| --- |
| license: mit |
| library_name: mlx |
| pipeline_tag: video-to-video |
| tags: |
| - mlx |
| - frame-interpolation |
| - video-frame-interpolation |
| - rife |
| - apple-silicon |
| --- |
| |
| # RIFE 4.25 (MLX) |
|
|
| Apple **MLX** port of [Practical-RIFE](https://github.com/hzwer/Practical-RIFE) |
| **4.25** — 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 |
|
|
| ```bash |
| 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 |
| ``` |
|
|
| ```python |
| 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) — RIFE's coarse-to-fine flow is fp16-sensitive. |
| - **Parity vs PyTorch (CPU fp32)**: warp 2.2e-6 · interp 1.2e-7 · full IFNet 1.43e-3. |
|
|
| ## License |
|
|
| MIT (upstream Practical-RIFE, © hzwer). Weights are the official RIFE 4.25 |
| release, converted to MLX. |
|
|
