chaiNNer
Image Processing Unit
https://chainner.app/
- NMKD Superscale
4x
ESRGAN
Purpose: Clean Real-World Images
Upscaling of realistic images/photos with noise and compression artifacts
https://openmodeldb.info/models/4x-NMKD-Superscale - SPANkendata
4x
SPAN
Purpose: Intended as a pretrain model, can be used to upscale undegraded photos.
4x realistic upscaler that may also work for general purpose usage. Trained on Bicubic downscaled tiles from very high quality images.
https://openmodeldb.info/models/4x-SPANkendata - 4xNomos8kSCHAT-L
4x
HAT
4x photo upscaler with otf jpg compression and blur, trained on musl's Nomos8k_sfw dataset for realisic sr. Since this is a big model, upscaling might take a while.
https://openmodeldb.info/models/4x-Nomos8kSCHAT-L - realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN
4x
?
SwinIR achieves state-of-the-art performance in
bicubic/lighweight/real-world image SR
grayscale/color image denoising
grayscale/color JPEG compression artifact reduction
https://github.com/JingyunLiang/SwinIR/ - Real_HAT_GAN_sharper
?
HAT
?
https://drive.google.com/drive/folders/1HpmReFfoUqUbnAOQ7rvOeNU3uf_m69w0 - UltraSharp
4x
ESRGAN
It generates lots and lots of detail and leaves a nice texture on images. It works on most images, whether compressed or not. It does work best on JPEG compression though, as that's mostly what it was trained on. It has the ability to restore highly compressed images as well!
https://openmodeldb.info/models/4x-UltraSharp - 4xPurePhoto-RealPLSKR
4x
RealPLKSR
Skilled in working with cats, hair, parties, and creating clear images. Also proficient in resizing photos and enlarging large, sharp images. Can effectively improve images from small sizes as well (300px at smallest on one side, depending on the subject). Experienced in experimenting with techniques like upscaling with this model twice and then reducing it by 50% to enhance details, especially in features like hair or animals.
https://openmodeldb.info/models/4x-PurePhoto-RealPLSKR - 4xNomos2_hq_drct-l
4x
DRCT
Purpose: Upscaler
Subject: Photography
https://openmodeldb.info/models/4x-Nomos2-hq-drct-l
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.