---
title: EfRLFN-x4
canonical_url: "https://www.modelscope.cn/models/mlx-community/EfRLFN-x4"
md_url: "https://www.modelscope.cn/models/mlx-community/EfRLFN-x4.md"
repository: mlx-community/EfRLFN-x4
last_updated: 2026-06-04
license: mit
pipeline_tag: image-to-image
tasks:
  - image-to-image
base_model:
  - EvgeneyBogatyrev/EfRLFN
base_model_relation: finetune
parameters: 503894
tensor_type:
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 9
stars: 0
tags:
  - mlx
  - super-resolution
  - efrlfn
---

# EfRLFN-x4

> EfRLFN-x4 - mlx-community 在 ModelScope 开源的模型。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).

mlx-community/EfRLFN-x4 是 ModelScope 魔搭社区上的 503894 参数image-to-image模型，采用 mit 许可，基于 EvgeneyBogatyrev/EfRLFN 构建。

- **Repository**: mlx-community/EfRLFN-x4
- **License**: mit
- **Tasks**: image-to-image
- **Parameters**: 503894
- **Base model**: EvgeneyBogatyrev/EfRLFN
- **Tags**: mlx, super-resolution, efrlfn
- **Downloads**: 9
- **Stars**: 0
- **Last updated**: 2026-06-04

Source: https://www.modelscope.cn/models/mlx-community/EfRLFN-x4

---

# EfRLFN x4 (MLX)
Apple MLX port of [EfRLFN](https://github.com/EvgeneyBogatyrev/EfRLFN) (ICLR 2026), x4 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.x4())
upscale_to_file(m, "lr.png", "sr.png")
```
MIT, derived from EvgeneyBogatyrev/EfRLFN.