Search

PythonReactSEOPDF
OpenClaw

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.

fzlra0 source installs☆ 0 Repository stars

Installation

Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.

SkillHub CLI

skillhub install fzlra/gemini-watermark-remover

Inspect the source and compatibility requirements, then follow its installation steps.

Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.

View source ↗Guides

Skill instructions

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

Source information

Source
github
Repository
openclaw/skills
Path
skills/fzlra/gemini-watermark-remover
Version
—
Commit
6d66b9bbef02d6d6e06c7867ad8904cd74b88415
Classification source
rules
Status
active
Visibility
public

These signals come from indexed source analysis and may lag behind changes. Check the current source files.

README

Gemini Watermark Remover

English | 中文


Remove visible Gemini AI watermarks from images using reverse alpha blending algorithm.

⚠️ Disclaimer

This tool is for personal learning and research only. Commercial use is prohibited.

Features

  • ✅ Pure local processing (images not uploaded)
  • ✅ Reverse alpha blending algorithm, lossless watermark removal
  • ✅ Automatic watermark size detection (48×48 or 96×96)
  • ✅ Standalone script with embedded templates (no external dependencies)

Installation

pip install Pillow numpy

Usage

# Basic usage
python3 scripts/remove_watermark.py image.jpg

# Specify output
python3 scripts/remove_watermark.py image.jpg -o cleaned.jpg

Algorithm

Gemini uses alpha blending:

watermarked = α × 255 + (1 - α) × original

Reverse:

original = (watermarked - α × 255) / (1 - α)

Files

├── scripts/
│   └── remove_watermark.py   # Main script with embedded templates
├── requirements.txt
├── README.md
├── README_zh.md
└── LICENSE

License

MIT License

Extracted content

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)

```bash
pip install Pillow numpy
```

### Usage

```bash
# 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
README
# Gemini Watermark Remover

[English](./README.md) | [中文](./README_zh.md)

---

Remove visible Gemini AI watermarks from images using reverse alpha blending algorithm.

## ⚠️ Disclaimer

**This tool is for personal learning and research only. Commercial use is prohibited.**

## Features

- ✅ Pure local processing (images not uploaded)
- ✅ Reverse alpha blending algorithm, lossless watermark removal
- ✅ Automatic watermark size detection (48×48 or 96×96)
- ✅ Standalone script with embedded templates (no external dependencies)

## Installation

```bash
pip install Pillow numpy
```

## Usage

```bash
# Basic usage
python3 scripts/remove_watermark.py image.jpg

# Specify output
python3 scripts/remove_watermark.py image.jpg -o cleaned.jpg
```

## Algorithm

Gemini uses alpha blending:
```
watermarked = α × 255 + (1 - α) × original
```

Reverse:
```
original = (watermarked - α × 255) / (1 - α)
```

## Files

```
├── scripts/
│   └── remove_watermark.py   # Main script with embedded templates
├── requirements.txt
├── README.md
├── README_zh.md
└── LICENSE
```

## License

[MIT License](./LICENSE)

Related skills

OpenClaw

ad-compliance-reviewer

danyangliu-sandwichlab

Review ads and campaign setup for policy compliance on Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Amazon Ads, and DSP/programmatic.

OpenClaw

afrexai-seo-content-engine

1kalin

Complete SEO content creation system for AI agents. Research keywords, analyze competitors, write optimized articles, and track rankings — all through natural conversation. No APIs required.