EfRLFN MLX
Collection
MLX port of EfRLFN (ICLR 2026): realtime x2/x4 image super-resolution on Apple Silicon. • 2 items • Updated
EfRLFN x4 (MLX)
Apple MLX port of EfRLFN (ICLR 2026), x4 super-resolution. PT-vs-MLX parity ~1e-6. Realtime on Apple Silicon (270x480 -> 1080x1920 ~0.06s for x4).
from efrlfn_mlx import EfRLFNConfig
from efrlfn_mlx.pipeline import load_model, upscale_to_file
m = load_model("model.safetensors", EfRLFNConfig.x4())
upscale_to_file(m, "lr.png", "sr.png")
MIT, derived from EvgeneyBogatyrev/EfRLFN.
- Downloads last month
- -
Model size
504k params
Tensor type
F32
·
Hardware compatibility
Log In to add your hardware
Quantized
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir EfRLFN-x4 mlx-community/EfRLFN-x4