simple workflow to do the post processing for mainly videos.
since i get many OOM. in some parts of the video generations. i split the post processing to avoid this problem.
any content of this workflows dont require checkpoint models. only his own models like rife49 for interpolation. etc.etc.etc.
v1.05 - requires now my own custom nodes to solve some issues from now on
shirosaki33/shiroaudio: custom nodes for comfy, related to audio
v1.055 - experimental tools
shirosaki33/shirotools: many utility tools made for different situations
the image process is just a extra.
you can do by single file or batch path in both.
Description
Layout reorganized.
Cozy voice added.
Trim frame crop added (new cropping logic).
Anti-flicker added. Does the same thing as color match, but in a different way.
Final sharpener added. It mainly serves to improve the final upscale result of cartoons/anime. If it's a bit blurry, this tends to resolve that somewhat.
After-upscale features. These are copies of some previous content that can be reused to correct some details.
New audio switch logic. The system now automatically switches to the chosen audio. You need to download my custom nodes for this to work. Link in the main model.