Skip to content
SPECIFICTION
Get listed

Video Background Remover CLI

github.com

Free plan WindowsLinuxSelf-hosted
Visit github.com
Spec score 8.1 #14 of 29 in AI Video Background Removers

What it is

Video Background Remover CLI is a free Linux command-line tool for removing video backgrounds with rembg and OpenCV. It accepts MP4 and MOV files and can export processed video, transparent PNG or WebP frames, and animated WebP or GIF files. Removed backgrounds can be replaced with a solid color or an image. Available models include isnet-general-use, u2net, u2netp, u2net_human_seg, and silueta. The CLI can convert MatAnyone foreground and alpha video pairs, or invoke MatAnyone 2 through matanyone2-runtime. A bundled Gradio WebUI provides a CLI Export tab and helpers for WebP, GIF, frame ZIP, MP4, and WebM output. Installation uses pip, Python 3.10 or later is required, and FFmpeg is not required. Models download on first run. Regular video output composites transparent pixels onto a selected background or black by default, so it does not preserve alpha. Long GIF exports can become large. Silueta is described as higher quality but slower, while u2netp is lighter but may lose quality on complex fire frames.

Spec sheet

What it does
Python command-line software removes video backgrounds with rembg and OpenCV.Read 21 Oct 2026 · github.com
Animated exports
It can create animated WebP, GIF, or both from video.Read 21 Oct 2026 · github.com
API availability
The published documentation exposes command-line and Python module entry points but no hosted HTTP API.Read 21 Oct 2026 · raw.githubusercontent.com
Background options
Users can replace the removed background with a solid color or an image.Read 4 Oct 2026 · github.com
Background replacement
Removed backgrounds can be replaced with a solid color or an image.Read 21 Oct 2026 · github.com
CLI entry points
The package exposes video-background-remover, vbr, video-background-remover-webui, and vbr-webui commands.Read 21 Oct 2026 · raw.githubusercontent.com
Default model
isnet-general-use is the documented default model.Read 21 Oct 2026 · sunwood-ai-labs.github.io
Developer dependencies
The project declares rembg, OpenCV, NumPy, Pillow, tqdm, onnxruntime, and imageio-ffmpeg dependencies.Read 21 Oct 2026 · raw.githubusercontent.com
FFmpeg requirement
The documentation says FFmpeg is not required.Read 21 Oct 2026 · sunwood-ai-labs.github.io
First-run model download
Models download automatically on first use and are cached locally.Read 21 Oct 2026 · sunwood-ai-labs.github.io
GIF limit
The README cautions that animated GIF exports of long videos can become large.Read 4 Oct 2026 · github.com
Green-fringe cleanup
MatAnyone processing includes cleanup for green matte contamination around semi-transparent edges.Read 21 Oct 2026 · github.com
Install method
The README documents installation from PyPI with pip install video-background-remover.Read 4 Oct 2026 · github.com
Installation
The package can be installed with pip as video-background-remover.Read 21 Oct 2026 · pypi.org
Licence status
The repository file listing and pyproject metadata show no declared software licence.Read 21 Oct 2026 · github.com
Limit: GIF size
The README warns that long animated GIF exports can become large.Read 21 Oct 2026 · github.com
Limit: processing startup
The documentation warns that initial model loading can take time.Read 21 Oct 2026 · github.com
Limit: regular video alpha
Regular MP4 output does not retain alpha transparency and composites onto a selected background or black.Read 21 Oct 2026 · sunwood-ai-labs.github.io
Maker identity
The GitHub organization profile identifies the account as Maki Sunwood-ai-labs and links to hamaruki.com.Read 21 Oct 2026 · github.com
Maker portfolio
Devpost lists Maki Maki (sunwood-ai-labs) with one project and one hackathon.Read 21 Oct 2026 · devpost.com
Maker website date
The maker's website footer states © 2022 Sun wood AI labs.2.Read 21 Oct 2026 · hamaruki.com
MatAnyone backend
It can invoke matanyone2-runtime through a separately specified Python interpreter.Read 21 Oct 2026 · github.com
MatAnyone integration
The CLI can convert MatAnyone foreground and alpha video pairs, or invoke MatAnyone 2 through matanyone2-runtime.Read 4 Oct 2026 · github.com
MatAnyone pairs
The tool combines matching foreground and alpha video files into transparent outputs.Read 21 Oct 2026 · github.com
Model selection
Available rembg models are isnet-general-use, u2net, u2netp, u2net_human_seg, and silueta.Read 21 Oct 2026 · sunwood-ai-labs.github.io
Model tradeoff
The documentation describes silueta as higher quality but slower and u2netp as faster with lower accuracy.Read 21 Oct 2026 · sunwood-ai-labs.github.io
Optional extras
The package offers dev and webui extras, with the latter requiring Gradio 6 through version 7.Read 21 Oct 2026 · raw.githubusercontent.com
Performance tradeoff
The README describes silueta as higher quality but slower, and u2netp as a lightweight model whose quality can drop on complex fire frames.Read 4 Oct 2026 · github.com
PyPI artifact
The 0.3.0 wheel is a 69.5 kB universal Python wheel.Read 21 Oct 2026 · pypi.org
PyPI maintainer
PyPI identifies one maintainer named MakiMakiAi.Read 21 Oct 2026 · pypi.org
PyPI maturity
PyPI classifies the package as Development Status 3 - Alpha.Read 21 Oct 2026 · pypi.org
PyPI provenance
PyPI records the 0.3.0 release as published through GitHub Actions trusted publishing.Read 21 Oct 2026 · pypi.org
PyPI release
PyPI lists version 0.3.0 uploaded on 2026-03-15.Read 21 Oct 2026 · pypi.org
Release v0.3.0
Version 0.3.0 was released on 2026-03-15 with the Gradio WebUI and MatAnyone2 Tile workflow.Read 21 Oct 2026 · github.com
Removal models
Available models include isnet-general-use, u2net, u2netp, u2net_human_seg, and silueta.Read 4 Oct 2026 · github.com
Repository activity
The GitHub repository page shows 29 stars, 2 forks, 85 commits, and no open issues.Read 21 Oct 2026 · github.com
Requirements
The project requires Python 3.10 or newer.Read 21 Oct 2026 · sunwood-ai-labs.github.io
Security and support
The repository page does not state a security certification or dedicated support commitment.Read 4 Oct 2026 · github.com
Tile workflow
MatAnyone2 Tile handles 2x2 and 3x3 tiled videos and produces per-tile animations.Read 21 Oct 2026 · sunwood-ai-labs.github.io
Transparency limit
Regular video output does not preserve alpha transparency; the CLI composites transparent pixels onto a chosen background or black by default.Read 4 Oct 2026 · github.com
Transparent frames
It exports transparent PNG or WebP frames at configured time intervals.Read 21 Oct 2026 · sunwood-ai-labs.github.io
Video and image outputs
It exports processed video, transparent PNG or WebP frames, and animated WebP or GIF files.Read 4 Oct 2026 · github.com
Video export
It extracts frames, removes backgrounds, and rebuilds regular video files.Read 21 Oct 2026 · sunwood-ai-labs.github.io
Web interface
The repository includes a Gradio WebUI with a CLI Export tab and post-export helpers for WebP, GIF, frame ZIPs, MP4, and WebM.Read 4 Oct 2026 · github.com
WebUI
The repository includes a Gradio 6 WebUI with CLI export helpers.Read 21 Oct 2026 · pypi.org
WebUI outputs
The WebUI supports WebP, GIF, PNG frame ZIPs, flattened MP4, and transparent WebM outputs.Read 21 Oct 2026 · pypi.org

Plans and prices

Video Background Remover CLI Free Python 3.10+ · model downloads on first run · long animated GIFs can become large Read 4 Oct 2026 · github.com

Every Video Background Remover CLI plan and price →

Strong points and limits

Strong points

  • Free use with no trial required
  • Supports MP4 and MOV input
  • Offers several removal models
  • Includes Gradio WebUI export helpers
  • Can replace backgrounds with color or image

Limits

  • Regular video output does not preserve alpha
  • Long animated GIFs can become large
  • Silueta trades speed for quality
  • Requires Python 3.10 or later

Who it suits

It suits Linux users who want command-line or Gradio workflows for removing backgrounds from MP4 or MOV video. It also fits users needing frame, animated-image, or replacement-background output.

Verdict

Video Background Remover CLI covers command-line, WebUI, frame, and animated-image workflows on Linux. Check the alpha-compositing behavior and model speed tradeoffs before choosing an output format.

Where Specifiction places it

Alternatives to Video Background Remover CLIAll alternatives →