Background Remove Skill

Quick Examples

Prerequisites

• rembg

  - AI-based background removal (recommended)
  bash

  pip install rembg
  # Or with GPU acceleration (faster, requires CUDA)
  pip install rembg[gpu]

• Pillow

  - Required for image processing
  bash

  pip install Pillow

Methods

Workflow

Step 1: Gather Requirements (REQUIRED)

AskUserQuestion

"Which image(s) should I remove the background from?

Please provide the file path or paste the image."

"Which removal method?

• AI (rembg) - Best quality, works on any image (default)
• Built-in - Faster, best for white backgrounds"

"Where should I save the result?

• Same location with

  _nobg

  suffix (default)
• Custom path"

Step 2: Execute Background Removal

python3 ${SKILL_PATH}/skills/background-remove/scripts/background_remove.py \
  -i "/path/to/image.jpg" \
  -o "/path/to/output.png"

python3 ${SKILL_PATH}/skills/background-remove/scripts/background_remove.py \
  -i "/path/to/img1.jpg" "/path/to/img2.png" "/path/to/img3.webp" \
  -o "/path/to/output_folder"

python3 ${SKILL_PATH}/skills/background-remove/scripts/background_remove.py \
  -i "/path/to/icon.png" \
  -m builtin

Step 3: Deliver Result

1. Show the result to the user
2. Confirm the background was removed successfully
3. Offer to:
   • Process additional images
   • Try a different method if quality isn't satisfactory
   • Adjust output format (PNG vs WebP)

Script Parameters

--input

-i

--output

-o

_nobg

--method

-m

Output Formats

.png

.webp

Integration with Other Skills

From Python (import)

import sys
sys.path.insert(0, "${SKILL_PATH}/skills/background-remove/scripts")
from background_remove import remove_background

result = remove_background("/path/to/image.png", "/path/to/output.png", method="rembg")
if result.get("success"):
    print(f"Saved to: {result['file']}")
else:
    print(f"Error: {result['error']}")

From Command Line

python3 ${SKILL_PATH}/skills/background-remove/scripts/background_remove.py \
  -i "/path/to/image.png" \
  -o "/path/to/output.png" \
  -m rembg

Error Handling

rembg not installed. Install with: pip install rembg[gpu] (or pip install rembg for CPU-only)

Image not found: /path/to/image.png

• Try a different method
• Check if the image file is corrupted
• Ensure sufficient memory for large images

Tips for Best Results

1. Use rembg for photos - AI handles complex edges (hair, fur, transparent objects)
2. Use builtin for graphics - Faster for icons/logos with clean white backgrounds
3. Check edges - If edges are rough, the AI method usually gives better results
4. Batch process - Process multiple images at once for efficiency
5. GPU acceleration - Install

   rembg[gpu]

   for faster processing on NVIDIA GPUs

Examples

Remove background from a photo

python3 ${SKILL_PATH}/skills/background-remove/scripts/background_remove.py \
  -i "product_photo.jpg" \
  -o "product_transparent.png"

Batch process a folder

python3 ${SKILL_PATH}/skills/background-remove/scripts/background_remove.py \
  -i photos/*.jpg \
  -o "transparent_photos/"

Fast removal for icons (white background)

python3 ${SKILL_PATH}/skills/background-remove/scripts/background_remove.py \
  -i "icon.png" \
  -m builtin

Output as WebP (smaller file size)

python3 ${SKILL_PATH}/skills/background-remove/scripts/background_remove.py \
  -i "photo.jpg" \
  -o "result.webp"