design

Remove AI Watermarks with remove-ai-watermarks

Name: Remove AI Watermarks with remove-ai-watermarks
Author: wiltodelta

Strip AI watermarks from images with this CLI and Python library, ideal for startup founders, backed by 3.9k+ GitHub stars

From the repo · “AI watermark remover. CLI and Python library to strip visible and invisible AI watermarks (Gemini / Nano Banana sparkle, SynthID) and provenance metadata (C2PA, EXIF, IPTC) from images.”

6,089 stars+85★ this week565 forksPythonGuide quality 9/10 · reviewed Jul 7Updated 10/22/2026100% free · open source

What it does

Remove AI watermarks and provenance metadata from images using a CLI and Python library

When to use it

•When you need to use AI-generated images without visible or invisible watermarks
•When you want to remove provenance metadata like C2PA, EXIF, or IPTC from images
•When you're working with images that have Gemini, Nano Banana sparkle, or SynthID watermarks

Ready-to-paste prompt

remove-ai-watermarks -w synthid -v input_image.png cleaned_image.png

Heads up: The tool requires Python 3.8 or later to run, so make sure your Python version is up-to-date before installing and using the library

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/remove-ai-watermarks && curl -fsSL https://workflowstacks.com/api/skills/remove-ai-watermarks/claude-skill -o ~/.claude/skills/remove-ai-watermarks/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Remove AI Watermarks with remove-ai-watermarks works

Codeflow

Free to inspect

Remove AI Watermarks with remove-ai-watermarks is a very large Python project (~61k lines across 170 code files, plus 126 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~61k lines · 170 code files · ~8 h to skim

Setup

Install as a skill / plugin

Add it to Claude Code (or your AI tool) with one command — 3 skills inside. Nothing to run yourself.

Runs on

Inside your AI tool

Helper scripts use Python · needs API keys

Python 100%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
CLAUDE.md
The instructions the AI actually follows
3
.env.example
The API keys and settings you must provide
4
src/remove_ai_watermarks/__init__.py
Inside src/ — the main logic begins here

What's in each folder

src/Core code — the actual logic82 files

skills/Prompts, skills & agent definitions5 files

docs/Documentation46 files

data/Data files143 files

scripts/Helper scripts122 files

.claude-plugin/Plugin manifest — what gets installed1 files

typings/Folder1 files

tests/Tests — proof it works126 files

READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/remove-ai-watermarks && curl -fsSL https://workflowstacks.com/api/skills/remove-ai-watermarks/claude-skill -o ~/.claude/skills/remove-ai-watermarks/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

wiltodelta

Language

Python