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)→
More from Multimodal
- Third-party test: Claude Opus 5.5 renders finer 3D scenes but costs 13x more than GPT-6 Sol — testingcatalog · 2026-09-23
- ComfyUI trick: aux preprocessor + Qwen transfers poses across characters with one prompt — Acceptable-Work8202 · 2026-09-23
- Same portrait prompt across Midjourney V6.1, V7 and V8.2: do older models look better? — tisch_eins · 2026-09-23
- Testing AI character consistency across a 20-image travel sequence — SiennaVaire · 2026-09-23
- Midjourney v8.2 Faces: New Portrait Generation Samples Shared — azed_ai · 2026-09-23
- One-sentence prompt generates lifelike dog video, shown side-by-side with the real one — wgrathwohl · 2026-09-23