Skip to main content

photo-s-plugin-scunet — PhotoS 官方 SCUNet 强降噪插件

PhotoS 官方可选插件:基于 SCUNet(ONNX,onnxruntime)的高强度降噪, 适用于高 ISO / 弱光照片。比核心内置的 OpenCV NLM 降噪更强(恢复更多纹理)。

安装

# 方式一(推荐,agent 友好):PhotoS 插件管理器
photo-s plugin install scunet

# 方式二:传统 pip
pip install photo-s-plugin-scunet

# 查看状态
photo-s plugin list
photo-s plugin info scunet

使用

安装后,--denoise N 自动优先使用本插件(未装本插件时回退到内置 NLM):

photo-s batch ~/highiso/ --denoise 12

强度语义:SCUNet 是固定噪声级盲降噪模型,N 映射为原始图与全量降噪 输出的线性混合 t = clip(N/15, 0, 1)——N=0 原图不动,N>=15 全量 模型输出,中间线性过渡(与核心 NLM 的 ~3-20 有效区间手感一致)。

模型权重

使用 SCUNet 彩色降噪 (noise-25) 检查点,由官方 cszn/SCUNet PyTorch 权重 重新导出为 ONNX(保留上游 MIT 许可),托管于 HuggingFace Heliosoph/scunet-onnx

权重不进 wheel,首次使用时自动下载到缓存目录 (~/.cache/photo-s/models/,可用 $PHOTOS_CACHE_DIR 覆盖),带 sha256 校验。 SCUNet 导出为 external-data 格式:图 (.onnx,~3.8MB) 与权重 (.onnx.data,~73MB) 两个文件都要下载;两者保持规范文件名以便 onnxruntime 解析。可预下载:

photo-s plugin fetch scunet

默认指向社区 HF 镜像。如需第一方托管,可把两个文件重新挂到自己的 GitHub Release 并更新 photo_s_plugin_scunet/__init__.py 中的 DEFAULT_MODEL_URL/_SHA256/_SIZEDEFAULT_DATA_* 常量 (或保留 PHOTOS_SCUNET_MODEL_* 环境变量覆盖,测试即用此机制)。

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

photo_s_plugin_scunet-0.2.0.tar.gz (5.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

photo_s_plugin_scunet-0.2.0-py3-none-any.whl (5.8 kB view details)

Uploaded Python 3

File details

Details for the file photo_s_plugin_scunet-0.2.0.tar.gz.

File metadata

  • Download URL: photo_s_plugin_scunet-0.2.0.tar.gz
  • Upload date:
  • Size: 5.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for photo_s_plugin_scunet-0.2.0.tar.gz
Algorithm Hash digest
SHA256 630227807def762b0f4c9557447fa5d29a652db048ef7a28a37ea5e52ab4ba52
MD5 333a364df8c4bdab099f4815be1fbd77
BLAKE2b-256 69be0e859535d07eb7d5b3f517e11e2d0182507474f3d003e91f783941d4f90f

See more details on using hashes here.

Provenance

The following attestation bundles were made for photo_s_plugin_scunet-0.2.0.tar.gz:

Publisher: publish.yml on Dongwu259/photo_s

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file photo_s_plugin_scunet-0.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for photo_s_plugin_scunet-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 051df5d5f9fab182fb51afa1eb1fa03c18303855674393f852999aec1c756738
MD5 b9bf66451bec36f2fddaef52701cad1b
BLAKE2b-256 6b6c7f50484af092d655089985e740e40ec103ba2c9e477270fcc87bd80ac83b

See more details on using hashes here.

Provenance

The following attestation bundles were made for photo_s_plugin_scunet-0.2.0-py3-none-any.whl:

Publisher: publish.yml on Dongwu259/photo_s

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page