Selur's Little Message Board

Selur's Little Message Board > Talk, Talk, Talk > Small Talk > vscodeformer
Full Version: vscodeformer
You're currently viewing a stripped down version of our content. View the full version with proper formatting.

Selur

01.04.2023, 12:57
Did some small tests with https://github.com/HolyWu/vs-codeformer.
https://imgsli.com/MTY2MTM5
Suzie: https://imgsli.com/MTY2MTQz
Suzie with weight=1: https://imgsli.com/MTY2MjEw
https://imgsli.com/MTY2MTQ0
https://imgsli.com/MTY2MTQ2
https://imgsli.com/MTY2MTQ3
https://imgsli.com/MTY2MTQ5
https://imgsli.com/MTY2MTUy
seems more like a gimmick filter than really usable atm., but its impressive.
=> not planning to include it in the torch package, atm.

Cu Selur

Selur

02.04.2023, 11:51
Did some further testing and if upscale is > 1 and the upscaling is later undone it basically can be used as a 'face detail enhancer' which might be interesting.
Also in combination with FeMaSR it can be used to fix the face distortions FeMaSR does.
[Image: grafik.png][Image: grafik.png][Image: grafik.png]
=> I'll add it to the torch-addon. Smile
SwinIRx4+vsCodeFormer: https://imgsli.com/MTY2NDA3, looks nice frame-by-frame, but isn't really temporally stable => adding 3xQTGMC_type3 seems more stable and all in all a nice result in my book.

Cu Selur

Ps.: got a nice example why, weight=0 usually shouldn't be used: https://imgsli.com/MTY2NDI2
Selur's Little Message Board > Talk, Talk, Talk > Small Talk > vscodeformer