Skip to content
ModelListedExternal
Download

4xBHI Realplksr Dysample Real

Scale: 4x Network type: RealPLKSR Author: Philip Hofmann License: CC-BY-4.0 Purpose: 4x upscaling images, handling some blur, some noise, and compression Pretrained Model: 4xNomos2realplksrdysample Training...

Sourcehuggingface.co/Phips/4xBHI_realplksr_dysample_real/tree/04267a3c6d487e6ed883e567dedd7f09135e6deb
KindOtherVersionRevision 04267a3Bgrade

Model source

Kind
Other
File size
28.3 MB
Version
vRevision 04267a3
Updated
Oct 20, 2026
Downloads
0
Source
Hugging Face

Source description

Link to Github Release

4xBHI_realplksr_dysample_real

Scale: 4x
Network type: RealPLKSR
Author: Philip Hofmann
License: CC-BY-4.0
Purpose: 4x upscaling images, handling some blur, some noise, and compression
Pretrained Model: 4xNomos2_realplksr_dysample
Training iterations: 380000
Description: 4x realplksr dysample model to upscale images, trained on the BHI dataset. This is with a created LR set where I used wtp_destroyer to add blur (50% chance), my ludvae200 model to add noise (50% chance), and then wtp to add compression, scaling, recompression (50% chance), scaling.

Sources

1 source
Hugging FacePrimaryVersion 04267a3c6d487e6ed883e567dedd7f09135e6deb
huggingface.co/Phips/4xBHI_realplksr_dysample_real/tree/04267a3c6d487e6ed883e567dedd7f09135e6deb

Verified Oct 20

Model artifacts

1 artifact

4xBHI_realplksr_dysample_real.safetensors

safetensors · 28.3 MB · SHA-256 e4cbccc2e3c1…75c2 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 3huggingface.co/Phips/4xBHI_realplksr_dysample_real

--- license: cc-by-4.0 pipeline_tag: image-to-image tags: - pytorch - super-resolution --- [Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xbhi_realplksr) 4xBHI_realplksr_dysample_real Scale: 4x Network type: RealPLKSR Author: Philip Hofmann License: CC-BY-4.0 Purpose: 4x upscaling images, handling some blur, some noise, and compression Pretrained Model: 4xNomos2_realplksr_dysample Training iterations: 380000 Description: 4x realplksr dysample model to upscale images, trained on the BHI dataset. This is with a created LR set where I used wtp_destroyer to add blur (50% chance), my ludvae200 model to add noise (50% chance), and then wtp to add compression, scaling, recompression (50% chance), scaling.

NoteOct 20huggingface.co/Phips/4xBHI_realplksr_dysample_real

Source context: 0 downloads · 5 likes · Pipeline image-to-image · Repo Phips/4xBHI_realplksr_dysample_real

NoteAug 3huggingface.co/Phips/4xBHI_realplksr_dysample_real

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