Ir para o conteúdo
ModelListadosExterno
Browse files

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).

TipoOtherVersãoRevision e9a382fBnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
2,32 MB
Versão
vRevision e9a382f
Atualizado
9 de out. de 2026
Downloads
142
Fonte
Hugging Face

Descrição da fonte

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) 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.).

Fontes

1 fonte
Hugging FacePrimárioVersão e9a382fa779f227abf65ad49d4e5b90c1202d683
huggingface.co/mlx-community/Real-ESRGAN-general-x4v3/tree/e9a382fa779f227abf65ad49d4e5b90c1202d683

Verificado 9 de out.

Download files

Artefatos de modelo

2 artefatos

model_wdn.safetensors

safetensors · 2,32 MB · SHA-256 f321fe29403f…89a8 · Hugging Face

Download file

model.safetensors

safetensors · 2,32 MB · SHA-256 86f4714b7420…4265 · Hugging Face

Download file

Trechos de fonte

3 trechos

--- 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