# natethegreate/hent-AI

Automation of censor bar detection

Repository: https://github.com/natethegreate/hent-AI
Canonical: https://ross.abutalabs.com/products/hent-ai
Language: Python
License: MIT
License Family: permissive
Last push: 2023-03-25T00:22:58+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2386, "days_push": 1258, "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 1730, forks 162 (observed 2026-08-28T04:05:28.557150+00:00)

## What it is
A Python application that automatically detects censor bars and mosaic blurs in illustrated adult content using deep learning (Mask R-CNN) and image segmentation. It generates masks for use with DeepCreamPy or decensors images/videos directly via ESRGAN.

## Use cases
- automatically detect censor bars in images
- find mosaic censored regions for DeepCreamPy
- decensor mosaic images and videos with ESRGAN
- batch process censored illustrations
- generate overlay masks from detected censors

## When to choose
- you need automated censor detection instead of manual masking
- you want to feed masks into DeepCreamPy or use built-in ESRGAN decensoring
- you work with illustrated Japanese adult content that is legally censored

## When to avoid
- you need support for real photographic content rather than illustrations
- you require modern maintained TensorFlow/PyTorch versions, since it depends on old 2018-era stacks
- you need a supported executable on Linux or macOS (executable is Windows-only)

## Facets
- artifact type: application
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: image-processing, computer-vision, deep-learning
- platform: windows, python
- tags: nsfw, decensoring, mask-rcnn, esrgan, image-segmentation, gui, linux

## Member repositories
- natethegreate/hent-AI (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:28.557150+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 2026-08-30T03:31:45.617052+00:00, confidence not recorded.
  - readme: https://github.com/natethegreate/hent-AI (fetched 2026-08-28T04:05:28.557150+00:00, sha 426605944014)
- Data as of 2026-08-30T08:39:29.467469+00:00.