Inquiry about issues with 60fps video interpolation in long videos, duration and audio sincronization
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1k
- Forks
- 131
- PR merge metrics
- No merged PRs in 30d
Description
Dear hzwer,
First of all, I want to congratulate you on the amazing work you've done with the RIFE repository. The quality of the video interpolation is impressive and has been incredibly useful for several of my projects.
However, I've encountered some issues when working with long videos. While RIFE successfully converts videos to 60fps, I've noticed that the duration of the video doesn't remain the same, and even when I try to fix this using setpts in FFmpeg, the audio is not properly synchronized. I'm currently using Model 4.25, and I was wondering if you could recommend a different model that might handle these cases better.
Additionally, I wanted to ask if there's a way to use multiple GPUs when running RIFE. Right now, I can only use one GPU, and I'd love to take advantage of multiple GPUs to improve performance, especially when working with long videos.
I really appreciate your attention and any suggestions you might have. Thanks again for your incredible work!
Best regards,
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no files, tests, or entry points. Start by reproducing long-video interpolation with Model 4.25 and the reported FFmpeg duration and audio-sync problems; separately investigate the request for multi-GPU support. Done would require a confirmed diagnosis and clearly scoped changes, but the stale thread provides no settled implementation path.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100