mcpField
G
gemini-watermark-remover

gemini-watermark-remover

github.com/rookie-ricardoCreative & media9371.7k installsUpdated 14w ago
Repository

About gemini-watermark-remover

gemini-watermark-remover is a Python skill for processing Gemini-watermarked images, intended for command-line image editing. It uses Pillow for image input, output, and per-pixel changes, with the output format inferred from the file extension.

Key features

  1. 01Process a single image from the CLI
  2. 02Read and edit pixels with Pillow
  3. 03Infer image format from output extension
  4. 04Document watermark detection and algorithm

Use cases

  1. 01Remove a watermark from a Gemini image
  2. 02Process an input image as part of a workflow
  3. 03Adjust watermark detection rules or alpha logic

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/rookie-ricardo/erduo-skills --skill gemini-watermark-remover

After installing, type/gemini-watermark-removerin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
algorithm.md
scripts/
remove_watermark.py
requirements.txt

Details

From the project README

Gemini Watermark Remover

Dependencies

  • Python 3.9+
  • Pillow (install with pip install -r requirements.txt)

Quick start

  1. Install dependencies in the scripts folder:
    • cd skills/gemini-watermark-remover/scripts && pip install -r requirements.txt
  2. Run the CLI:
    • python remove_watermark.py <input-image> <output-image>

CLI usage

  • Parameters:
    • input-image: path to the Gemini watermarked image
    • output-image: path for the cleaned image (format inferred from extension)

Example:

python remove_watermark.py ./in.png ./out.png

What this skill provides

  • scripts/remove_watermark.py: CLI entry point and core algorithm.
  • assets/bg_48.png, assets/bg_96.png: Pre-captured watermark alpha maps.
  • references/algorithm.md: Math, detection rules, and limits.

Workflow

  1. Use remove_watermark.py for one-off processing.
  2. If you need to adjust detection rules or alpha logic, read references/algorithm.md.

Notes

  • The script uses Pillow for image IO and per-pixel edits.
  • Output format is inferred from the output file extension by Pillow.

Comments

Markdown supported