hzwer / hzwer/Practical-RIFE

--Montage feature doesn't work correctly (maybe just with --fps=60?)

Open
#142 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1k
Forks
131
PR merge metrics
No merged PRs in 30d

Description

My expectation on the --montage flag would be to see the original untouched video on (I'm guessing the left side), but, regardless of side, both images in the video have blurry interpolation when I advance frame by frame. I would expect the original side to just repeat the same original frame to match the new FPS, and the other side to have been processed with RIFE.

I did use --fps=60 as my only other flag, and maybe my expectation on how it should work is just incorrect. There was a warning about audio being unavailable, but not montage.

This is my first look at AI anything, so I appreciate all that you've done. Your work is totally fascinating. Thank you. I'm so used to installing software and it just not working (For example, installing Cuda took 6 hours of problem solving with various workarounds required, and after all that pytorch still doesn't see it), and the unbundled nature of Python source files had me worried I would be wasting my time. Amazingly, it just worked problem free.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the reported command using --montage with --fps=60, then advance through the output frame by frame to compare both sides with the expected original and RIFE-processed video. Determine whether the behavior is an implementation problem or an incorrect expectation, and consider the audio-unavailable warning separately. Done means the montage behavior is correct or its documented behavior is clarified.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
cli, computer-vision
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.