Saltar al contenido
ModelPublicadoExterno
Descargar

4xBHI Realplksr Dysample Otf

Scale: 4x Network type: RealPLKSR Author: Philip Hofmann License: CC-BY-4.0 Purpose: 4x upscaling images, can handle some blur, jpeg compression, and noise, trained with realesrgan otf pipeline. Pretrained Model:...

TipoOtherVersiónRevision 4de90d9Ccalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
28,3 MB
Versión
vRevision 4de90d9
Actualizado
20 oct 2026
Descargas
0
Fuente
Hugging Face

Descripción de la fuente

Link to Github Release

4xBHI_realplksr_dysample_otf

Scale: 4x
Network type: RealPLKSR
Author: Philip Hofmann
License: CC-BY-4.0
Purpose: 4x upscaling images, can handle some blur, jpeg compression, and noise, trained with realesrgan otf pipeline.
Pretrained Model: 4xNomos2_realplksr_dysample
Training iterations: 413000
Description: 4x realplksr dysample model to upscale images, trained on the BHI dataset. This time, instead of manual degradation, I made use of the real-esrgan otf pipeline with adjusted values to handle some blur, noise and jpeg compression.

Fuentes

1 fuente
Hugging FacePrincipalVersión 4de90d9751847f3ff67c4a4b98f46046831589f9
huggingface.co/Phips/4xBHI_realplksr_dysample_otf/tree/4de90d9751847f3ff67c4a4b98f46046831589f9

Verificado 20 oct

Artefactos del modelo

1 artefacto

4xBHI_realplksr_dysample_otf.safetensors

safetensors · 28,3 MB · SHA-256 fb75b19983bc…49ae · Hugging Face

Download file

Extractos de fuentes

2 extractos

--- 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_otf Scale: 4x Network type: RealPLKSR Author: Philip Hofmann License: CC-BY-4.0 Purpose: 4x upscaling images, can handle some blur, jpeg compression, and noise, trained with realesrgan otf pipeline. Pretrained Model: 4xNomos2_realplksr_dysample Training iterations: 413000 Description: 4x realplksr dysample model to upscale images, trained on the BHI dataset. This time, instead of manual degradation, I made use of the real-esrgan otf pipeline with adjusted values to handle some blur, noise and jpeg compression.

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