
Watermark Removal
This does what it says: removes watermarks from images using four different methods depending on your priority. The smart routing is nice, it auto-detects Google SynthID watermarks and uses the aggressive crop method that's proven to work, while falling back to ML-based inpainting for everything else. The inpaint method preserves dimensions and works on any watermark type, which matters more than you'd think when you're cleaning up stock photos or AI-generated images for production. Batch processing is built in, though you'll want to check dimensions first since some methods crop 120px off the corner. It's honest about tradeoffs: speed versus quality, cropping versus preservation.
- skills.sh installs
- 128
- last updated
- Jun 3, 2026
Install
$ npx -y skills add horace4444/extend-my-claude-code --skill watermark-removal --agent claude-codeInstalls into .claude/skills of the current project.
Files
Universal Watermark Removal
Remove watermarks from ANY image source using intelligent detection and proven methods. Smart routing: automatically detects Google SynthID and uses the proven aggressive method, falls back to ML inpainting for unknown watermark types.
Quick Start
Single Image - Smart Auto-Detection (Recommended)
# Smart detection: Google SynthID → aggressive method (proven), Unknown → inpaint (ML)
python .claude/skills/watermark-removal/scripts/remove-watermark.py \
input.png \
output.png
Single Image - Preserve Dimensions (Force ML)
# Force ML inpainting even for Google SynthID (preserves exact dimensions)
python .claude/skills/watermark-removal/scripts/remove-watermark.py \
input.png \
output.png \
--method inpaint
Batch Processing (Get User Approval First!)
⚠️ IMPORTANT: Always ask user before batch processing, especially with crop/aggressive methods that alter dimensions.
# Recommended: Preserves dimensions
python .claude/skills/watermark-removal/scripts/batch-process.py \
/path/to/input-dir \
/path/to/output-dir \
--method inpaint
Sponsors
Details
- Repository
- github.com/horace4444/extend-my-claude-code
- First seen
- Jun 3, 2026