FlowDownTheRiver

Also thanks for the zits model and updates(redo functionality is great I loved it),I forgot to say :)

Also about --upsample_num_times parameter can it be possible to detect an avarage face size so it can be automated? For example if there is only 1 face in the image...

Thank you very much. I hope it all goes well. Will be waiting for the improvements.

@sczhou Thank you very much for the time you have spent on implementing new models,I have checked yolo,didn't have time to test retina face yet but I will test both...

I was able to test yolo and retina face. In my tests I found retina gave me most consistent results.Especially when the faces roll to left or right yolo detection...

[Codeformer Direct Input and Output.zip](https://github.com/sczhou/CodeFormer/files/9300139/Codeformer.Direct.Input.and.Output.zip) @sczhou As an appreciation and a python beginner,I have made an alternative inference which is directly outputing final result without any extras with bat files...

@caacoe My personel preference is retina face detector as well. Yolo is missing some faces with some yaw direction and in some cases if the face is large at the...

Original Image  Codeformer 2x with w=1  Gfpgan 2x v2 model  Gfpgan 2x v3 model  Gpen 2x 256 model  Gpen 2x 512 model  The reason...

> @FlowDownTheRiver well noted, I could try to make it in these few days, but I can't make sure since I've been on another project recently. Please take your time,no...

> Hi @FlowDownTheRiver @caacoe, the repo has updated: > > * Switch 'retinaface_resnet50' as the default face detection model. > > * Fix the issue of bounding box lines in...