# danielgatis/rembg

Rembg is a tool to remove images background

Repository: https://github.com/danielgatis/rembg
Canonical: https://ross.abutalabs.com/products/rembg
Language: Python
License: MIT
License Family: permissive
Topics: image-processing, background-removal, python
Last push: 2026-08-18T23:41:55+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 98, longevity 100
- inputs: {"age_days": 2214, "days_push": 15, "days_rel": 15, "gap_med": 19, "n_releases_24m": 22}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 24449, forks 2394 (observed 2026-08-28T04:11:37.107518+00:00)

## What it is
Rembg is a Python tool for removing image backgrounds using U2Net-based deep learning models. It can be used as a CLI, Python library, HTTP server, or Docker container, with CPU and GPU (CUDA) support.

## Use cases
- remove background from images
- extract subject from photo with transparent background
- batch remove image backgrounds via CLI
- serve background removal as an HTTP API
- cut out product photos for e-commerce
- create transparent PNGs from portraits

## When to choose
- you need offline, self-hosted background removal without a paid API
- you want a Python library, CLI, or HTTP server for the same task
- you have NVIDIA GPUs and want faster inference via onnxruntime-gpu

## When to avoid
- you need video background removal or fine-grained interactive editing
- you want a hosted API with no model downloads or GPU setup
- your Python version is outside the supported 3.11-3.13 range

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, cli, http-server
- domain: image-processing, computer-vision, machine-learning
- platform: python, cli, cross-platform
- tags: background-removal, u2net, onnxruntime, segmentation, alpha-matting, docker, gpu

## Member repositories
- danielgatis/rembg (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:37.107518+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:56:13.546098+00:00, confidence not recorded.
  - readme: https://github.com/danielgatis/rembg (fetched 2026-08-28T04:11:37.107518+00:00, sha 84656708083b)
  - registry_pypi: https://pypi.org/pypi/rembg/json (fetched 2026-08-29T07:53:28.867958+00:00, sha 0e770f13b4f5)
- Data as of 2026-08-30T08:39:29.467469+00:00.