note: see this issue before downloading
- batch processing
- supports most image formats
- before/after view
- fully offline
this is not a "super resolution AI upscaler", but simple non-destructive method for cleaning up/restoring images
FBCNN (JPEG compression)
SCUNet (Grain/Noise)
info here (also in the apps FAQ)
you can also run other experimental models, more info here
- processed locally, minimum 4gb ram and 4 threads recommended
- limited to images below 8000 pixels, and images above 4000px will affect performance
see the wiki for more information
the desktop version was deprecated and lacking many features, please use chaiNNer
DeJPEG is not affiliated or related with Topaz DEJPEG or any other similarly named software/project.
this app stems from personal uses and was modified for public release
@adrianerrea for the base application, FBCNN and SCUNet creators plus all other model creators.
this is a GUI wrapper for a select amount of 1x ONNX image processing models
all models used are under their respective licenses
you are free to embed parts of this app in your own project as long as it remains free/non-paywalled and must abide to the GPL v3 license