Sys.Directive // 0x4A/Content Moderation

Content Moderation & Image Analysis

Flag explicit and violent images and spot AI-generated uploads before they reach your users. Sightova returns scores and evidence for each image in seconds. You set the threshold and decide what happens next.

INTEGRATION: REST API
SCORES: NSFW · VIOLENCE · AI
EVIDENCE: SYNTHID + C2PA

Detection Capabilities

QUERY: SELECT * FROM moderation_signals
MOD-NSFW-01
DETECTION MODULE

NSFW Score

Flag explicit images with one clear probability and an is_nsfw flag for each image. A single number your code can route on, at whatever threshold suits your community.

NSFW PROBABILITYIS_NSFW FLAGYOUR THRESHOLD
MOD-VIOL-02
DETECTION MODULE

Violence Score

Flag violent imagery with a dedicated endpoint. It returns a violence probability, a safe probability, an is_violent flag and a verdict of violent, safe or uncertain.

VIOLENCE PROBABILITYVERDICTIS_VIOLENT FLAG
MOD-AI-03
DETECTION MODULE

AI-Generated Image Detection

An AI probability and a verdict (ai-generated, real or uncertain) for each image, so your team can label or review images that look generated. The model reads the pixels, so it works even when metadata has been stripped.

AI PROBABILITYVERDICTCLOSEST GENERATOR STYLE
MOD-WMK-04
DETECTION MODULE

Watermark & Credential Evidence

Evidence, not just a score. Each AI image check looks for invisible Google SynthID and OpenAI watermarks and reads C2PA content credentials and EXIF metadata, which can name the exact tool that made the image.

SYNTHIDOPENAI WATERMARKC2PAEXIF
MOD-HMP-05
DETECTION MODULE

Heatmap for Reviewers

See exactly where an image looks AI-edited. The heatmap shows your reviewers where to look. In the dashboard on the Starter plan and up.

HEATMAPREVIEWER AIDSTARTER PLAN +
MOD-DOC-06
DETECTION MODULE

Edited Document Images

Expose edits in images of documents such as receipts, invoices and IDs. The document tampering endpoint flags regions that look edited and returns a tampered percentage (Starter plan and up).

DOCUMENT TAMPERINGEDITED REGIONSSTARTER PLAN +
MOD-AGE-07
DETECTION MODULE

Optional Age Estimation

Optional age estimation: an estimated age and likely range for each person, switched on in Settings and shown alongside the AI detection result.

OPTIONAL EXTENSIONESTIMATED AGELIKELY RANGE
MOD-PRV-08
DETECTION MODULE

Hosted in Germany

Moderation images can be sensitive. Sightova is hosted in Germany, images are deleted after analysis, and they are not used to train our models.

HOSTED IN GERMANYDELETED AFTER ANALYSISNO TRAINING
MOD-API-09
DETECTION MODULE

REST API & Human Review

Connect through the REST API on any plan, up and running with an API key. Scores come back as data; your team sets the thresholds and decides which images go to human review.

REST APIAPI KEYHUMAN REVIEW
// PAYLOAD STRUCTURE

Plain JSON Scores

Each endpoint returns a small JSON result with probabilities and, for some endpoints, a verdict. Route images in your own code on the thresholds you choose, and send borderline scores straight to your reviewers.

  • Clear scores your code can route on, with the REST API on every plan
  • Combine scores in your own logic, e.g. NSFW score plus AI verdict
  • Scan records are kept with your account for your own reference
RESPONSE — POST /api/v1/detect/nsfw
{
  "request_id": "req_5oQjGqU4mB2nQp9Hg7vTz",
  "endpoint": "/api/v1/detect/nsfw",
  "detection_type": "nsfw moderation",
  "result": {
    "nsfw": {
      "nsfw_probability": 0.97,
      "is_nsfw": true
    }
  }
}

Give Your Review Team a Head Start

Connect the REST API to your own workflow with an API key and put high-scoring images in front of your reviewers first. Start free with no credit card.