-
Notifications
You must be signed in to change notification settings - Fork 5
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
this isn't an actual issue, I'm just wondering about something. #7
Comments
Forgive me for not having the energy to see this issus, I'm not sure to what extent “a specified framerate” is a problem, but GMFSS is not capable of implementing any framerate, and we need to revisit this point. |
Basically back in march I had found this program called svfi on steam that has the options of gmfss or other interpolation models. This program does what enhancr doesn't provide, an option for fps ratio. In my case I can set it to interpolate to 120fps for ultra smooth scenes with low or no jitter. Svfi also has scene detection with options for what to do at scene changes. I'd personally like to work with a coder to train a gmfss model for anime like I said and also code in multiple options for dealing with scene changes (which I think python may be able to do but idk since I don't code), like an option to blend between frames in the way that topaz does with its models. I don't know what happens in the background code that runs when I set the option there to use an fps ratio instead of simply x2, x3, x4, x5 (119fps if source file is 23.976fps), etc. |
SVFI, smh, finally got it! |
basically I want to create a custom anime interpolation program that's based on gmfss fortuna (but custom trained on various anime scenes so the visuals look correct and retain their original forms) and also handles scene changes correctly. I use enhancr for gmfss fortuna but it doesn't let me interpolate to a specified framerate, and topaz video ai's chronos model. I'm hoping you could make this program with me and I could tell you know I want it built. you can close this issue if it's out of line or whatevever, I'm just not sure where to ask this question.
The text was updated successfully, but these errors were encountered: