athen-lab/mai
Multilayer Authenticity Identifier (MAI), a CNN model that attempts to identify synthetic AI images.
This project helps anyone who needs to determine if an image is real or was generated by artificial intelligence. It takes an image, ideally 200x200 pixels, and provides a score indicating its likelihood of being AI-generated, with a score of 1 meaning it's absolutely synthetic and 0 meaning it's authentic. Journalists, content creators, or researchers can use this to verify image origins.
No commits in the last 6 months.
Use this if you need to quickly assess the authenticity of a single image and suspect it might be AI-generated.
Not ideal if you need a solution for identifying AI-generated content across various media types beyond just images, or if you require an extremely high degree of certainty for critical applications.
Stars
31
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/athen-lab/mai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google/magika
Fast and accurate AI powered file content types detection
meilfang/LMFD-PAD
Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for...
2spi/ai-v-real
Real/AI Generated Image Classifier
Saranya-T-S/AI-Image-Detector
Deep learning-based system to detect AI-generated images using ELA, PRNU, FFT, and noise...
Linear-Fox-Labs/DePixel
Distinguish between real and AI-generated images.