gconsigli/ai-watermarking

AI watermarker for images and text that replicates SynthID's functionality.

21
/ 100
Experimental

This tool helps content creators and platforms identify AI-generated images and text. It embeds an invisible digital watermark into images created by AI models like Stable Diffusion and assesses the likelihood that text was generated by AI, specifically GPT2. This is useful for anyone managing or consuming digital content who needs to distinguish between human-made and AI-made material.

No commits in the last 6 months.

Use this if you need to detect or track AI-generated images and text to combat misinformation or ensure content authenticity.

Not ideal if you require the full robust functionality and scale of Google's official SynthID for all media types.

content-verification misinformation-detection digital-forensics AI-content-management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Mar 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gconsigli/ai-watermarking"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.