# D-Ogi/WatermarkRemover-AI

AI-Powered Watermark Remover using Florence-2 and LaMA: Remove watermarks from images and videos, including AI-generated content from Sora, Runway, and others. Features a modern PyWebview GUI.

Repository: https://github.com/D-Ogi/WatermarkRemover-AI
Canonical: https://ross.abutalabs.com/products/watermarkremover-ai
Language: HTML
License: MIT
License Family: permissive
Topics: florence-2, lama-cleaner, watermark-remover, dataset-creation, inpainting
Last push: 2026-03-29T20:46:06+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 74, release rhythm 35, longevity 53
- inputs: {"age_days": 743, "days_push": 157, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1859, forks 369 (observed 2026-08-28T04:05:45.270294+00:00)

## What it is
An AI-powered desktop application that detects and removes watermarks from images and videos using Microsoft's Florence-2 for detection and LaMA for inpainting. It offers a PyWebview-based GUI plus a CLI, with batch processing, GPU acceleration, and support for AI-generated video watermarks.

## Use cases
- remove watermarks from images
- remove watermark from Sora or Runway AI-generated videos
- batch clean watermarks from a folder of photos
- inpaint watermark regions naturally in video frames
- preview detected watermark masks before processing
- create clean datasets by stripping watermarks

## When to choose
- you need AI-based watermark detection and inpainting rather than manual editing
- you want a GUI with batch processing and preview mode
- you need to clean watermarks from AI-generated videos like Sora or Runway
- you want both GUI and CLI workflows with CUDA acceleration

## When to avoid
- you need legally authorized content only - removing watermarks may violate copyright or terms of service
- you need a lightweight tool without downloading large AI models
- you require real-time or streaming video watermark removal
- you need a web-based or mobile solution

## Facets
- artifact type: application
- maturity: active
- function: image-processing, video-processing, machine-learning, gui, cli
- domain: image-processing, artificial-intelligence, media
- platform: windows, python
- tags: watermark-removal, inpainting, florence-2, lama, pywebview, batch-processing, ai-generated-video, video, linux, macos, desktop, gpu

## Member repositories
- D-Ogi/WatermarkRemover-AI (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:45.270294+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:15:57.666888+00:00, confidence not recorded.
  - readme: https://github.com/D-Ogi/WatermarkRemover-AI (fetched 2026-08-28T04:05:45.270294+00:00, sha 102fe6e7cc45)
- Data as of 2026-08-30T08:39:29.467469+00:00.