AnaMVasilcoiu/LATTE-Diffusion-Detector
Official code for "LATTE: Latent Trajectory Embedding for Diffusion-Generated Image Detection"
This project helps you identify if an image was generated by an AI diffusion model, rather than being a real photograph. It takes a collection of images as input and tells you which ones are likely AI-generated. This tool is for professionals in fields like forensic analysis, content moderation, or digital media who need to verify image authenticity.
Use this if you need to reliably distinguish between real and AI-generated images, especially those produced by diffusion models like Stable Diffusion.
Not ideal if you're trying to detect AI-generated content beyond images or from non-diffusion-based generative models.
Stars
8
Forks
—
Language
Python
License
—
Category
Last pushed
Oct 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/AnaMVasilcoiu/LATTE-Diffusion-Detector"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OPTML-Group/Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in...
Shilin-LU/VINE
[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From...
WindVChen/DiffAttack
An unrestricted attack based on diffusion models that can achieve both good transferability and...
koninik/DiffusionPen
Official PyTorch Implementation of "DiffusionPen: Towards Controlling the Style of Handwritten...
Wuyxin/DISC
(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation