bg-remove for Openclaw

A high-precision AI tool for instant background removal and image matting using advanced models like RMBG-1.4.

sxliuyu
v1.0.0
Mar 17, 2026
0
855
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install background-remove-pro

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install background-remove-pro using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is bg-remove?

The bg-remove skill is a professional-grade image processing utility designed for Openclaw Skills users who need to isolate subjects from their backgrounds with surgical precision. Leveraging state-of-the-art AI models including RMBG-1.4 and u2net, it automates the tedious task of manual masking, providing clean transparency for portraits, products, and graphic design assets.

Built for performance and flexibility, this tool handles everything from single image edits to massive directory batch processing. Whether you are preparing assets for e-commerce, creating marketing materials, or developing personal projects, bg-remove ensures high-quality PNG outputs with full alpha channel support, making it an essential part of any automated creative workflow.

bg-remove Use Cases

  • Removing backgrounds from product photos for e-commerce listings.
  • Creating transparent PNG portraits for team pages or social media.
  • Batch processing large sets of identity photos for standardized backgrounds.
  • Preparing assets for complex digital marketing and graphic design layouts.
  • Automating image preprocessing for AI training or web development.

How bg-remove Works

  1. The user provides an input path via Openclaw Skills, specifying either a single image or a directory.
  2. The skill initializes the selected AI model (defaults to u2net or specifically RMBG-1.4).
  3. The image is processed through the model to identify the foreground subject and calculate a transparency mask.
  4. Optional Alpha Matting is applied to refine edges, particularly useful for complex subjects like hair or fur.
  5. The tool generates a transparent PNG file, saving it to the specified output directory with refined naming conventions.

bg-remove Setup

To get started with this skill, ensure you have the necessary environment and run the installation within your Openclaw Skills workspace:

# Ensure Python 3.8+ is installed
pip install rembg pillow onnxruntime

# The skill will automatically download model files on first run
/bg-remove --input test.jpg

bg-remove Data Schema & Taxonomy

The skill manages data through a structured input/output system, maintaining the integrity of original files while generating high-quality derivatives.

Feature Details
Input Formats PNG, JPG, WebP, BMP
Output Format PNG (RGBA) with 8-bit Alpha Channel
Naming Convention Appends _nobg suffix unless --keep-name is flagged
Metadata Preserves core image dimensions and essential properties
Model Storage Models are cached locally for offline performance after first download

bg-remove Advanced Features

  • Multi-model support: Toggle between u2net and RMBG-1.4 for varying levels of detail.
  • Alpha Matting: Advanced edge refinement for hair, fur, and semi-transparent objects.
  • Batch Processing: Recursively process entire folders of images with a single command.
  • Threshold Control: Manually adjust the segmentation threshold for difficult lighting conditions.
  • Overwrite Protection: Use the force flag to manage file versioning during iterative tasks.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*