Ir para o conteúdo
ModelListadosExterno
Browse files

4xSPAN Pretrains

Neosr's latest update from yesterday included a new adaptation of the multi-scale ssim loss. This was an experiment to test out the difference between making a SPAN pretrain with pixel loss with L1 criteria (as often...

Fontehuggingface.co/Phips/4xSPAN_pretrains/tree/e831aeca4b8baa5de427616c74c3f562a420c8cf
TipoOtherVersão4xmssim span pretrainCnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
8,55–8,60 MB
Versão
v4xmssim span pretrain
Atualizado
26 de out. de 2026
Fonte
Hugging Face

Descrição da fonte

Link to Github Release

Neosr's latest update from yesterday included a new adaptation of the multi-scale ssim loss.
This was an experiment to test out the difference between making a SPAN pretrain with pixel loss with L1 criteria (as often used in research) vs mssim loss as its only loss.
Models are provided so they can be used for tests or also used as a pretrain for another SPAN model.

4xpix_span_pretrain

Scale: 4
Architecture: SPAN

Author: Philip Hofmann
License: CC-BY-4.0
Purpose: Pretrain
Subject: Realistic, Anime
Date: 10.04.2024

Dataset: nomos_uni
Dataset Size: 2989
OTF (on the fly augmentations): No
Pretrained Model: None
Iterations: 80'000
Batch Size: 12
GT Size: 128

Description: 4x SPAN pretrain trained on pixel loss with L1 criteria (as often used in research) on downsampled nomos_uni dataset using kim's dataset destroyer with down_up,linear,cubic_mitchell,lanczos,gauss,box (while down_up used the same and with range = 0.15,1.5).
The new augmentations except CutBlur have also been used (since CutBlur is meant to be applied to real-world SR and may cause undesired effects if applied to bicubic-only).
Config and training log provided for more details.

4xmssim_span_pretrain

Scale: 4
Architecture: SPAN

Author: Philip Hofmann
License: CC-BY-4.0
Purpose: Pretrain
Subject: Realistic, Anime
Date: 10.04.2024

Dataset: nomos_uni
Dataset Size: 2989
OTF (on the fly augmentations): No
Pretrained Model: None
Iterations: 80'000
Batch Size: 12
GT Size: 128

Description: 4x SPAN pretrain trained on neosr's new adaptation of the multi-scale ssim loss from yesterdays update on downsampled nomos_uni dataset using kim's dataset destroyer with down_up,linear,cubic_mitchell,lanczos,gauss,box (while down_up used the same and with range = 0.15,1.5).
The new augmentations except CutBlur have also been used (since CutBlur is meant to be applied to real-world SR and may cause undesired effects if applied to bicubic-only).
Config and training log provided for more details.

Showcase:
7 Slowpics Examples

Example1 Example2 Example3 Example4 Example5 Example6 Example7

Fontes

1 fonte
Hugging FacePrimárioVersão e831aeca4b8baa5de427616c74c3f562a420c8cf
huggingface.co/Phips/4xSPAN_pretrains/tree/e831aeca4b8baa5de427616c74c3f562a420c8cf

Verificado 26 de out.

Download files

Artefatos de modelo

4 artefatos

4xmssim_span_pretrain.pth

pth · 8,60 MB · SHA-256 234ac9facfdc…5b18 · Hugging Face

Download file

4xmssim_span_pretrain.safetensors

safetensors · 8,55 MB · SHA-256 e0468355ee34…fe68 · Hugging Face

Download file

4xpix_span_pretrain.pth

pth · 8,60 MB · SHA-256 724d6a9f675c…927f · Hugging Face

Download file

4xpix_span_pretrain.safetensors

safetensors · 8,55 MB · SHA-256 5b654da0254c…333c · Hugging Face

Download file

Trechos de fonte

2 trechos
Readme8 de ago.huggingface.co/Phips/4xSPAN_pretrains

--- license: cc-by-4.0 pipeline_tag: image-to-image tags: - pytorch - super-resolution - pretrain --- [Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xSPAN_pretrains) [Neosr](https://github.com/muslll/neosr)'s latest update from yesterday included a [new adaptation of the multi-scale ssim loss](https://github.com/muslll/neosr/wiki/Losses#mssim_opt). This was an experiment to test out the difference between making a SPAN pretrain with pixel loss with L1 criteria (as often used in research) vs mssim loss as its only loss. Models are provided so they can be used for tests or also used as a pretrain for another SPAN model. --- ## 4xpix_span_pretrain Scale: 4 Architecture: SPAN Author: Philip Hofmann License: CC-BY-4.0 Purpose: Pretrain Subject: Realistic, Anime Date: 10.04.2024 Dataset: [nomos_uni](https://github.com/muslll/neosr) Dataset Size: 2989 OTF (on the fly augmentations): No Pretrained Model: None Iterations: 80'000 Batch Size: 12 GT Size: 128 Description: 4x SPAN pretrain trained on pixel loss with L1 criteria (as often used in research) on downsampled nomos_uni dataset using kim's [dataset destroyer](https://github.com/Kim2091/helpful-scripts/tree/main/Dataset%20Destroyer) with down_up,linear,cubic_mitchell,lanczos,gauss,box (while down_up used the same and with range = 0.15,1.5). The new augmentations except CutBlur have also been used (since CutBlur is meant to be applied to real-world SR and may cause undesired effects if applied to bicubic-only). Config and training log provided for more details. --- ## 4xmssim_span_pretrain Scale: 4 Architecture: SPAN Author: Philip Hofmann License: CC-BY-4.0 Purpose: Pretrain Subject: Realistic, Anime Date: 10.04.2024 Dataset: [nomos_uni](https://github.com/muslll/neosr) Dataset Size: 2989 OTF (on the fly augmentations): No Pretrained Model: None Iterations: 80'000 Batch Size: 12 GT Size: 128 Description: 4x SPAN pretrain trained on [neosr](https://github.com/muslll/neosr)'s [new adaptation of the multi-scale ssim loss](https://github.com/muslll/neosr/wiki/Losses#mssim_opt) from yesterdays update on downsampled nomos_uni dataset using kim's [dataset destroyer](https://github.com/Kim2091/helpful-scripts/tree/main/Dataset%20Destroyer) with down_up,linear,cubic_mitchell,lanczos,gauss,box (while down_up used the same and with range = 0.15,1.5). The new augmentations except Cu...

Note8 de ago.huggingface.co/Phips/4xSPAN_pretrains

Source context: 0 downloads · 0 likes · Pipeline image-to-image · Repo Phips/4xSPAN_pretrains