Skip to content
ModelListedExternal
Download

4xHFA2kLUDVAESwinIR Light

Name: 4xHFA2kLUDVAESwinIRlight Author: Philip Hofmann Release Date: 10.06.2023 License: CC BY 4.0 Network: SwinIR Arch Option: SwinIR-light Scale: 4 Purpose: An lightweight anime 4x upscaling model with realistic...

Sourcehuggingface.co/Phips/4xHFA2kLUDVAESwinIR_light/tree/d53094d265a76c8c45e33cda76cf00ab1d051bf8
KindOtherVersion4x HFA2k LUDVAESwin IR lightCgrade

Model source

Kind
Other
File size
16.3 MB
Version
v4x HFA2k LUDVAESwin IR light
Updated
Oct 26, 2026
Source
Hugging Face

Source description

Link to Github Release

4xHFA2kLUDVAESwinIR_light

Name: 4xHFA2kLUDVAESwinIR_light
Author: Philip Hofmann
Release Date: 10.06.2023
License: CC BY 4.0
Network: SwinIR
Arch Option: SwinIR-light
Scale: 4
Purpose: An lightweight anime 4x upscaling model with realistic degradations, based on musl's HFA2k_LUDVAE dataset
Iterations: 350,000
batch_size: 3
HR_size: 256
Epoch: 99 (require iter number per epoch: 3424)
Dataset: HFA2kLUDVAE
Number of train images: 10270
OTF Training: No
Pretrained_Model_G: None

Description: 4x lightweight anime upscaler with realistic degradations (compression, noise, blur). Visual outputs can be found on https://github.com/Phhofm/models/tree/main/4xHFA2kLUDVAE_results, together with timestamps and metrics to compare inference speed on the val set with other trained models/networks on this dataset.

image
image
image

Sources

1 source
Hugging FacePrimaryVersion d53094d265a76c8c45e33cda76cf00ab1d051bf8
huggingface.co/Phips/4xHFA2kLUDVAESwinIR_light/tree/d53094d265a76c8c45e33cda76cf00ab1d051bf8

Verified Oct 26

Model artifacts

1 artifact

4xHFA2kLUDVAESwinIR_light.safetensors

safetensors · 16.3 MB · SHA-256 ea9a78e303d4…899b · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 8huggingface.co/Phips/4xHFA2kLUDVAESwinIR_light

--- 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/4xHFA2kLUDVAESwinIR_light%264xHFA2kLUDVAESRFormer_light) # 4xHFA2kLUDVAESwinIR_light Name: 4xHFA2kLUDVAESwinIR_light Author: Philip Hofmann Release Date: 10.06.2023 License: CC BY 4.0 Network: SwinIR Arch Option: SwinIR-light Scale: 4 Purpose: An lightweight anime 4x upscaling model with realistic degradations, based on musl's HFA2k_LUDVAE dataset Iterations: 350,000 batch_size: 3 HR_size: 256 Epoch: 99 (require iter number per epoch: 3424) Dataset: HFA2kLUDVAE Number of train images: 10270 OTF Training: No Pretrained_Model_G: None Description: 4x lightweight anime upscaler with realistic degradations (compression, noise, blur). Visual outputs can be found on https://github.com/Phhofm/models/tree/main/4xHFA2kLUDVAE_results, together with timestamps and metrics to compare inference speed on the val set with other trained models/networks on this dataset. ![image](https://github.com/Phhofm/models/assets/14755670/64941695-7904-4ddf-9fad-d5f2ff04439a) ![image](https://github.com/Phhofm/models/assets/14755670/095cf1c6-3506-4c3d-a2f3-fa619650915d) ![image](https://github.com/Phhofm/models/assets/14755670/2dfa9f62-4ec2-4fab-9417-1b18bb4c1315)

NoteAug 8huggingface.co/Phips/4xHFA2kLUDVAESwinIR_light

Source context: 0 downloads · 0 likes · Pipeline image-to-image · Repo Phips/4xHFA2kLUDVAESwinIR_light