# YaoFANGUK/video-subtitle-remover

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

Repository: https://github.com/YaoFANGUK/video-subtitle-remover
Canonical: https://ross.abutalabs.com/products/video-subtitle-remover
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, deepleanring, vsr, sub-remove, subtile
Last push: 2026-06-30T01:06:52+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 46, longevity 74
- inputs: {"age_days": 1043, "days_push": 65, "days_rel": 146, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 12553, forks 1598 (observed 2026-08-28T04:10:59.299826+00:00)

## What it is
An AI-based desktop application that removes hard-coded subtitles and text-like watermarks from videos and images using deep learning inpainting, preserving original resolution. It runs fully locally with no third-party API, with prebuilt packages for CPU, DirectML, and NVIDIA CUDA GPUs.

## Use cases
- remove hard-coded subtitles from a video
- erase text watermarks from images
- clean burned-in subtitles without losing resolution
- batch remove watermarks from multiple pictures
- remove subtitles only in a specified region of a video
- extract subtitles then remove them from footage

## When to choose
- you need to remove burned-in subtitles or text watermarks locally without uploading media to a cloud API
- you want resolution-preserving AI inpainting rather than blur or mosaic
- you have an NVIDIA GPU (or want CPU/DirectML fallback) and want prebuilt Windows packages or Docker images

## When to avoid
- you need to remove soft/embedded subtitle tracks, which can be stripped directly with tools like ffmpeg
- you have no GPU and need fast processing of long videos
- you need a lightweight library to integrate into your own pipeline rather than a standalone application

## Facets
- artifact type: application
- maturity: active
- function: image-processing, video-processing, machine-learning, ocr
- domain: computer-vision, image-processing, deep-learning
- platform: windows, python
- tags: subtitle-removal, watermark-removal, video-inpainting, hard-subtitles, ai-inpainting, video, macos, linux, docker, gpu

## Member repositories
- YaoFANGUK/video-subtitle-remover (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:59.299826+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 2026-08-29T17:13:58.520766+00:00, confidence not recorded.
  - readme: https://github.com/YaoFANGUK/video-subtitle-remover (fetched 2026-08-28T04:10:59.299826+00:00, sha 8cbc568f2667)
- Data as of 2026-08-30T08:39:29.467469+00:00.