Megum1/CO-SPY
[CVPR'25] CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI
CO-SPY helps you identify whether an image has been generated by artificial intelligence. You provide an image, and it tells you if it's likely real or AI-generated. This tool is useful for anyone needing to verify the authenticity of visual content, such as journalists, content moderators, or researchers.
Use this if you need to quickly and accurately determine if an image is synthetically generated by popular AI models.
Not ideal if you need to detect subtle manipulations in real images rather than distinguishing between real and entirely AI-generated content.
Stars
40
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jan 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Megum1/CO-SPY"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yannadani/image_tampering_detection_references
A list of papers, codes and other interesting collections pertaining to image tampering...
ControlNet/LAV-DF
[CVIU, DICTA Award] Glitch in the Matrix: A Large Scale Benchmark for Content Driven...
shraddhavijay/IFAKE
IFAKE is an application for detecting image and video forgery, designed to help users verify the...
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）