RIFE 4.25 (MLX)

Apple MLX port of Practical-RIFE 4.25 โ€” real-time video frame interpolation on Apple Silicon. MIT.

First MLX/Apple-Silicon-native RIFE: torch-free inference, arbitrary-timestep interpolation, --multi Nx frame rate, --scale pyramid for 4K, audio-preserving video. Converted from the official RIFE 4.25 flownet.pkl (Google-Drive-only upstream) to fp32 safetensors.

Usage

pip install rife-mlx   # https://github.com/xocialize/rife-mlx
rife-mlx -i input.mp4 -o out.mp4 --multi 2          # 2x fps, keep audio
rife-mlx --img0 a.png --img1 b.png -t 0.5 -o mid.png
from rife_mlx.utils.weights import build_model
from rife_mlx.pipeline_mlx import interpolate_pair
model = build_model("4.25")                    # auto-downloads this repo
mid = interpolate_pair(model, frame_a, frame_b, 0.5) # HWC uint8

Details

  • Architecture: IFNet (5 coarse-to-fine IFBlocks c=[192,128,96,64,32], LeakyReLU, ResConv+beta, Head encoder, ConvTranspose+PixelShuffle).
  • Precision: fp32 (~23 MB) โ€” RIFE's coarse-to-fine flow is fp16-sensitive.
  • Parity vs PyTorch (CPU fp32): warp 2.2e-6 ยท interp 1.2e-7 ยท full IFNet 1.43e-3.

License

MIT (upstream Practical-RIFE, ยฉ hzwer). Weights are the official RIFE 4.25 release, converted to MLX.

Downloads last month
1,120
Safetensors
Model size
5.66M params
Tensor type
F32
ยท
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support