Downloads · 30 days
170
36% of all-time downloads
Real-ESRGAN-general-x4v3
mlx-community/Real-ESRGAN-general-x4v3
Real-ESRGAN-general-x4v3 is a image-to-image model from mlx-community. Use it when you need one image transformed into another. It is set up for mlx. The card lists the license as bsd-3-clause.
Apple MLX fp16 port of Real-ESRGAN realesr-general-x4v3 (SRVGGNetCompact, ×4), for super-resolution on Apple Silicon. Converted from the official xinntao/Real-ESRGAN release checkpoint (BSD-3-Clause).
All-time downloads
472
Public
Parameters
1.2M
4.9 MB on disk
Likes
2
Trending 1
Repo makeup
Click a slice to open those files.
.safetensors4.9 MB · 100%
At a glance
- Task
- Image-to-Image
- Library
- mlx
- License
- bsd-3-clause
- Access
- Public
- Created
- Jun 6, 2026
- Updated
- Jun 6, 2026
- SHA
- e9a382fa
Model card
From the Hugging Face model README
Real-ESRGAN-general-x4v3 (MLX)
Apple MLX fp16 port of Real-ESRGAN realesr-general-x4v3 (SRVGGNetCompact, ×4), for super-resolution on Apple Silicon. Converted from the official xinntao/Real-ESRGAN release checkpoint (BSD-3-Clause).
Usage
pip install realesrgan-mlx # https://github.com/xocialize/realesrgan-mlx
realesrgan-mlx -i input.png -o out/ -n realesr-general-x4v3
from realesrgan_mlx.pipeline_mlx import make_upsampler, upscale_image
up = make_upsampler("realesr-general-x4v3", tile=256) # tile>0 caps memory on large images
out = upscale_image("input.png", up)
make_upsampler downloads these weights automatically.
Details
- Architecture: SRVGGNetCompact (
num_feat=64,num_conv=32,act=prelu) - Scale: ×4 · Precision: fp16
- Parity vs PyTorch: full-forward 4.1e-6 (CPU fp32); fp16 vs fp32 golden 2.0e-3.
- Denoise strength: this model ships with a paired
model_wdn.safetensors;build_model(..., denoise_strength=s)blendss*model + (1-s)*wdn(1.0keeps detail,0.0= max denoise).
License
BSD-3-Clause (upstream Real-ESRGAN, Xintao Wang et al.).
- Task
- Image-to-Image
- Library
- mlx
- License
- bsd-3-clause
- Created
- Jun 6, 2026
- Updated
- Jun 6, 2026