storyicon/comfyui_segment_anything

Based on GroundingDino and SAM, use semantic strings to segment any element in an image. The comfyui version of sd-webui-segment-anything.

45
/ 100
Emerging

This tool helps creative professionals and artists precisely select any element within an image using simple text descriptions. You input an image and a text prompt (e.g., "the red car" or "the person in the foreground"), and it outputs a segmented mask highlighting exactly what you described. It's ideal for anyone looking to isolate specific objects in images for editing, compositing, or further AI-driven art generation.

1,088 stars. No commits in the last 6 months.

Use this if you need to accurately identify and create a mask for a specific object or region in an image using descriptive text.

Not ideal if you prefer manual selection tools or don't need a text-guided approach for image segmentation.

image editing digital art creative design visual content creation asset preparation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

1,088

Forks

103

Language

Python

License

Apache-2.0

Last pushed

Jul 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/storyicon/comfyui_segment_anything"

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