{"id":17908196,"url":"https://github.com/y-t-g/blur-anything","last_synced_at":"2025-03-23T20:31:05.941Z","repository":{"id":162159295,"uuid":"636757229","full_name":"Y-T-G/Blur-Anything","owner":"Y-T-G","description":"Track and blur any object or person in a video.","archived":false,"fork":false,"pushed_at":"2024-02-10T07:53:22.000Z","size":167,"stargazers_count":10,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-19T00:38:54.163Z","etag":null,"topics":["blurring","mobilesam","segment-anything","track-anything","xmem"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Y-T-G.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-05-05T15:13:06.000Z","updated_at":"2024-12-27T21:15:13.000Z","dependencies_parsed_at":null,"dependency_job_id":"d5694348-e488-439c-aa49-5a2eb7481e15","html_url":"https://github.com/Y-T-G/Blur-Anything","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Y-T-G%2FBlur-Anything","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Y-T-G%2FBlur-Anything/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Y-T-G%2FBlur-Anything/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Y-T-G%2FBlur-Anything/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Y-T-G","download_url":"https://codeload.github.com/Y-T-G/Blur-Anything/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245164804,"owners_count":20571186,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["blurring","mobilesam","segment-anything","track-anything","xmem"],"created_at":"2024-10-28T19:14:52.860Z","updated_at":"2025-03-23T20:31:00.847Z","avatar_url":"https://github.com/Y-T-G.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Blur Anything For Videos\n\n![Mentioned in Awesome OpenVINO](https://camo.githubusercontent.com/9dbe56f475e0abb1d07a9a18d841378c3d40325ae7df300f29491158cf38d013/68747470733a2f2f617765736f6d652e72652f6d656e74696f6e65642d62616467652d666c61742e737667)\n\nBlur Anything is an adaptation of the excellent [Track Anything](https://github.com/gaomingqi/Track-Anything) project which is in turn based on Meta's Segment Anything and XMem. It allows you to blur anything in a video, including faces, license plates, etc.\n\n\u003cdiv\u003e\n\u003ca src=\"https://img.shields.io/badge/%F0%9F%A4%97-Open_in_Spaces-informational.svg?style=flat-square\" href=\"https://huggingface.co/spaces/Y-T-G/Blur-Anything\"\u003e\n\u003cimg src=\"https://img.shields.io/badge/%F0%9F%A4%97-Open_in_Spaces-informational.svg?style=flat-square\"\u003e\n\u003c/a\u003e\n\u003c/div\u003e\n\n\u003cvideo src=\"https://media.githubusercontent.com/media/Y-T-G/Blur-Anything/main/assets/sample-1-blurred-stacked.mp4\"\u003e\u003c/video\u003e\n\n## Get Started\n```shell\n# Clone the repository:\ngit clone https://github.com/Y-T-G/Blur-Anything.git\ncd Blur-Anything\n\n# Install dependencies: \npip install -r requirements.txt\n\n# Run the Blur-Anything gradio demo.\npython app.py --device [cpu|cuda:0|cuda:1|...] --sam_model_type [vit_t| vit_b|vit_h| vit_l] [--backend [onnx|openvino]]\n```\n\n## Features\n\n- FastSAM with ONNX and OpenVINO support.\n- Lower memory usage.\n\n## To Do\n- [x] Add a gradio demo\n- [ ] Add support to use YouTube video URL\n- [ ] Add option to completely black out the object\n- [ ] Convert XMem to ONNX\n\n## Acknowledgements\n\nThe project is an adaptation of [Track Anything](https://github.com/gaomingqi/Track-Anything) which is based on [Segment Anything](https://github.com/facebookresearch/segment-anything) and [XMem](https://github.com/hkchengrex/XMem).\n\nThanks to [PIMS](https://github.com/soft-matter/pims) which is used to process video files while keeping memory usage low.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fy-t-g%2Fblur-anything","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fy-t-g%2Fblur-anything","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fy-t-g%2Fblur-anything/lists"}