Run RIFE
Ready in about 90 seconds. No install, no setup. From $0.45 per hour.
What it does
RIFE invents the frames in between the frames you already have. Double the frame rate and motion becomes smoother. Multiply it by eight and you get slow motion that looks like it was shot that way.
It also fixes footage shot at the wrong frame rate for its destination, which is a common problem when phone video ends up in a broadcast timeline.
It runs quickly and it batches, so a folder of clips is one job rather than one job per clip.
What you can make
These are prompts, not fixed presets. The workspace opens with one of them already loaded so your first result is one click away.
Your setup
We run this on an RTX 4090. It generates about 40 new 1080p frames per second, so a minute of footage doubled in frame rate takes roughly 45 seconds. $0.45 per hour, billed by the minute.
Why this card?
RIFE is a small model, so memory is not the constraint. What matters is how fast the card can hold two full frames, compare them, and write a third. At 4K that is a lot of data moving per frame, and the RTX 4090 has roughly double the memory bandwidth of the cheaper cards, which shows up almost one-for-one in how long your job takes.
- Memory
- 24GB
- Speed
- about 45 seconds per minute of footage
- Rate
- $0.45/hr
What will it cost you?
Billed by the minute on a RTX 4090 at $0.45 per hour. A batch job shuts the GPU off when the last minute of footage is done, so this is the whole cost.
Two ways to run it
Click and use it
Upload one clip, pick a multiplier, watch the preview before committing.
Get early access Best for exploring.Hand us the whole pile
Drop in a folder of clips with one setting and collect them all processed.
Join the list Best for volume. The GPU shuts off automatically when it is done.Model facts
| Parameters | 10M |
|---|---|
| License | MIT |
| Memory required | 6GB minimum |
| Base model | Trained from scratch |
| Publisher | Megvii Research |
| Recommended hardware | RTX 4090, 24GB |
| Hugging Face | hzwer/RIFE |
Want RIFE the day it opens?
We are testing the rental flow with a small group first. Leave an email and we will tell you when RIFE is ready to run. One message, no newsletter.
RIFE questions
Do I need to install anything to use RIFE?
No. We start a machine with RIFE already loaded and hand you a link. Everything runs in your browser, there is nothing to download, and nothing is left on your computer afterwards. It works the same on a Mac, a Windows laptop, or a Chromebook. A workspace is usually ready in about 90 seconds.
How much does it cost to run 60 minutes of footage?
About $0.34. RIFE takes about 45 seconds per minute of footage on the RTX 4090 we recommend, so 60 minutes of footage is roughly 45 minutes of GPU time at $0.45 per hour. Billing is by the minute, and a batch job shuts the GPU off the moment the last item finishes. The calculator above works this out for your own numbers.
Can I run RIFE on a cheaper card?
Sometimes, and the calculator will not always make it look worth it. RIFE is a small model, so memory is not the constraint. What matters is how fast the card can hold two full frames, compare them, and write a third. At 4K that is a lot of data moving per frame, and the RTX 4090 has roughly double the memory bandwidth of the cheaper cards, which shows up almost one-for-one in how long your job takes. If you want to try a different card anyway, the advanced catalog lets you pick one and shows the estimated time before you commit.
Can I use RIFE commercially?
Yes. RIFE is released under the MIT license, which permits commercial use with no conditions worth worrying about. You can use the output in paid client work and in products you sell.
What happens to my files after I stop?
Anything you save into your workspace folder stays in your account and is there when you come back. Everything else is destroyed: the machine is terminated and its disk is wiped. Batch job inputs and outputs are deleted from our storage 24 hours after you download them. We do not read your files or use them to train anything.
What if it fails partway through?
You are not charged for work that did not complete, and failed sessions are refunded automatically. Batch jobs write each output as it finishes rather than at the end, so a failure at item 380 of 400 leaves you 379 usable files and a message saying what broke. Restarting picks up where it stopped rather than redoing the work.
Own a GPU that sits idle? Put it to work. The average provider earns $180 to $420 per month per card.
List your GPU