduce several improvements compared to V2, including:
More faithful appearance to original source Improved handling of oversharpening artifacts, ringing, aliasing Better at preserving intentional blur in scenes using depth of field More accurate line colors, darkness, and thickness Better preservation of soft shadow edges
Overall, the V3 models yield significantly more natural and faithful results compared to the V2 models.
Compact
2x
AnimeJaNai_HD_V3_UltraCompact
by the database
Real-time 2x Real-ESRGAN Compact/UltraCompact/SuperUltraCompact models designed for upscaling 1080p anime to 4K.
The aim of these models is to address scaling, blur, oversharpening, and compression artifacts while upscaling to deliver a result that appears as if the anime was originally mastered in 4K resolution. Can be set up to run in real-time with mpv on Windows using https://github.com/the-database/mpv-upscale-2x_animejanai
The development of the V3 models spanned over seven months, during which over 100 release candidate models were trained and meticulously refined. The V3 models introduce several improvements compared to V2, including:
More faithful appearance to original source Improved handling of oversharpening artifacts, ringing, aliasing Better at preserving intentional blur in scenes using depth of field More accurate line colors, darkness, and thickness Better preservation of soft shadow edges
Overall, the V3 models yield significantly more natural and faithful results compared to the V2 models.
SwinIR
1x
Bendel_Halftone
by Bendel
A model trained with the goal of preserving texture while removing halftones. I do plan on making improved versions down the line, as this one didn't come out as well as I'd like.
SRFormer
4x
Frankendata_FullDegradation_SRFormer
Description: 4x realistic upscaler that may also work for general purpose usage. It was trained with OTF random degradation with a very low to very high range of degradations, including blur, noise, and compression. Trained with the same Frankendata dataset that I used for the pretrain model.
Compact
2x
Higurashi_v1_compact
by evA-01
this a compact model I trained to upscale the SD Blu-ray release of Higurashi no Naku Koro ni and other early 2000 shows like Yu Gi Ho GX, it can do line darkening and some restoration.
Unfortunately I lost everything related to it from the dataset and training settings
SPAN
1x
SwatKats_SPAN
by Kim2091
This is SaurusX's original description:
Fix vertical blur / split lines / shadowing. A 1x model of my 2xSwatKats. Resolves the same video problems as before, but 1x and faster and meant for chaining to other 2x models (or whatever). Input MUST be 540 vertical as the blur problem is very resolution sensitive.
-------
The goal for this retrain was to get the "magic" of SwatKatsLite into SPAN for much faster video processing. It's about 80% of the way there. There's some artifacts here and there that aren't present in the original, and it has small amounts of color halos in certain areas. I've retrained this model so many times that I've just decided to release it. This particular release was trained to ~450k.
The included Family Guy image shows the color ringing issue. Sorry.
Update: I've added a second alt model that has less color ringing, but doesn't do quite as good with line repair. I believe I've reached architecture limits
SPAN
4x
4x-NomosUni_span_multijpg
by Helaman
4x fast universal upscaler pair trained with jpg degradation (down to 40) and multiscale (down_up, bicubic, bilinear, box, nearest, lanczos).
SPAN
1x
BroadcastToStudio_SPAN
by Kim2091
This is SaurusX's original description:
Improvement of low-quality cartoons from broadcast sources. Will greatly increase the visual quality of bad broadcast tape sources of '80s and '90s cartoons (e.g. Garfield and Friends, Heathcliff, DuckTales, etc). Directly addresses chroma blur, dot crawl, and rainbowing. You're highly advised to take care of haloing beforehand in your favorite video editor as the model will not fix it and may make existing halos more noticeable.
-------
Sadly this model has some intense artifacts. Thankfully the SPAN re-train reduced these a bit, but they're still problematic. This was just a quick test of SPAN's capabilities. This was trained only to ~66k iterations, compared to the 480k of the original.
SPAN
2x
GarfieldJr_span
by evA-01
2x span nf48 model trained with 2x_Garfield dataset.
the output of this model is in no way near the 2x_Garfield, but it can do everything that the esrgan model does to some degree and have the speed advantage.
finally, I would like to thank @SaurusX for providing me with his dataset.
Comp:
https://slow.pics/c/Yezua7O7
Compact
2x
2x-NomosUni_compact_multijpg
by Helaman
2x compact fast universal upscaler pair trained with jpg degradation (down to 40) and multiscale (down_up, bicubic, bilinear, box, nearest, lanczos).