OpenToolbox

Free Video FPS Increaser

Video FPS Increaser raises the frame rate 2×, 3× or 4×, or to 60 or 120 fps, with RIFE AI frame interpolation, or turns the new frames into slow motion. Frames across detected scene cuts are repeated instead of morphed, and the sound keeps its pitch. Motion and Blend are faster non-AI methods for devices without WebGPU.

Targets:
2×, 3×, 4×, 60 or 120 fps
Input:
Up to 2 minutes and 1080p
Methods:
AI (RIFE), Motion or Blend
Price:
Free
Runs:
AI model in your browser
Uploads:
None: files never leave your device
Account:
Not needed

Quick answers

Is my video uploaded?

No. The AI model is downloaded once from Hugging Face and runs in your browser; the video never leaves your device.

Does the video get longer?

Not with Same speed: the new frames are placed between the original ones, so length, speed and sound stay the same. Slow motion plays the new frames at the original rate, so the clip becomes 2 to 4 times longer and the sound is slowed down with its pitch kept.

Loading tool…

Processed on your device: your files are never uploaded. How it works

How to use the Video FPS Increaser

  1. Drop a short video (up to 2 minutes and 1080p).
  2. Pick the new frame rate (2×, 3×, 4×, 60 or 120 fps) and whether to keep the speed or make slow motion.
  3. Move the slider to a moment with motion and press Preview to see one generated frame between two originals.
  4. Press Convert: the frames are generated on your device with a progress bar, then play and download the MP4.

Credits & open source

Open-source AI model running in your browser. Thank you to the people who make these projects.

  • ONNX Runtime WebExecutes ONNX models with WebGPU or WebAssembly (self-hosted from /vendor/ort). © Microsoft Corporation · MIT
  • MediabunnyReads, writes and converts media files with WebCodecs (MP4, WebM, MKV, MOV, MP3, WAV, Ogg...). © Vanilagy and contributors · MPL-2.0

Web platform APIs used: Web Workers, WebAssembly, WebGPU, WebCodecs, OffscreenCanvas, Canvas 2D, File API.

  • RIFE v4.9 (ONNX) by Zhewei Huang, Tianyuan Zhang, Wen Heng, Boxin Shi, Shuchang Zhou (Megvii Research, Practical-RIFE weights by hzwer); ONNX export by FuryTMP (MIT) — AI frame interpolation

Full license texts: third-party notices · all credits

Frequently asked questions

What happens at scene cuts?

Cuts are detected and the frames around them are repeated instead of blended, so two different shots are never morphed into each other. You can change the sensitivity or turn the detection off.

Why does fast motion look wobbly?

Interpolation guesses the motion between two frames. Very fast movement, motion blur, flashing lights or objects passing in front of each other can produce warped edges; a higher original frame rate gives better results.

Can it run without a graphics card?

Yes, but RIFE on the processor takes seconds per frame. The Motion and Blend methods are classic, non-AI alternatives that are fast everywhere.

More video tools