Detect explicit and violent images.
Before they go live.
Sightova scores every image for explicit content and for violence, including graphic injury. Each check returns a probability and a flag in seconds, so your platform can hold an upload for review before anyone sees it.
Or try it free in the dashboard. No card needed.
- Violence99%
- Explicit contentUnder 1%
- 2
- Checks: explicit content and violence
- 0–100%
- Probability for every image
- EEA
- Images analysed in Germany and Iceland
- REST
- API access on every plan
Two moderation checks, one API.
Score each image for explicit content, for violence, or both. Every check returns a probability and a flag, so your team sets its own thresholds for approval and review.
01 · Explicit content
Explicit content detection
Returns the probability that an image contains explicit sexual content, with an is_nsfw flag for routing.
02 · Violence
Violence and injury detection
Detects physical violence and graphic injury. Returns a violence probability, a safe probability, an is_violent flag and a verdict.
03 · Thresholds
Configurable thresholds
Use the probability to set your own levels for automatic approval, human review and rejection.
Output · Score
Probability scores
A probability from 0 to 100% for each check, on every image.
Output · Verdict
Verdicts for routing
is_nsfw, is_violent and a violence verdict (safe, uncertain or violent) to route images in your own workflow.
Output · History
Scan history
Every scan is stored in your account with its scores and metadata for later review.
Tested on violent scenes and on everyday images.
Fights, armed scenes and simulated injuries were flagged by the violence check. Swimwear, bare skin and a cracked phone screen passed both checks. All images were scanned on the live models on 10 November 2026.
Flagged · Violence
Combat sport (MMA)
- Violence
- 99%
- Explicit content
- Under 1%
Armed scene, police training
- Violence
- 96%
- Explicit content
- Under 1%
Simulated arm wound (training makeup)
- Violence
- 99%
- Explicit content
- Under 1%
Passed · Both checks
Beach, swimwear
- Violence
- Under 1%
- Explicit content
- Under 1%
Pool, bare chest
- Violence
- Under 1%
- Explicit content
- Under 1%
Cracked phone screen
- Violence
- Under 1%
- Explicit content
- Under 1%
Photos via Wikimedia Commons, including the hero: ice hockey fight by ArtBrom (CC BY-SA 2.0); MMA fight (CC0); police training by Sgt. 1st Class Ben Houtkooper and training makeup by Senior Airman Austin Harvill, U.S. Air Force (public domain; use of U.S. Department of Defense imagery does not imply endorsement); cracked iPhone by Ed6767 (CC BY-SA 4.0). Photos of people in the everyday set were generated by Sightova with Google's Nano Banana Pro and Nano Banana 2.
Built for government, law enforcement and enterprise.
Image moderation with documented scores, in the dashboard or through the API.
Government & public sector
Moderate images submitted to public services, consultations and community channels before they are published.
- Images analysed in Germany and Iceland (EEA)
- DPA, MSA and subprocessor list published
- Enterprise agreements for agencies
Law enforcement & investigations
Sort large image sets by explicit and violent content, so investigators can prioritise review and limit unnecessary exposure.
- Probability per image for sorting
- Scan history in your account
- REST API for your case tools
Enterprise trust & safety
Screen uploads on marketplaces, dating apps and communities as they arrive.
- One API call per image and check
- Configurable review thresholds
- API access on every plan
Integrates with your existing workflow.
Use the dashboard for manual review, or call the REST API from your upload pipeline and moderation tools.
- 01
Submit
Send each image to /detect/nsfw, /detect/violence or both, as a file, URL or base64. JPEG, PNG, GIF and WebP, up to 50 MB.
- 02
Analyse
Each check returns its probability and flag in seconds. The violence check also returns a verdict.
- 03
Review
Apply your own thresholds. Approve low scores automatically and route flagged images to your review queue.
Request
curl -X POST 'https://sightova.com/api/v1/detect/nsfw' \
-H 'X-API-Key: sk_<your-key>' \
-H 'Content-Type: application/json' \
-d '{"image_url": "https://example.com/upload.jpg"}'Example response · /detect/nsfw
{ "request_id": "req_8kWq2LmZp4TnVc7RbYd1F", "endpoint": "/api/v1/detect/nsfw", "result": { "nsfw": { "nsfw_probability": 0.01, "is_nsfw": false } } }
Example response · /detect/violence
{ "request_id": "req_3HsLq9XcPa2MvN6TeRw8K", "endpoint": "/api/v1/detect/violence", "result": { "violence": { "violence_probability": 0.01, "safe_probability": 0.99, "is_violent": false, "verdict": "safe" } } }
Each check is a separate request and uses one credit from your plan.
Processing, retention and contracts.
Where images are processed, what is retained, and the agreements available for review.
EEA processing
Application and database are hosted in Nuremberg, Germany. Detection also runs on a GPU server in Reykjavík, Iceland. Traffic is routed through Cloudflare over TLS 1.2 or higher.
Deleted after analysis
Uploaded images are written to a temporary file during analysis and deleted when the scan completes.
Not used for training
Scanned images are not used for model training. Images are retained only when you submit them as feedback.
Published DPA and MSA
The DPA, MSA and subprocessor list are publicly available for legal and procurement review.
Enterprise agreements
Volume pricing, contract terms and self-hosted deployment can be discussed under an enterprise agreement.
One balance for every check
Explicit content, violence and AI image checks share one monthly credit balance, in the dashboard and through the API.
Test Sightova on your own images.
Request a demo, or start a free account and run your first scans today.