Meta SAM 3 can segment and remove image backgrounds with text prompts

amos_gyamfi · x · 2026-07-27

Meta's Segment Anything Model 3 (SAM 3) is presented as a way to use text and visual prompts to precisely identify, segment, and remove image backgrounds.

The post also points to a working example inside Stream Chat iOS/SwiftUI using Apple’s new Core AI framework, showing the model in a real app integration rather than as a standalone demo.

Related event: Meta SAM 3 Enables Text-Prompted and On-Device Segmentation(2 posts)→

Original post →

More from Multimodal

Multimodal channel →