NotebookLM Cleaner v2.0

清掉导出文件角落那枚水印:五种格式在本页清,视频生成本地命令

Remove the corner watermark from your exports: five formats cleaned here, video via a local command

给自己生成的 NotebookLM / Gemini Notebook 导出文件去可见水印:图片、Gemini 图、PDF、PPTX、音频在本页内处理,文件不离开这台设备,全部处理代码都在页内、断网可用;视频生成 FFmpeg 命令在本机终端跑,同样不上传。

Remove the visible watermark from NotebookLM / Gemini Notebook exports you created yourself: images, Gemini images, PDF, PPTX and audio are processed on this page — files never leave this device, and all processing code lives in the page itself, so it works offline. Video generates an FFmpeg command to run in your local terminal, also with no upload.

视频是生成命令、不是页内处理:浏览器内跑 WASM 重编码太吃内存,本页按实查坐标生成 FFmpeg 命令,你在本机终端跑,文件同样不上传。 Video generates a command — it is not processed in-page: WASM re-encoding in the browser is too memory-heavy, so this page generates an FFmpeg command from verified coordinates for you to run in a local terminal. The file is not uploaded either.
Gemini 四角星默认是检测填充重建:算术恢复需要模板图,原站模板属原站资产、不能复用;v2 起你可以在 Gemini 标签页上传自己做的模板,走真正的 alpha 反推恢复。 The Gemini sparkle is rebuilt by detect-and-fill by default: arithmetic recovery needs a template image, and the original site's template is their asset. New in v2: upload a template you made yourself in the Gemini tab to run true alpha reversal.
图片 PNG · JPG · WebP 可直接清Images PNG · JPG · WebP cleaned directly Gemini 图 固定 48/96 区 · 可自建模板恢复Gemini images Fixed 48/96 area · bring your own template PDF 逐页重建为图像 PDFPDF Rebuilt page by page as image PDF PPTX 只改嵌入图片PPTX Only embedded images are changed 音频 末尾剪秒导出 WAVAudio Trim the end, export WAV 视频 生成 FFmpeg 命令本地跑Video Generates an FFmpeg command to run locally
把文件拖到这里,或点这里选择Drag a file here, or click to choose 一次一个文件 · 桌面建议 500 MB 以内、手机 100 MB 以内(超 500 MB 会拦下)· 先留一份原文件不动 One file at a time · Suggested max 500 MB on desktop, 100 MB on mobile (files over 500 MB are refused) · Keep an untouched copy of the original
处理库状态:Libraries: ZIP(页内自带)ZIP (built in) PDF 解析与重建(页内自带)PDF parse & rebuild (built in) 全部处理代码都在页内,不依赖 CDN,断网可用。All processing code ships in this page — no CDN, works offline.

图片清理设置Image cleanup settings

这一路处理普通图片与信息图右下角的水印;Gemini 原图的四角星请切到「Gemini 图」标签页,那边有固定尺寸与自建模板恢复。

This tab handles the bottom-right watermark on regular images and infographics. For the Gemini sparkle, switch to the “Gemini Image” tab — it has the fixed-size area and bring-your-own-template recovery.

原理:扫描右下角区域,以中位灰度为背景找偏离块,按连通域过滤掉噪点(面积 <20px)、细线(高 <8px)、边框线(长宽比 >12:1)与扫描框顶部四分之一内的块,同行块合并后外扩,再用矩形上下各 8px 条带的列平均做逐列垂直渐变填充。平面或渐变背景接近隐形;照片、纹理、图表线条下方会留一块平滑色块,属预期。

How it works: scan the bottom-right area, find blocks that deviate from the median-gray background, filter connected components — dropping noise (area <20px), thin lines (height <8px), border lines (aspect ratio >12:1) and anything in the top quarter of the scan box — merge same-row blocks, expand, then fill with a per-column vertical gradient averaged from 8px strips above and below. On flat or gradient backgrounds it is nearly invisible; over photos, textures or chart lines it will leave a smooth patch — that is expected.

清完必查三处(处理完就地对照)Three checks after cleaning (right here, before you leave)

完整参数表Full parameter table

参数来源:Skill muzi-notebooklm-cleaner,2026-11-22 实查;与页内实现逐项对照一致。

Source of parameters: the muzi-notebooklm-cleaner Skill, verified 2026-11-22; each row matches the in-page implementation.

格式Format关键参数Key parameters
视频 1080pVideo 1080pdelogo x=1104, y=656, w=770, h=62; 剪尾 2.5s;CRF 18trim end 2.5s; CRF 18
视频 720pVideo 720pdelogo x=736, y=437, w=513, h=41
PDF页内解析整页图片(DCT 直接取 JPEG、Flate 原始像素重绘);扫描框最小 350×80,大图至宽 22%·高 8%;阈值 80/60/45;连通域过滤(面积 ≥20、高 ≥8、长宽比 ≤12:1、排除顶部四分之一);外扩 +15/+8(PDF 标签页内可调);95% JPEG 逐页重建In-page parsing of full-page images (JPEG taken directly for DCT, raw pixels redrawn for Flate); scan box min 350×80, up to 22% W × 8% H on large images; thresholds 80/60/45; connected-component filtering (area ≥20, height ≥8, aspect ≤12:1, top quarter excluded); expansion +15/+8 (adjustable in the PDF tab); rebuilt page by page as 95% JPEG
PPTX页内 ZIP 读写只改 ppt/media/;PNG 无损、JPEG 0.95 写回Built-in ZIP read/write changes only ppt/media/; PNG lossless, JPEG written back at 0.95
图片检测Image detection与 PDF 同一检测器;外扩默认 15px(图片标签页内可调);填充取上下各 8px 条带列平均渐变Same detector as PDF; padding defaults to 15px (adjustable in the Image tab); fill is a per-column gradient from 8px strips above and below
Gemini 图Gemini images固定方块 48px(短边≤1024,边距 32)/ 96px(边距 64),不缩放;自建模板 alpha 反推,误差放大 α=0.8 时 5×、α=0.9 时 10×Fixed square 48px (short side ≤1024, margin 32) / 96px (margin 64), never scaled; alpha reversal with your own template; error amplification 5× at α=0.8, 10× at α=0.9
音频Audio末尾默认剪 5s、开头 0s;导出 WAV(多声道混为双声道,先提示);流复制命令 -c copy;MP3 帧边界约 26msDefault trim: 5s off the end, 0s off the start; WAV export (multi-channel mixed to stereo, with a warning first); stream-copy command -c copy; MP3 frame boundary ≈26ms

一键自检:没有真实文件也能验链路One-click self-check: verify the pipeline without a real file

点一下,页内现造一张带模拟水印块的测试图(浅色渐变底 + 右下角灰字块,另在角落放一颗孤立噪点和一条细线验过滤规则),走一遍检测 + 填充,把前后对比和填充框尺寸摆出来。噪点与细线不该把填充框撑大。

One click generates a test image in-page (light gradient background, a gray “watermark” block in the bottom-right, plus an isolated noise dot and a thin line in the corner to exercise the filters), runs detect + fill, and shows the before/after with the filled box size. The noise dot and the thin line must not stretch the fill box.

边界,先说清Boundaries, up front

  • 只清你自己拥有或被授权处理的文件。去标不改变版权,也不免除披露义务。
  • Only clean files you own or are authorized to process. Removing a mark does not change copyright, nor remove disclosure duties.
  • 这里只清可见水印。SynthID 隐形水印不在处理范围:角落清干净了,Google 的 SynthID 检测仍能识别 AI 来源——需要披露的地方照常披露。
  • Only visible watermarks are handled here. The invisible SynthID watermark is out of scope: even with the corner cleaned, Google's SynthID detection can still identify the AI origin — disclose wherever disclosure is required.
  • 与 Google / NotebookLM 无隶属关系;名称只作来源与兼容性说明。
  • Not affiliated with Google / NotebookLM; names are used only to indicate source and compatibility.
  • 原站有第 7 个工具「元数据清理」,本页不做:去掉可见标记与去掉文件溯源信息是两回事,不跟进。
  • The original site has a 7th tool, metadata cleaning, which this page does not do: removing a visible mark and removing a file's provenance data are different things.
  • 老实账:本页尚未拿真实 NotebookLM 导出文件做过一轮完整实测;v2 的检测器过滤、自建模板恢复与 PDF 页内解析都先用上方的自检和你自己的文件抽查后再放心用。
  • Honest note: this page has not yet been fully tested end-to-end on a real NotebookLM export. For v2's detector filters, own-template recovery and in-page PDF parsing, run the self-check above and spot-check with your own file first.

开源对比:复刻站在谁的肩膀上Open-source comparison: what this rebuild stands on

原站 notebooklmremover.org 是闭源纯静态站(Astro + Cloudflare Pages),未找到仓库与许可证,只能对照功能、不能抄实现。本页的方法以 MIT 开源项目为准:

The original site, notebooklmremover.org, is a closed-source static site (Astro + Cloudflare Pages) with no repository or license found — features can be compared, implementation cannot be copied. This page's methods follow MIT open-source projects:

项目Project许可证License覆盖Coverage本页取了什么What this page took
alpinist-GH · Logo Remover v0.2.4MIT视频 + PDF + PPTX + 图片Video + PDF + PPTX + Images视频 delogo 快档思路、按格式分流的整体结构Fast-preset delogo approach for video; overall per-format routing structure
froggeric · wmr (132 星stars)MIT视频 / Gemini 图Video / Gemini images反向 alpha 方法与「视频须 inpainting」的判断Reverse-alpha method and the “video needs inpainting” judgment
Albonire (83 星stars)MIT批量 + 预览Batch + previewPPTX 批量处理与 Telea 参数参考PPTX batch handling and Telea parameter reference
encoreshao · nlm-unwatermarkMITPPTX / PDF检测 → 干净 patch 优先 → inpainting 兜底的三段骨架Detect → clean patch first → inpainting fallback, three-stage skeleton
dovetaill / CourseBar101无许可证No license图片Images只学双旋钮参数设计,不用代码Two-knob parameter design only; no code used
LazySo / ijpg / Source Helper未开源Not open source图片 / 桌面Images / Desktop只学方法,不用代码Methods only; no code used

实现全在页内:图片走 Canvas API,PPTX 走页内 ZIP 读写,PDF 走页内解析与重建,音频走 Web Audio;只有视频 / 音频的原格式处理借你本机的 FFmpeg(命令由本页生成)。没有任何第三方库、没有 CDN 依赖。

Everything runs in-page: Canvas API for images, a built-in ZIP reader/writer for PPTX, built-in parsing and rebuilding for PDF, Web Audio for audio; only the original-format video/audio path borrows your local FFmpeg (with commands generated here). No third-party libraries, no CDN dependencies.