#77 · Primary category: Computer Vision
remove-ai-watermarks
Remove visible and invisible AI watermarks and provenance metadata from images and video. Python library and CLI for SynthID, C2PA, EXIF, IPTC, XMP, and common generative-AI marks.
Project last updated:08/30/26
GitHub Stars
5.3K
Forks
499
Contributors
7
License
Apache-2.0
Why we included this project
Anyone who generates images with Gemini or Nano Banana has seen the sparkle badge and the provenance metadata those models attach to every output. This tool removes that from content you made yourself: known visible vendor marks, C2PA and EXIF and IPTC metadata, and, when you have a GPU, a diffusion pass that disrupts the invisible SynthID watermark. It works as a CLI or a Python library, so you can clean one file interactively or script a batch run over a folder. Video gets the same treatment, with provenance identification and visible mark removal for Sora, Veo, Kling, and others. The project is deliberately scoped to content you own rather than third-party paid previews, which keeps it a cleanup tool for your own work instead of something aimed at copying other people's paid content.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)