Firefox Browser Add-ons
  • Extensions
  • Themes
    • for Firefox
    • Dictionaries & Language Packs
Log in
Preview of Haram Blur – AI NSFW Image Blocker

Haram Blur – AI NSFW Image Blocker by msaidzengin

Blur porn, nude and suggestive images on any website with on-device AI. Free NSFW image blocker for Firefox, Chrome and Edge. Photos are checked in your browser and never uploaded.

0 (0 reviews)0 (0 reviews)
Download Firefox and get the extension
Download file

Extension Metadata

Screenshots
Blur inappropriate images automaticallyChecked by AI on your device, never uploadedSee what was checked on every pageChoose how strict the filter isCovered while checking, shown when safe
About this extension
Haram Blur is a free NSFW image blocker for Chrome, Edge and Firefox. It blurs porn, nude and suggestive photos on the websites you visit, using an AI model that runs on your own device. Your images are never uploaded.

HOW IT WORKS
• Every photo is covered the moment it appears on the page, so explicit images do not flash before they are checked.
• A built-in NSFW detection model (NSFWJS on TensorFlow.js) scores each photo for porn, hentai and sexy content, right in your browser.
• If the highest score in a category you enabled reaches your threshold (50% by default), the photo stays blurred. Otherwise it appears normally.
• Works on image search, social media, news sites, infinite scroll, lazy-loaded images and pages that change without reloading.

PRIVATE BY DESIGN
• On-device AI: photos are checked locally and never sent to us or to any AI service.
• No account, no analytics, no ads, no browsing history.
• Settings are stored only in your browser.

YOU STAY IN CONTROL
• Click a blurred photo (or press Enter or Space) to show it when the filter is wrong.
• Reveal every blurred photo on a page from the popup, then hide them again.
• Pause the filter on a website, or turn protection off with one click.
• Choose how strict the filter is, which categories count (porn, hentai, sexy) and how strong the blur looks.
• Live counts in the popup show how many photos were checked and blurred on the current page.

GOOD TO KNOW
• Haram Blur is an image filter, not a website blocker: pages still open and their text stays visible.
• No AI filter is perfect. It can miss an explicit photo or blur a safe one, such as some swimwear photos. Lower the threshold for a stricter filter, raise it for fewer blurs.
• A photo that cannot be checked stays covered; click it to show it.
• Images inside embedded frames are not scanned.

Website: https://haram-blur.msaidzengin.com
Privacy policy: https://haram-blur.msaidzengin.com/privacy-policy
Rated 0 by 0 reviewers
Log in to rate this extension
There are no ratings yet

Star rating saved

5
0
4
0
3
0
2
0
1
0
No reviews yet
Permissions and data

Required permissions:

  • Display notifications to you
  • Access browser tabs
  • Access your data for all websites

Optional permissions:

  • Access your data for all websites

Data collection:

  • The developer says this extension doesn't require data collection.
Learn more
More information
Add-on Links
  • Homepage
  • Support site
  • Support Email
  • Copy add-on ID
Version
0.1.0
Size
2.84 MB
Last updated
12 days ago (Oct 18, 2026)
Related Categories
  • Privacy & Security
License
All Rights Reserved
Privacy Policy
Read the privacy policy for this add-on
Version History
  • See all versions
Tags
  • content blocker
  • privacy
Add to collection
Report this add-on
Go to Mozilla's homepage

Add-ons

  • About
  • Firefox Add-ons Blog
  • Extension Workshop
  • Developer Hub
  • Developer Policies
  • Community Blog
  • Forum
  • Report a bug
  • Review Guide

Download

  • Download Firefox
  • Windows
  • macOS
  • iOS
  • Android
  • Linux
  • All

Latest Builds

  • Nightly
  • Beta

Firefox for Business

  • Enterprise

Community

  • Connect
  • Contribute
  • Developer

Follow

  • Instagram
  • YouTube
  • TikTok
  • Bluesky
  • Podcast
  • Privacy
  • Cookies
  • Legal

Except where otherwise noted, content on this site is licensed under the Creative Commons Attribution Share-Alike License v3.0 or any later version.