guardex-security/safevision-python — explained in plain English
Analysis updated 2026-05-18
Scan user-uploaded images for NSFW content, gore, weapons, or blood before showing them.
Automatically blur or pixelate flagged regions of an image with one API call.
Add content moderation to an app without building your own image classifier.
| guardex-security/safevision-python | 0xallam/my-recipe | 0xhassaan/nn-from-scratch | |
|---|---|---|---|
| Stars | 0 | — | 0 |
| Language | Python | Python | Python |
| Last pushed | — | 2022-11-22 | — |
| Maintenance | — | Dormant | — |
| Setup difficulty | easy | moderate | moderate |
| Complexity | 2/5 | 2/5 | 4/5 |
| Audience | developer | general | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires an active SafeVision account and API key since moderation runs on their servers, not locally.
SafeVision Python SDK is the official Python client library for a hosted image moderation service called SafeVision. Instead of building your own system to detect inappropriate content in images, you send an image to SafeVision's API through this library, and the service tells you whether the image contains things like sexually explicit content, gore, weapons, or blood. After installing the package, you create a SafeVision client with an API key you get from SafeVision's own dashboard, then call scan on an image file. The result tells you whether the image is considered safe, which categories of unsafe content were detected along with their location in the image, and how long the check took. If the image is flagged as unsafe, you can call a second method, censor, which automatically blurs, pixelates, or blacks out the flagged regions and gives you back the edited image as bytes you can save to a file. The README documents two methods in total: scan, which returns the safety verdict and bounding boxes, and censor, which applies the chosen covering style to detected regions. Configuration is limited to an API key and, optionally, a different base URL if you are pointed at a different server than SafeVision's default one. This is a thin client library, so using it requires an active SafeVision account and API key from the service's own website, since the moderation itself happens on SafeVision's servers rather than on your own machine. The README does not state a license for the code, and points to SafeVision's own site for full documentation, getting an API key, and support.
A Python client for the SafeVision API that detects unsafe image content and can automatically blur or pixelate it.
Mainly Python. The stack also includes Python.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
double-check against the repo, no cap.