# notAI-tech/NudeNet

Lightweight nudity detection

Repository: https://github.com/notAI-tech/NudeNet
Canonical: https://ross.abutalabs.com/products/nudenet
Homepage: https://nudenet.notai.tech/
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: nsfw-recognition, censorship, object-detection, keras, nsfw-data, machinelearning, nudity-detection, nudity-detector, nudity, javascript, nsfw, onnxruntime
Last push: 2026-06-09T14:32:18+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 86, release rhythm 8, longevity 100
- inputs: {"age_days": 2743, "days_push": 85, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2433, forks 433 (observed 2026-08-28T04:06:51.195686+00:00)

## What it is
NudeNet is a lightweight Python library for nudity detection in images, built on YOLOv8 models running via ONNX Runtime. It detects exposed and covered body parts with bounding boxes and can censor flagged regions, with an optional Docker-based inference server.

## Use cases
- detect nudity in uploaded images
- moderate user-generated content for NSFW images
- censor exposed body parts in images before publishing
- classify images as safe or unsafe for a platform
- run nudity detection locally without sending images to a server
- batch-scan a folder of images for explicit content

## When to choose
- you need fast, lightweight NSFW image detection with fine-grained body-part labels
- you want local/on-premise detection so images never leave your infrastructure
- you need both detection and automatic censoring in one package
- you want a simple pip-installable model with ONNX and PyTorch weights available

## When to avoid
- you need video or live-stream moderation rather than still images
- you need text-based NSFW classification
- you require a commercially permissive license - the repo is AGPL-3.0
- you need actively developed features - the project is seeking maintainers

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, computer-vision
- domain: machine-learning, image-processing, privacy
- platform: python, cross-platform
- tags: nsfw-detection, nudity-detection, object-detection, yolo, onnx, content-moderation, censoring, docker

## Member repositories
- notAI-tech/NudeNet (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:51.195686+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:31:09.821442+00:00, confidence not recorded.
  - readme: https://github.com/notAI-tech/NudeNet (fetched 2026-08-28T04:06:51.195686+00:00, sha 1a15d65e81cb)
  - registry_pypi: https://pypi.org/pypi/nudenet/json (fetched 2026-08-29T10:12:35.117006+00:00, sha f6c7b67568f3)
- Data as of 2026-08-30T08:39:29.467469+00:00.