|
|
--- |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
chaiNNer<br> |
|
|
Image Processing Unit<br> |
|
|
https://chainner.app/<br><br> |
|
|
|
|
|
1. NMKD Superscale<br> |
|
|
4x<br> |
|
|
ESRGAN<br> |
|
|
Purpose: Clean Real-World Images<br> |
|
|
Upscaling of realistic images/photos with noise and compression artifacts<br> |
|
|
https://openmodeldb.info/models/4x-NMKD-Superscale<br> |
|
|
2. SPANkendata<br> |
|
|
4x<br> |
|
|
SPAN<br> |
|
|
Purpose: Intended as a pretrain model, can be used to upscale undegraded photos.<br> |
|
|
4x realistic upscaler that may also work for general purpose usage. Trained on Bicubic downscaled tiles from very high quality images.<br> |
|
|
https://openmodeldb.info/models/4x-SPANkendata<br> |
|
|
3. 4xNomos8kSCHAT-L<br> |
|
|
4x<br> |
|
|
HAT<br> |
|
|
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.<br> |
|
|
https://openmodeldb.info/models/4x-Nomos8kSCHAT-L<br> |
|
|
4. realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN<br> |
|
|
4x<br> |
|
|
?<br> |
|
|
SwinIR achieves state-of-the-art performance in<br> |
|
|
bicubic/lighweight/real-world image SR<br> |
|
|
grayscale/color image denoising<br> |
|
|
grayscale/color JPEG compression artifact reduction<br> |
|
|
https://github.com/JingyunLiang/SwinIR/<br> |
|
|
5. Real_HAT_GAN_sharper<br> |
|
|
?<br> |
|
|
HAT<br> |
|
|
?<br> |
|
|
https://drive.google.com/drive/folders/1HpmReFfoUqUbnAOQ7rvOeNU3uf_m69w0<br> |
|
|
6. UltraSharp<br> |
|
|
4x<br> |
|
|
ESRGAN<br> |
|
|
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!<br> |
|
|
https://openmodeldb.info/models/4x-UltraSharp<br> |
|
|
7. 4xPurePhoto-RealPLSKR<br> |
|
|
4x<br> |
|
|
RealPLKSR<br> |
|
|
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.<br> |
|
|
https://openmodeldb.info/models/4x-PurePhoto-RealPLSKR<br> |
|
|
8. 4xNomos2_hq_drct-l<br> |
|
|
4x<br> |
|
|
DRCT<br> |
|
|
Purpose: Upscaler<br> |
|
|
Subject: Photography<br> |
|
|
https://openmodeldb.info/models/4x-Nomos2-hq-drct-l<br> |
