{"id":20067705,"url":"https://github.com/ae9is/ezsam","last_synced_at":"2025-05-05T19:30:46.661Z","repository":{"id":220821711,"uuid":"740798129","full_name":"ae9is/ezsam","owner":"ae9is","description":"Extract objects from images or video via text prompt","archived":false,"fork":false,"pushed_at":"2024-08-01T07:38:23.000Z","size":7412,"stargazers_count":5,"open_issues_count":2,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-10-01T15:41:17.589Z","etag":null,"topics":["ai","background","extract","filter","foreground","grounded-segment-anything","groundingdino","image-editing","object-detection","prompt","remove","segment","segment-anything","select","subtract","video-editing"],"latest_commit_sha":null,"homepage":"https://www.ezsam.org/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ae9is.png","metadata":{"files":{"readme":"README.md","changelog":null,"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}},"created_at":"2024-01-09T04:52:31.000Z","updated_at":"2024-08-15T16:09:32.000Z","dependencies_parsed_at":"2024-02-21T00:55:20.650Z","dependency_job_id":"e484e93d-e363-4db2-9ed7-32d3bb488a10","html_url":"https://github.com/ae9is/ezsam","commit_stats":null,"previous_names":["ae9is/ezsam"],"tags_count":4,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ae9is%2Fezsam","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ae9is%2Fezsam/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ae9is%2Fezsam/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ae9is%2Fezsam/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ae9is","download_url":"https://codeload.github.com/ae9is/ezsam/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224461815,"owners_count":17315116,"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":["ai","background","extract","filter","foreground","grounded-segment-anything","groundingdino","image-editing","object-detection","prompt","remove","segment","segment-anything","select","subtract","video-editing"],"created_at":"2024-11-13T14:03:06.018Z","updated_at":"2024-11-13T14:03:06.782Z","avatar_url":"https://github.com/ae9is.png","language":"Python","readme":"*Update: [SAM 2 extends SAM to video](https://github.com/facebookresearch/sam2). You might still find ezsam useful for small GIFs or image batches.*\n\n# ezsam (easy segment anything model)\n\nA command line and gui tool to segment images and video via text prompts.\n\nInput images and videos, describe the subjects or objects you want to keep, and output new images and videos with the background removed.\n\n**Check out the docs! [ezsam.org](https://www.ezsam.org)**\n\n\u003cp\u003e\n  \u003cimg src=\"examples/car-3.gui.png\" height=200 /\u003e\n  \u003cimg src=\"examples/food.gif\" height=200 alt=\"A large table with plates of Thanksgiving food including a whole turkey on a conveyor-style lazy susan.\" /\u003e\n  \u003cimg src=\"examples/food.turkey.gif\" height=200 alt=\"A whole cooked turkey flying through the void.\" /\u003e\n\u003c/p\u003e\n\n\u003cimg src=\"examples/car-3.both.png\" width=150 /\u003e\n\n\u003cimg src=\"examples/car-3.black.png\" width=150 /\u003e\n\n\u003cimg src=\"examples/car-3.nowheels.png\" width=150 /\u003e\n\n## Why?\n\nMeta's [Segment Anything](https://github.com/facebookresearch/segment-anything) is a powerful tool for separating parts of images,\nbut requires coordinate prompts\u0026mdash;either bounding boxes or points.\nAnd manual prompt generation is tedious for large collections of still images or video.\n\nIn contrast, text-based prompts describing the object(s) in the foreground to segment can be constant.\nInspired by [Grounded-Segment-Anything](https://github.com/IDEA-Research/Grounded-Segment-Anything),\nthis project tries to package a simpler to use tool.\n\nIf you're not interested in text-based prompts with Segment Anything, \ncheck out [rembg](https://github.com/danielgatis/rembg).\n\n## How does it work?\n\nThe foreground is selected using text prompts to [GroundingDINO](https://github.com/IDEA-Research/GroundingDINO) to detect objects.\nImage segments are generated using [Segment Anything](https://github.com/facebookresearch/segment-anything) \nor [Segment Anything HQ (SAM-HQ)](https://github.com/SysCV/SAM-HQ).\n\n## Quick start\n\n```bash\n# Ubuntu 22.04, Python 3.9 - 3.11\npip install ezsam\nsudo apt install ffmpeg imagemagick\nezsam --help\nezsam-gui\n```\n\nFor more detailed info, see the documentation site here: [ezsam.org](https://www.ezsam.org)\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fae9is%2Fezsam","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fae9is%2Fezsam","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fae9is%2Fezsam/lists"}