ahmetkumass/yolo-gen

Train YOLO + VLM with one command. Auto-generate vision-language training data from YOLO labels - no extra labeling needed.

42
/ 100
Emerging

This tool helps quality control inspectors, manufacturing engineers, or medical imaging analysts automatically get detailed descriptions and classifications of objects detected in images. You provide images with basic bounding box labels for objects (like 'defect' or 'nodule'), and it outputs not just the object's location but also structured, descriptive text about its characteristics, such as `{"defect": true, "type": "scratch", "size": "2mm"}`. This allows for more precise automated analysis than simple object detection alone.

Use this if you need both fast object detection and detailed, descriptive information about those objects for tasks like automated inspection, damage assessment, or medical diagnostics.

Not ideal if you only need to know the location of objects without any further textual analysis or detailed categorization, or if you don't have existing YOLO-style bounding box labels for your data.

quality-control manufacturing-inspection medical-imaging-analysis defect-detection asset-damage-assessment
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 13 / 25
Community 13 / 25

How are scores calculated?

Stars

24

Forks

4

Language

Python

License

MIT

Last pushed

Feb 07, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ahmetkumass/yolo-gen"

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