Instructions to use mlx-community/EfRLFN-x2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/EfRLFN-x2 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir EfRLFN-x2 mlx-community/EfRLFN-x2
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| license: mit | |
| library_name: mlx | |
| pipeline_tag: image-to-image | |
| tags: [mlx, super-resolution, efrlfn] | |
| base_model: EvgeneyBogatyrev/EfRLFN | |
| # EfRLFN x2 (MLX) | |
| Apple MLX port of [EfRLFN](https://github.com/EvgeneyBogatyrev/EfRLFN) (ICLR 2026), x2 super-resolution. | |
| PT-vs-MLX parity ~1e-6. Realtime on Apple Silicon (270x480 -> 1080x1920 ~0.06s for x4). | |
| ```python | |
| from efrlfn_mlx import EfRLFNConfig | |
| from efrlfn_mlx.pipeline import load_model, upscale_to_file | |
| m = load_model("model.safetensors", EfRLFNConfig.x2()) | |
| upscale_to_file(m, "lr.png", "sr.png") | |
| ``` | |
| MIT, derived from EvgeneyBogatyrev/EfRLFN. | |