mirror of
https://github.com/hanzoui/workflow-templates-broken-zap-2026-06-08.git
synced 2026-10-30 20:44:35 +00:00
683 B
683 B
hanzo_studio_segment_anything
Author: storyicon URL: https://github.com/storyicon/hanzo_studio_segment_anything Stars: 1,073 Templates using this: 1
Description
Based on GroundingDino and SAM (Segment Anything Model), this pack allows you to use semantic text strings to segment any element in an image. Combines open-vocabulary object detection with precise segmentation for powerful text-guided masking.
Key Nodes
GroundingDinoSAMSegment: Takes an image and a text prompt describing the object to segment. Uses GroundingDino for open-vocabulary detection and SAM for precise mask generation, producing segmentation masks for the described objects.