ControlNet/LAV-DF
[CVIU, DICTA Award] Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization
This project provides a robust dataset and tools to identify manipulated segments within audio-visual content. It takes videos as input and outputs precise timestamps or regions where deepfake alterations have occurred. Professionals in journalism, fact-checking, and digital forensics can use this to verify media authenticity.
108 stars. No commits in the last 6 months.
Use this if you need to automatically detect and pinpoint specific forged sections in videos and their accompanying audio, especially for identifying sophisticated deepfakes.
Not ideal if you are looking for a simple, out-of-the-box user application for general deepfake detection without needing to train or evaluate models.
Stars
108
Forks
19
Language
Python
License
—
Category
Last pushed
Jun 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ControlNet/LAV-DF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
yannadani/image_tampering_detection_references
A list of papers, codes and other interesting collections pertaining to image tampering...
shraddhavijay/IFAKE
IFAKE is an application for detecting image and video forgery, designed to help users verify the...
Megum1/CO-SPY
[CVPR'25] CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI
lintsinghua/VerifyVision-Pro
VerifyVision-Pro是一个全面的图像伪造篡改检测解决方案，利用深度学习（deep...
Junjue-Wang/Rank1-Ali-Tianchi-Real-World-Image-Forgery-Localization-Challenge
2022阿里天池真实场景篡改图像检测挑战赛-冠军方案（1/1149）