Strip multi-vendor AI provenance marks: Unicode text hygiene, statistical rewrite hooks, and C2PA/metadata from PNG/JPEG/SVG/PDF/DOCX/HTML/MD
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.
Remove invisible AI watermarks (SynthID, StableSignature, TreeRing) and strip AI metadata from images. Open-source CLI & Python toolkit.
Cross platform CLI tool for removing watermarks from images and videos generated by Google Gemini, Veo, and NotebookLM.
🍌 Remove invisible AI watermarks from Google Gemini images — npm package
AI watermark removal built for Apple Silicon. SynthID-class pixel regeneration, visible vendor labels and provenance metadata, with every pipeline decision measured on Metal.
Invisible, key-verifiable watermarks for AI/LLM-generated text — SynthID-Text-style, in Rust + WebAssembly (Node + browser). Live playground included.
A specialized tool for removing invisible AI watermarks, such as Google SynthID, from images.
Clean. Detect. Generate. In Seconds.
Strip EXIF, GPS, C2PA / Content Credentials, AI watermarks, and Stable Diffusion / ComfyUI / Midjourney / ChatGPT prompt blocks from any image. Three modes: safe (pixel-identical), paranoid (re-encode), nuclear (disrupt SynthID/Digimarc). CLI + macOS desktop app. 100% offline.
ComfyUI custom nodes for detecting provenance marks, removing visible and invisible AI watermarks, stripping metadata, and erasing selected regions.
Remove invisible AI watermarks and manage metadata from images generated by popular AI models like DALL-E, Midjourney, and Stable Diffusion.
AI watermarker for images and text that replicates SynthID's functionality.
Automatically remove SynthID from any image
Find and remove AI provenance signals from files you own: hidden Unicode, token watermarks, visible image marks, and C2PA/EXIF/XMP metadata. Zero-dependency Python 3.10+ core; models, GPUs, and system binaries sit behind opt-in adapters.
Research demo: scrub generative text watermarks (e.g. SynthID-Text) via H-token sliding-window MLM token replacement. Gradio UI, multilingual (ModernBERT / mmBERT).
An invisible watermark is still a signal. A lightweight CNN ensemble that detects SynthID — the imperceptible watermark in ChatGPT / GPT-Image-2 images — trained on a laptop and validated against the official verifier.
Check any text for the traces AI chat interfaces leave behind — Claude HTML class names, zero-width characters, exotic Unicode spaces. Zero dependencies, MIT, runs offline.
Add a description, image, and links to the synthid topic page so that developers can more easily learn about it.
To associate your repository with the synthid topic, visit your repo's landing page and select "manage topics."