CoffeeVampir3/grounding-sam2-demo

A simple demo for utilizing grounding dino and segment anything v2 models together

22
/ 100
Experimental

This tool helps you quickly isolate specific objects or regions within an image based on a text description or by interactively pointing them out. You provide an image and a text prompt (like "dog" or "tree"), and it outputs an outline (mask) around the specified area. You can refine the selection by adding positive or negative control points directly on the image. This is ideal for anyone who needs to precisely segment visual elements for analysis, editing, or data labeling.

No commits in the last 6 months.

Use this if you need to accurately select and outline objects in images using natural language descriptions or interactive clicks.

Not ideal if you need a fully automated image segmentation solution without any human input or if you are looking to train custom segmentation models.

image-analysis visual-data-labeling photo-editing computer-vision-prototyping content-moderation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

21

Forks

2

Language

Python

License

Last pushed

Jul 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CoffeeVampir3/grounding-sam2-demo"

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