yuxin-jiang/Anomagic
[AAAI 2026] The Official Implementation for "Anomagic: Crossmodal Prompt-driven Zero-shot Anomaly Generation"
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.
Stars
129
Forks
5
Language
Python
License
—
Category
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.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...