hzwer / hzwer/Practical-RIFE

What CPU w/ a 4080 Super to Interpolate Anime to 120fps Quicker?

Open
#91 1 comment 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

I'm currently using a AMD Ryzen 5 7600 with a 4080super, if i want to SVP rife ai interpolate using 4.18v2 faster with more detail by transcoding rather than plying in real time, which cpu should I get? If I use slow mode, it uses like 75% gpu 100% cpu, and takes about 40-60 minutes to interpolate 1080@24-->1080@120. When realtime interpolating, which i assume uses the equivalent to fast mode in the transcoding section, uses 100%gpu and 60%cpu when realtime interpolating from 1080@24-->1080@120. I bought all the parts to this pc for the purpose of ai frame interpolating anime, so I'd have a budget of probably like $450 for the cpu. If the cpu would be fast enough to interpolate to 120fps on slow mode, would there be a setting I could change in SVP so that I could real time have the more detailed and smoother interpolation?

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

No source file, test, or entry point is named. Start by tracing how RIFE 4.18v2 handles slow and real-time interpolation, then verify whether CPU selection or an SVP setting can change the quality and throughput; done would require a supported, evidence-based answer for the stated hardware and modes.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.