From writing-workflows
Removes Gemini AI watermarks from images using Python CLI script with Pillow and reverse alpha blending. For batch-processing Gemini images or modifying the script.
npx claudepluginhub rookie-ricardo/erduo-skills --plugin writing-workflowsThis skill uses the workspace's default tool permissions.
- Python 3.9+
Removes Gemini logos, watermarks, or AI-generated image markers from images using OpenCV inpainting. Useful when users request logo or watermark removal from images.
Removes backgrounds from single or batch images using AI (rembg/U2-Net) or built-in white-to-transparent methods. Outputs PNG/WebP with transparency for photos, products, icons.
Generates and edits images via Gemini 2.0 Flash API using pure Python stdlib. Zero dependencies for locked-down environments, containers, or Fly.io free tier.
Share bugs, ideas, or general feedback.
pip install -r requirements.txt)cd skills/gemini-watermark-remover/scripts && pip install -r requirements.txtpython remove_watermark.py <input-image> <output-image>input-image: path to the Gemini watermarked imageoutput-image: path for the cleaned image (format inferred from extension)Example:
python remove_watermark.py ./in.png ./out.png
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.remove_watermark.py for one-off processing.references/algorithm.md.