yuxin-jiang/Anomagic

[AAAI 2026] The Official Implementation for "Anomagic: Crossmodal Prompt-driven Zero-shot Anomaly Generation"

32
/ 100
Emerging

This project helps quality control engineers and manufacturing line operators improve anomaly detection systems. It generates realistic, diverse images of defective products based on simple text descriptions or examples of normal products. These synthetic anomaly images can then be used to train and test automated inspection systems, even when real-world defect examples are scarce.

129 stars.

Use this if you need to create synthetic images of product defects to train an automated visual inspection system, especially when you have limited real-world examples of specific anomalies.

Not ideal if you're looking for a tool to detect anomalies in live production without needing to generate new training data.

quality-control manufacturing visual-inspection defect-detection synthetic-data-generation
No License No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 5 / 25
Community 7 / 25

How are scores calculated?

Stars

129

Forks

5

Language

Python

License

Last pushed

Mar 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yuxin-jiang/Anomagic"

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