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 620 models
DAT
4x
![4xNomos2_hq_dat2](/thumbs/a5830a98c896629990c0f8a6.jpg)
![4xNomos2_hq_dat2](/thumbs/772e41c09e5e357a8fa5d9ce.jpg)
4xNomos2_hq_dat2
by Helaman
A 4x model for Upscaler .
Link to Github Release
# 4xNomos2_hq_dat2
Scale: 4
Architecture: DAT
Architecture Option: dat2
Author: Philip Hofmann
License: CC-BY-0.4
Subject: Photography
Input Type: Images
Release Date: 29.08.2024
Dataset: nomosv2
Dataset Size: 6000
OTF (on the fly augmentations): No
Pretrained Model: DAT_2_x4
Iterations: 140'000
Batch Size: 4
Patch Size: 48
Description:
A dat2 4x upscaling model, similiar to the 4xNomos2_hq_mosr model, trained and for usage on non-degraded input to give good quality output.
I scored 7 validation outputs of each of the 21 checkpoints (10k-210k) of this model training with 68 metrics.
The metric scores can be found in this google sheet.
The corresponding image files for this scoring can be found here
Screenshot of the google sheet:
!|100
Release checkpoint has been selected by looking at the scores, manually inspecting, and then getting responses on discord to this quick visual test, A B or C, which denote different checkpoints: https://slow.pics/c/8Akzj6rR
Checkpoint B is the one released here, but you can also try out Checkpoint A or Checkpoint C if you like them better.
## Model Showcase:
Slowpics
RealPLKSR
2x
![Text2HD v.1](/thumbs/41948c075f0da1623d8ce416.png)
![Text2HD v.1](/thumbs/8e6bbe0e525660b2161a97bc.jpg)
Text2HD v.1
by asterixcool
A 2x model for Upscale text in very low quality to normal quality..
The upscale model is specifically designed to enhance lower-quality text images, improving their clarity and readability by upscaling them by 2x. It excels at processing moderately sized text, effectively transforming it into high-quality, legible scans. However, the model may encounter challenges when dealing with very small text, as its performance is optimized for text of a certain minimum size. For best results, input images should contain text that is not excessively small.
RealPLKSR
2x
![VHS2HD](/thumbs/5d39a3eea22d135f847c1859.png)
![VHS2HD](/thumbs/b72dba2fc9e6693f78711ffe.jpg)
VHS2HD
by asterixcool
A 2x model for VHS Restoration.
An advanced VHS recording model designed to enhance video quality by reducing artifacts such as haloing, ghosting, and noise patterns. Optimized primarily for PAL resolution (NTSC might work good as well).
MoSR
4x
![4xNomos2_hq_mosr](/thumbs/e42e88bae2307dc5c6ea5292.jpg)
![4xNomos2_hq_mosr](/thumbs/ed8228a0ef66c9fb5be912b1.jpg)
4xNomos2_hq_mosr
by Helaman
A 4x model for Upscaler .
Link to Github Release
# 4xNomos2_hq_mosr
Scale: 4
Architecture: MoSR
Architecture Option: mosr
Author: Philip Hofmann
License: CC-BY-0.4
Subject: Photography
Input Type: Images
Release Date: 25.08.2024
Dataset: nomosv2
Dataset Size: 6000
OTF (on the fly augmentations): No
Pretrained Model: 4xmssim_mosr_pretrain
Iterations: 190'000
Batch Size: 6
Patch Size: 64
Description:
A 4x MoSR upscaling model, meant for non-degraded input, since this model was trained on non-degraded input to give good quality output.
If your input is degraded, use a 1x degrade model first. So for example if your input is a .jpg file, you could use a 1x dejpg model first.
Model Showcase: Slowpics
Compact
1x
![1x BW Denoise](/thumbs/167a8ad198fedd859b4c4255.jpg)
![1x BW Denoise](/thumbs/3f8000c84f17fa1b175733b6.jpg)
1x BW Denoise
by Loganavter
A fast upscaler that is a replacement for standard methods of cleaning noise from the picture. Ideal for BDRemux 720p and 1080p, but only if the noise is monochrome or close to it. So far, attempts are underway to create a dataset that could eliminate color noise at the same speed.
Compact
1x
![1x RGB max Denoise](/thumbs/ce9237da345f352d71c17359.jpg)
![1x RGB max Denoise](/thumbs/f171bff620de90a6ebf8b394.jpg)
1x RGB max Denoise
by Loganavter
A fast upscaler that is a replacement for standard methods of cleaning noise from the picture. Ideal for BDRemux or WEB-DL 720p or 1080p it. It gets rid of floral noise well, the smaller its grain size, the more uniform the resolution for all videos will be. If you need a more stable video, then you can also add 2x-DigitalFlim-SuperUltraCompact after this upscaler. My upscaler can slightly simplify the geometry of very small objects.
RealPLKSR
1x
![1xDeH264_realplksr](/thumbs/28540c5eccb8dc9a82a8e0f6.jpg)
![1xDeH264_realplksr](/thumbs/f6c44867bed965db8da71cb3.jpg)
1xDeH264_realplksr
by Helaman
A 1x model for Restoration, H264 .
Link to Github Release
# 1xDeH264_realplksr
Scale: 1
Architecture: RealPLKSR
Architecture Option: realplksr
Author: Philip Hofmann
License: CC-BY-0.4
Subject: Photography
Input Type: Images
Release Date: 08.08.2024
Dataset: nomosv2
Dataset Size: 6000
OTF (on the fly augmentations): No
Pretrained Model: 1xDeJPG_realplksr_otf
Iterations: 210'000
Batch Size: 8
Patch Size: 64
Description:
A 1x de h264 model to remove h264 compression.
Showcase:
Slowpics
Imgsli
RealPLKSR
1x
![1xDeNoise_realplksr_otf](/thumbs/32f56319a7a8f9fb411fc9f3.jpg)
1xDeNoise_realplksr_otf
by Helaman
A 1x model for Restoration, Denoise .
Link to Github Release
# 1xDeNoise_realplksr_otf
Scale: 1
Architecture: RealPLKSR
Architecture Option: realplksr
Author: Philip Hofmann
License: CC-BY-0.4
Subject: Photography
Input Type: Images
Release Date: 08.08.2024
Dataset: nomosv2
Dataset Size: 6000
OTF (on the fly augmentations): Yes
Pretrained Model: 1xDeJPG_realplksr_otf
Iterations: 200'000
Batch Size: 8
Patch Size: 64
Description:
A 1x realplksr model to denoise, trained with the realesrgan-otf pipeline, also handles a bit of jpg compression (if stronger jpg compression handling is needed, 1xDeJPG_realplksr_otf can be used).
RealPLKSR_dysample
4x
![4xArtFaces_realplksr_dysample](/thumbs/62857ce4d95a12b82b1916eb.jpg)
4xArtFaces_realplksr_dysample
by Helaman
A 4x model for Restoration .
Link to Github Release
# 4xArtFaces_realplksr_dysample
Scale: 4
Architecture: RealPLKSR with Dysample
Architecture Option: realplksr
Author: Philip Hofmann
License: CC-BY-0.4
Subject: Art
Input Type: Images
Release Date: 08.08.2024
Dataset: ArtFaces
Dataset Size: 5'630
OTF (on the fly augmentations): No
Pretrained Model: 4xNomos2_realplksr_dysample
Iterations: 139'000
Batch Size: 6
Patch Size: 64
Description:
A Dysample RealPLKSR 4x upscaling model for art / painted faces.
Based on my ArtFaces Dataset which is a curated version of the metfaces dataset for the purpose of training single image super resolution models.
ESRGAN
4x
No Image
AnalogFrames 1.0
by Muf
Restore frames to their original look as on Drawings. Before analog transfer
Trained on thousands of 4K HQ Drawing scans, the purpose of this model is restore the frame to its original paper and plastic look, with a particular emphasis on textures and preserving those brushstrokes and natural lines. Not to be used with heavily grainy sources.
Note: The random white speckles are an unfortunate side effect of not filtering the dataset.
ESRGAN
4x
No Image
NumericFrames 2.0
by Muf
Upscaling of Numeric Animation from SD to HD with high texture retention.
A serious upgrade over 1.0. Much more universality. Can look good on both clean SD and noisy/grainy source frames. It still has a weakness against sources with strong halos and jagged edges and rainbowing. (Recommended that these issues are fixed beforehand with avisynth)
ESRGAN
4x
No Image
NumericFrames 2.1-Aggressive
by Muf
Upscaling of Numeric Animation from SD to HD with high texture retention.
Provides the sharpest results yet. About 30% better than the base 2.0 version. But as the title says it's the most aggressive version of NF. Does it's best on animation with little to no textures. The model as well as any version of NF is not suitable at all for overly deteriorated/blurred and low quality TVRips and VHSRips copies of animation pieces.