Skip to content
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

adaptive motion frequency #12

Open
sbaier1 opened this issue Oct 20, 2022 · 0 comments
Open

adaptive motion frequency #12

sbaier1 opened this issue Oct 20, 2022 · 0 comments

Comments

@sbaier1
Copy link
Owner

sbaier1 commented Oct 20, 2022

It would be great to have the ability to "slow down" the motion in an animation by reducing the frames per second artifically (while still generating the expected amount of frames).

ideas:

reducing framerate situationally

i think this is already possible, needs a test scenario. just set all motion inducing parameters to 0 on the frames that should be stills, i.e.: strength should be 1, animation axes should be all 0

interpolated smoother but slow motion frequency:

  • add a new schedulable field interpolated_frames that defines how many steps are skipped variably at whatever point in time
  • whenever it's > 0: skip generating an entire new frame, instead:
    • if there's a video init, just skip until the next actual frame after skipping and interpolate towards that frame
    • if there's no video init, but animation is used:
      • get all the transform matrices for the intermediate steps and sum them up
      • transform current frame with the resulting matrix
      • interpolate towards that frame for however many frames will be skipped

interpolating in this case means: for a first implementation, just run rife-ncnn-vulkan directly to generate the intermediate frames.

could also be used to directly generate higher framerates, although probably with a huge perforamnce penalty if the model gets loaded for all the individual intermediate frames.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant