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/_SIZE 与 DEFAULT_DATA_* 常量 (或保留 PHOTOS_SCUNET_MODEL_* 环境变量覆盖,测试即用此机制)。

Release files for photo-s-plugin-scunet 0.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for photo-s-plugin-scunet 0.3.0
File Size Uploaded
photo_s_plugin_scunet-0.3.0.tar.gz 7.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for photo-s-plugin-scunet 0.3.0
File Interpreter ABI Platform
photo_s_plugin_scunet-0.3.0-py3-none-any.whl Python 3 none any Details

Total release size: 14.6 kB

Release files / photo_s_plugin_scunet-0.3.0.tar.gz

Download URL photo_s_plugin_scunet-0.3.0.tar.gz
Size 7.0 kB
Tags Source
SHA-256 checksum
How to use checksums
1428f77a1c725691588617a67da5aa8d68794021b557789f425638f27e8fa8f0
BLAKE2b-256 checksum
How to use checksums
41bd6a986d077b9360b5e34041a6f59170d7ad91c7aabf75c3266a9b94667440
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 14, 2026.

Transparency log

Release files / photo_s_plugin_scunet-0.3.0-py3-none-any.whl

Download URL photo_s_plugin_scunet-0.3.0-py3-none-any.whl
Size 7.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7252dac4bdaa24514bc631f31f3331204c8da62e94f971fe9c8142202a6337ae
BLAKE2b-256 checksum
How to use checksums
53f4a7d2b0b8d5f5f36a9448da3e26a0c42d7880bd8d7a1b0491abbdedbd6023
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 14, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.3.0 This release

2 release files

0.2.0

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page