UX-Decoder/Segment-Everything-Everywhere-All-At-Once

Health v2 · maintenance only

Adoption not part of the score

4794 stars · 449 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

SEEM is the official PyTorch implementation of the NeurIPS 2023 paper 'Segment Everything Everywhere All at Once', a model for universal image segmentation driven by multi-modal prompts. It supports visual prompts (points, boxes, scribbles, image segments) and language prompts (text, audio), individually or in combination.

Use cases

• segment objects in an image using text prompts
• click or scribble on an image to segment a region
• segment everything in an image automatically
• combine point and text prompts for interactive segmentation
• use segmentation as visual prompting for GPT-4V
• integrate segmentation into multimodal chat demos

When to choose

• you need state-of-the-art interactive or promptable image segmentation
• you want multi-modal prompting (text, points, boxes, scribbles, audio) in one model
• you are doing research on universal segmentation or visual prompting

When to avoid

• you need a lightweight production segmentation service with minimal dependencies
• you only need simple classical segmentation like thresholding or edge detection
• you lack a GPU or cannot build CUDA-based vision dependencies

Facets

library · maturity stable

computer-vision image-processing machine-learning deep-learning computer-vision image-processing artificial-intelligence deep-learning python image-segmentation multimodal-prompts interactive-segmentation research-code neurips-2023 linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="UX-Decoder/Segment-Everything-Everywhere-All-At-Once")