skilld
All skills
rookie-ricardo avatar

/gemini-watermark-remover

@5ec8748
by Rookierookie-ricardo/erduo-skills936 stars
87

Remove the visible Gemini AI watermark from images using reverse alpha blending. Use when asked to strip Gemini watermarks, batch-process Gemini images, or build/modify a CLI script that removes the bottom-right Gemini watermark without HTML or server-side components.

Ask your Agent

Use this Skill: https://skilld.dev/gh/rookie-ricardo/erduo-skills/gemini-watermark-remover

This session only. Nothing lands on disk.

SKILL.md

≈74 tokens always: the name and description. ≈278 when used: this file. ≈213 more on demand in 1 file.

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.

Source: SKILL.md on GitHub

Third-party checks

No alerts5mo5 checks · Risk SAFE
  • Gen Agent Trust Hub7mo

    The skill is a legitimate image processing tool designed to remove visual watermarks from Gemini-generated images using the Pillow library. It performs local per-pixel calculations and does not engage in any suspicious activities such as network communication, command execution, or data exfiltration.

  • Socket6mo

    No alerts

  • Snyk7mo

    Risk: LOW · No issues

  • Runlayer7mo

    1/4 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 5ec8748. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Steadyupdated 8 months ago

Topics

  • Python
  • CLI
  • watermark-removal
  • image-processing
  • pillow
  • gemini
  • alpha-blending

README badge

README badge for rookie-ricardo/erduo-skills

What it does

Removes the Gemini AI watermark from images using reverse alpha blending via a Python CLI. Targets batch processing of Gemini-generated images and includes pre-captured watermark alpha maps for the bottom-right logo.

Generated from the current SKILL.md.

Frequently asked

What Python version is required?
Python 3.9 or higher. The skill depends on Pillow, installed via the bundled requirements.txt.
Does this work on all image formats?
The skill uses Pillow for image IO, so it supports any format Pillow handles (PNG, JPG, etc.). Output format is inferred from the file extension you provide.
Can I batch-process multiple images?
The CLI processes one image at a time. You would need to wrap remove_watermark.py in a loop or modify the script to batch multiple files.
How does the watermark removal work?
The skill uses reverse alpha blending with pre-captured watermark alpha maps (bg_48.png and bg_96.png). Details on detection rules and limits are in references/algorithm.md.

Generated from the current SKILL.md. These answers refresh after source changes.