SAM3 — Segmentation AI Model

SAM3 segments anything you can name — "person", "red car" — returning a color overlay with every match labelled per instance. Comma-separate categories to catch several at once; each adds 10-30 seconds.

Try in Studio

Details

  • CategorySegmentation
  • Year2025
  • LicenseCustom (SAM License)

Compliance & Provenance

  • ProviderMeta (open) · Specialized
  • EU AI Act RiskMinimal Risk
  • Art. 50 TransparencyNot applicable

Inputs & Outputs

  • ImageInput · image

    Source image to segment

  • TextInput · string

    Noun phrase(s) naming the foreground objects to segment (e.g. 'person', 'the red car'). Comma- or semicolon-separated for multiple categories ('person, dog'); each category triggers its own inference call.

  • ImageOutput · image

    Colored overlay where each detected instance is painted in a distinct color. Pair with the Text output (which carries per-instance class+color metadata) into Masking-Image-Masker-By-Class for pixel-precise mask extraction.

  • TextOutput · string

    Per-instance metadata. Each line: '<prompt>|<prompt>_<idx>|object_<global>,(R G B),score,bbox[x0 y0 x1 y1]' — three pipe-separated alias labels (category / instance / legacy index) followed by the instance's overlay color, confidence, and bounding box.

Tags

  • segmentation
  • segment-anything
  • text-guided
  • multimodal
  • prompt-based
  • gpu-light
  • medium-speed

Alternatives in Segmentation

  • BiRefNet (Subject)

    Cleanly extracts a single salient subject with high-resolution edges. ~1-3s.

  • RF-DETR Seg Medium (Scene)

    Real-time instance segmentation on 80 COCO classes (RF-DETR Seg Medium).

  • SAM2 (Scene)

    Segment every object in an image (no labels needed). 10-30s.

  • SAM3.1 (Scene)

    Language-prompted segmentation — SAM 3.1 Object Multiplex with improved accuracy over SAM3. 10-30s/class.

Resources