Helaman's Models

1xDeJPG OmniSR model Meant to remove jpg artifacts. First compression round on the training dataset was 40-95, second round was 80-100. Example: https://slow.pics/c/70nGEvPR PS these are non-otf models. otf experiments have not quite done it for me (probably would need more adjusting), but they can be found in the experiments folder and their outputs in the outputs folder: https://drive.google.com/drive/folders/1RRXZCRVqlqU_iaeF-RGUM9UBWtI0HseY?usp=drive_link

1xDeJPG SRFormer light model Meant to remove jpg artifacts. First compression round on the training dataset was 40-95, second round was 80-100. onnx conversions in this folder which contains all files: https://drive.google.com/drive/folders/1RRXZCRVqlqU_iaeF-RGUM9UBWtI0HseY Example: https://slow.pics/c/70nGEvPR PS these are non-otf models. otf experiments have not quite done it for me (probably would need more adjusting), but they can be found in the experiments folder and their outputs in the outputs folder: https://drive.google.com/drive/folders/1RRXZCRVqlqU_iaeF-RGUM9UBWtI0HseY?usp=drive_link

A 2x Compact anime upscale model that handles AVC (h264) degradation. Applied h264 crf 20-28 degradation together with bicubic, bilinear, box and lanczos downsampling on musl's HFA2k dataset with Kim's dataset destroyer.

A 2x EDSR M anime upscale model that handles AVC (h264) degradation. Applied h264 crf 20-28 degradation and bicubic, bilinear, box and lanczos downsampling on musl's HFA2k dataset with Kim's dataset destroyer.

The second released community trained model on the OmniSR network. Trained with multiscale discriminator to fix decreased output brightness occuring with OmniSR. 2x anime upscale that handles AVC (h264) compression since h264 crf 20-28 degradation together with bicubic, bilinear, box and lanczos downsampling has been applied on musl's HFA2k dataset with Kim's dataset destroyer.

2x SRFormer_light anime upscale model that handles AVC (h264) compression since h264 crf 20-28 degradation together with bicubic, bilinear, box and lanczos downsampling has been applied on musl's HFA2k dataset with Kim's dataset destroyer for training. If you want to run this model with chaiNNer (or another application) you need to use the onnx files with an onnx upscale node. All onnx conversions can be found in the onnx folder on my repo. Example 1: https://imgsli.com/MTkxMTQz Example 2: https://imgsli.com/MTkxMTQ0

A compact anime 2x upscaling model based on musl's HFA2k dataset. Compact 2x anime upscaler with otf compression and blur. The '2xHFA2kCompact.pth' (4.6 MB) is the original trained model file, the other model files are conversions using chaiNNer. Trained on musl's latest dataset release for Anime SISR, which has been extracted from modern anime films, where the selection criteria was high SNR, no DOF and high frequency information. Examples: https://imgsli.com/MTcxNjA4 Example input files: https://drive.google.com/drive/folders/1VSPw8m7VbZO6roM9syE7Nf2QYwwn7GUz Example output files: https://drive.google.com/drive/folders/1NFfomnv6d5RtWy_GwOsKO3uZ_HNOo-2i Future work: Started training a 4xRRDBNet version of this, bigger model so maybe better results but slower, for still/ single anime images. Will release in the future or drop, based on achieved results.

Its like 2xLexicaRRDBNet model, but trained for some more with l1_gt_usm and percep_gt_usm set to true, resulting in sharper outputs. I provide both so they can be chosen based on preferrence of the user.

2x upscaler for the AI generated image output. Trained on 43856 images from lexica.art, so its trained specifically on that model but should work in general on ai generated images.

2x upscaler for AI generated images. Trained on 43856 images from lexica.art, so its trained specifically on that model but should work in general on ai generated images.

2x compact fast universal upscaler pair trained with jpg degradation (down to 40) and multiscale (down_up, bicubic, bilinear, box, nearest, lanczos).

2x span fast universal upscaler pair trained with jpg degradation (down to 40) and multiscale (down_up, bicubic, bilinear, box, nearest, lanczos).

A 2x photo upscaling compact model based on microsofts image pairs. This was one of the earliest models I started training and finished it now for release.

4x photo upscaler for faces with otf jpg compression, blur and resize, trained on FFHQ dataset. This has been trained on and for faces, but i guess can also be used for other photos, might be able to retain skin detail. This is not face restoration, but simply a 4x upscaler trained on faces, therefore input images need to be of good quality if good output quality is desired.

Since the above 4xFFHQDAT model is not able to handle the noise present in low quality input images, i made a small variant/finetune of this, the 4xFFHQLDAT model. This model might come in handy if your input image is of bad quality/not suited for the previous model. I basically made this model in a response to an input image posted in upscaling-results channel as a request to this upscale model (since 4xFFHQDAT would not be able to handle noise), see Imgsli1 example below for result.

Description: 4x photo upscaler for faces, trained on the FaceUp dataset. These models are an improvement over the previously released 4xFFHQDAT and are its successors. These models are released together with the FaceUp dataset, plus the accompanying youtube video This model comes in 4 different versions: 4xFaceUpDAT (for good quality input) 4xFaceUpLDAT (for lower quality input, can additionally denoise) 4xFaceUpSharpDAT (for good quality input, produces sharper output, trained without USM but sharpened input images, good quality input) 4xFaceUpSharpLDAT (for lower quality input, produces sharper output, trained without USM but sharpened input images, can additionally denoise) I recommend trying out 4xFaceUpDAT

Description: 4x photo upscaler for faces, trained on the FaceUp dataset. These models are an improvement over the previously released 4xFFHQDAT and are its successors. These models are released together with the FaceUp dataset, plus the accompanying youtube video This model comes in 4 different versions: 4xFaceUpDAT (for good quality input) 4xFaceUpLDAT (for lower quality input, can additionally denoise) 4xFaceUpSharpDAT (for good quality input, produces sharper output, trained without USM but sharpened input images, good quality input) 4xFaceUpSharpLDAT (for lower quality input, produces sharper output, trained without USM but sharpened input images, can additionally denoise) I recommend trying out 4xFaceUpDAT

Description: 4x photo upscaler for faces, trained on the FaceUp dataset. These models are an improvement over the previously released 4xFFHQDAT and are its successors. These models are released together with the FaceUp dataset, plus the accompanying youtube video This model comes in 4 different versions: 4xFaceUpDAT (for good quality input) 4xFaceUpLDAT (for lower quality input, can additionally denoise) 4xFaceUpSharpDAT (for good quality input, produces sharper output, trained without USM but sharpened input images, good quality input) 4xFaceUpSharpLDAT (for lower quality input, produces sharper output, trained without USM but sharpened input images, can additionally denoise) I recommend trying out 4xFaceUpDAT

Description: 4x photo upscaler for faces, trained on the FaceUp dataset. These models are an improvement over the previously released 4xFFHQDAT and are its successors. These models are released together with the FaceUp dataset, plus the accompanying youtube video This model comes in 4 different versions: 4xFaceUpDAT (for good quality input) 4xFaceUpLDAT (for lower quality input, can additionally denoise) 4xFaceUpSharpDAT (for good quality input, produces sharper output, trained without USM but sharpened input images, good quality input) 4xFaceUpSharpLDAT (for lower quality input, produces sharper output, trained without USM but sharpened input images, can additionally denoise) I recommend trying out 4xFaceUpDAT

4x anime image upscaler with a bit of otf jpg compression and blur. Trained on musl's hfa2k dataset release for Anime SISR, which has been extracted from modern anime films, where the selection criteria was high SNR, no DOF and high frequency information. Examples: https://imgsli.com/MTc2NDgx (PS Example input images are small, each around 500x280 px) \ Example input files: https://drive.google.com/drive/folders/1RI6gGqRy-KxDujbaIrpEMdvFkIWHvfPt \ Example output files: https://drive.google.com/drive/folders/1GqHwPlFp6bIQl4R1AxmrmJ6vUUD8FUxH \ All my model files can be found on my github repo https://github.com/Phhofm/models

4x anime super-resolution with real degradation.

4x lightweight anime upscaler with realistic degradations (compression, noise, blur).

4x lightweight anime upscaler with realistic degradations (compression, noise, blur).

A normal ESRGAN model without degradations and without any pretrain, simply an RRDBNet model trained on paired dataset (4x downsampled) on the full LSDIR dataset (84,991 images / 165 GB)

Upscale photos to x4 their size. 4xLSDIRCompactv2 supersedes the previously released models, it combines all my progress on my compact model. Both CompactC and CompactR had received around 8 hours more training since release with batch size 10 (CompactR had only been up to 5 on release), and these two were then interpolated together. This allows v2 to handle some degradations, while preserving the details of the CompactC model. Examples: https://imgsli.com/MTY0Njgz/0/2

Upscale small good quality photos to 4x their size My first ever model 😄 Well, it’s not the best, but, it’s something 😉 I provide some 15 examples from the validation set here for you to visually see the generated output (with chaiNNer), photo dimensions are in the name

Upscale small photos with compression to 4x their size. Trying to extend my previous model to be able to handle compression (JPG 100-30) by manually altering the training dataset, since 4xLSDIRCompact can't handle compression. Use this instead of 4xLSDIRCompact if your photo has compression (like an image from the web).

Upscale compressed photos to x4 their size. Able to handle JPG compression (30-100).

Upscale good quality input photos to x4 their size The original 4xLSDIRCompact a bit more trained, cannot handle degradation

Upscale small photos with compression, noise and slight blur to 4x their size. Extending my last 4xLSDIRCompact model to Real-ESRGAN, meaning trained on synthetic data instead to handle more kinds of degradations, it should be able to handle compression, noise, and slight blur. Here is a comparison to show that 4xLSDIRCompact cannot handle compression artifacts, and that these two models will produce better output for that specific scenario. These models are not ‘better’ than the previous one, they are just meant to handle a different use case.

Upscale (degraded) photos to x4 their size. Trained on synthetic data, meant to handle more degradations

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

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

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

The RealESRGAN_x4plus finetuned with the big LSDIR dataset (84,991 images / 165 GB), no degradation.

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

4x upscaler for AI generated images. Trained on 43856 images from lexica.art, so its trained specifically on that model but should work in general on ai generated images.

I release my span otf series: They come in three variations: weak, middle, and strong. Mainly meant for photos (can be tried on other things of course). (Also there is a non-otf span model I had been working on simultaneously that I will release shortly, should give better results on less degraded input in comparison to this span otf series) Basically I trained the otf_strong for 90k iter and then medium and weak based off that, with some more training to de-learn (tone down) the (too?) strong degradations. Used discrim resets to correct occuring colorloss in all of them. gt size was for the most part 512 with batch 9 (since i hoped it would give better results) with 0.55 it/s training speed (first 40k at the beginning were gt size 256 with batch 20 with 0.58 it/s).

I release my span otf series: They come in three variations: weak, middle, and strong. Mainly meant for photos (can be tried on other things of course). (Also there is a non-otf span model I had been working on simultaneously that I will release shortly, should give better results on less degraded input in comparison to this span otf series) Basically I trained the otf_strong for 90k iter and then medium and weak based off that, with some more training to de-learn (tone down) the (too?) strong degradations. Used discrim resets to correct occuring colorloss in all of them. gt size was for the most part 512 with batch 9 (since i hoped it would give better results) with 0.55 it/s training speed (first 40k at the beginning were gt size 256 with batch 20 with 0.58 it/s).

I release my span otf series: They come in three variations: weak, middle, and strong. Mainly meant for photos (can be tried on other things of course). (Also there is a non-otf span model I had been working on simultaneously that I will release shortly, should give better results on less degraded input in comparison to this span otf series) Basically I trained the otf_strong for 90k iter and then medium and weak based off that, with some more training to de-learn (tone down) the (too?) strong degradations. Used discrim resets to correct occuring colorloss in all of them. gt size was for the most part 512 with batch 9 (since i hoped it would give better results) with 0.55 it/s training speed (first 40k at the beginning were gt size 256 with batch 20 with 0.58 it/s).

A 4x photo upscaler with otf jpg compression, blur and resize, trained on musl's Nomos8k_sfw dataset for realisic sr, this time based on the DAT arch, as a finetune on the official 4x DAT model. The 295 MB file is the pth file which can be run with the dat reo github code. The 85.8 MB file is an onnx conversion. All Files can be found in this google drive folder. If above onnx file is not working, you can try the other conversions in the onnx subfolder. Examples: Imgsli1 (generated with onnx file) Imgsli2 (generated with onnx file) Imgsli (generated with testscript of dat repo on the three test images in dataset/single with pth file)

4x photo upscaler with otf jpg compression and blur, trained on musl's Nomos8k_sfw dataset for realisic sr