Real ESRGAN General X4v3
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).
Modellquelle
- Art
- Other
- Dateigröße
- 2,32 MB
- Version
- vRevision e9a382f
- Aktualisiert
- 9. Okt. 2026
- Downloads
- 142
- Quelle
- Hugging Face
Quellenbeschreibung
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.).
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 9. Okt.
Download files
Modellartefakte
2 Artefakte
Modellartefakte
2 ArtefakteQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- license: bsd-3-clause library_name: mlx pipeline_tag: image-to-image tags: - mlx - super-resolution - real-esrgan - image-to-image - apple-silicon --- # 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](https://github.com/xinntao/Real-ESRGAN) release checkpoint (BSD-3-Clause). ## Usage ```bash pip install realesrgan-mlx # https://github.com/xocialize/realesrgan-mlx realesrgan-mlx -i input.png -o out/ -n realesr-general-x4v3 ``` ```python 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)` blends `s*model + (1-s)*wdn` (`1.0` keeps detail, `0.0` = max denoise). ## License BSD-3-Clause (upstream Real-ESRGAN, Xintao Wang et al.).
Source context: 142 downloads · 1 likes · Pipeline image-to-image · Library mlx · Repo mlx-community/Real-ESRGAN-general-x4v3
Source context: 61 downloads · 1 likes · Pipeline image-to-image · Library mlx · Repo mlx-community/Real-ESRGAN-general-x4v3
