domains / families / media / segment-anything

segment-anything

separate

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

When to use

• Need to segment any object in images without task-specific training
• Building interactive annotation tools with point/box prompts
• Generating training data for other vision models
• Need zero-shot transfer to new image domains
• Building object detection/segmentation pipelines
• Processing medical, satellite, or domain-specific images
• **Zero-shot segmentation**: Works on any image domain without fine-tuning
• **Flexible prompts**: Points, bounding boxes, or previous masks

When not to use

• real-time object detection with classes
• semantic/panoptic segmentation with categories
• text-prompted segmentation
• video segmentation tasks

Skill page

Source