← Back to Skills Marketplace
476
Downloads
0
Stars
3
Active Installs
7
Versions
Install in OpenClaw
/install gemini-watermark-remover
Description
Remove visible Gemini AI watermarks from images via reverse alpha blending. Use for cleaning Gemini-generated images, removing the star/sparkle logo watermark.
README (SKILL.md)
Gemini Watermark Remover
Remove visible Gemini AI watermarks (star/sparkle logo) from generated images using mathematically accurate reverse alpha blending.
Fully offline — pure Python, local processing only, images are not uploaded.
When to Use
- Remove watermark from Gemini AI generated images
- Clean images before publishing or sharing
- Batch process multiple images
Quick Start
Install Dependencies (one-time)
pip install Pillow numpy
Usage
# Single image (auto-detect watermark)
python3 scripts/remove_watermark.py photo.jpg
# Specify output path
python3 scripts/remove_watermark.py photo.jpg -o clean_photo.jpg
# Force removal without detection
python3 scripts/remove_watermark.py photo.jpg -o clean.jpg --force
How It Works
Gemini adds watermark using alpha blending:
watermarked = alpha * 255 + (1 - alpha) * original
Reverse the equation:
original = (watermarked - alpha * 255) / (1 - alpha)
Detection Rules
| Image Size | Watermark Size | Right Margin | Bottom Margin |
|---|---|---|---|
| Width > 1024 AND Height > 1024 | 96×96 | 64px | 64px |
| Otherwise | 48×48 | 32px | 32px |
Key Points
- Uses built-in watermark templates (
assets/bg_48.png/assets/bg_96.png) - Alpha map = max RGB channel value (not alpha channel)
- Includes noise filtering (ALPHA_NOISE_FLOOR)
- Pure mathematical method, pixel-level accuracy
Limitations
- Removes only visible watermark (bottom-right semi-transparent logo)
- Cannot remove invisible watermarks (e.g., SynthID)
- Designed for current Gemini watermark pattern
Dependencies
- Python 3
- Pillow (PIL)
- NumPy
Usage Guidance
This skill appears coherent and local-only, but before running any third-party script: (1) inspect the full scripts/remove_watermark.py for any unexpected network calls or filesystem operations (the provided excerpt looks local-only), (2) run in an isolated environment or VM if you are unsure, (3) confirm you have the legal right to remove watermarks for the images you process, and (4) install dependencies into a virtualenv to avoid affecting system Python packages.
Capability Analysis
Type: OpenClaw Skill
Name: gemini-watermark-remover
Version: 1.1.2
The skill bundle provides a legitimate utility for removing Gemini AI watermarks from images using a local Python script. The implementation in `scripts/remove_watermark.py` uses mathematically sound reverse alpha blending with embedded base64-encoded watermark templates to process images offline. There are no signs of data exfiltration, network communication, or malicious code execution; the script relies solely on standard libraries like Pillow and NumPy for image manipulation.
Capability Assessment
Purpose & Capability
Name/description claim removing Gemini visible watermarks; included script and README implement a reverse alpha-blending algorithm with embedded watermark templates. No unrelated binaries, env vars, or external services are requested.
Instruction Scope
SKILL.md instructs only local usage (pip install Pillow/numpy and run scripts/remove_watermark.py). It does not direct reading unrelated system files, sending data to remote endpoints, or accessing credentials. The script embeds templates and operates on local images.
Install Mechanism
No install spec; this is instruction-only with a bundled Python script and requirements.txt. Dependency installation via pip is reasonable and expected for a Python image-processing tool. No remote downloads or nonstandard installers are used.
Credentials
No environment variables, credentials, or config paths are required. The requested dependencies (Pillow, NumPy) are appropriate for image processing.
Persistence & Privilege
Skill does not request always:true or modify system/other-skill configs. Default invocation settings are used; the skill is user-invocable and not forced into all agent runs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install gemini-watermark-remover - After installation, invoke the skill by name or use
/gemini-watermark-remover - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.2
Update Chinese README
v1.1.1
Update README to reflect embedded templates
v1.1.0
Embed templates in code for reliable distribution
v1.0.3
Include assets in scripts folder
v1.0.2
Ensure assets included
v1.0.1
Added file manifest to README
v1.0.0
Initial release of gemini-watermark-remover.
- Removes visible Gemini AI star/sparkle watermarks from images using reverse alpha blending.
- Fully offline; processes images locally with no uploads.
- Supports automatic watermark detection and batch processing.
- Provides pixel-level accuracy and noise filtering.
- Simple usage via command line, with options for output path and forced removal.
- Requires Python 3, Pillow, and NumPy.
Metadata
Frequently Asked Questions
What is Gemini Watermark Remover?
Remove visible Gemini AI watermarks from images via reverse alpha blending. Use for cleaning Gemini-generated images, removing the star/sparkle logo watermark. It is an AI Agent Skill for Claude Code / OpenClaw, with 476 downloads so far.
How do I install Gemini Watermark Remover?
Run "/install gemini-watermark-remover" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Gemini Watermark Remover free?
Yes, Gemini Watermark Remover is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Gemini Watermark Remover support?
Gemini Watermark Remover is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Gemini Watermark Remover?
It is built and maintained by FZLR (@fzlra); the current version is v1.1.2.
More Skills