{"id":21577883,"url":"https://github.com/leeyunjai/image2text","last_synced_at":"2025-07-03T17:32:32.469Z","repository":{"id":172579615,"uuid":"616308061","full_name":"leeyunjai/image2text","owner":"leeyunjai","description":"caption generator using lavis and argostranslate","archived":false,"fork":false,"pushed_at":"2023-03-21T01:11:20.000Z","size":131,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-10T17:41:51.260Z","etag":null,"topics":["blip2","caption","caption-generation","caption-generator","captioning-images","captions","image-analysis","image-text","img2txt"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/leeyunjai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-03-20T06:01:14.000Z","updated_at":"2024-02-20T15:05:20.000Z","dependencies_parsed_at":null,"dependency_job_id":"0b36c60d-5148-4483-9c2a-aa048722314d","html_url":"https://github.com/leeyunjai/image2text","commit_stats":{"total_commits":8,"total_committers":2,"mean_commits":4.0,"dds":0.5,"last_synced_commit":"61c3969f74bc04d0eba52d801df4712d37e4573d"},"previous_names":["leeyunjai/image2text"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/leeyunjai/image2text","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leeyunjai%2Fimage2text","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leeyunjai%2Fimage2text/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leeyunjai%2Fimage2text/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leeyunjai%2Fimage2text/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/leeyunjai","download_url":"https://codeload.github.com/leeyunjai/image2text/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/leeyunjai%2Fimage2text/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263369559,"owners_count":23456321,"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":["blip2","caption","caption-generation","caption-generator","captioning-images","captions","image-analysis","image-text","img2txt"],"created_at":"2024-11-24T13:08:53.846Z","updated_at":"2025-07-03T17:32:32.425Z","avatar_url":"https://github.com/leeyunjai.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# image2text\ncaption generator using lavis, argostranslate.\n\ndeploy gradio.\n\n\u003cpre\u003e\npip3 install -r requirements.txt\n\u003c/pre\u003e\n\n\u003cpre\u003e\npython3 main.py\n\u003c/pre\u003e\n\nIf you want to use GPU, Edit main.py\n\u003cpre\u003e\n# main\ncap = captionModel(\"cpu\") ## cuda\ntrans = translateModel(\"cpu\") ## cuda\ndemo.launch(share=True) \n\u003c/pre\u003e\n\nIf you want to change caption model, Edit caption.py\n\u003cpre\u003e\n# blip \n#model, vis_processors, _ = load_model_and_preprocess(name=\"blip_caption\", model_type=\"large_coco\", is_eval=True, device=device)\n\n# blip2 coco_opt2.7b\nself.model, self.vis_processors, _ = load_model_and_preprocess(name=\"blip2_opt\", model_type=\"caption_coco_opt2.7b\", is_eval=True, device=self.device)\n\n# blip2 coco_opt6.7b\nself.model, self.vis_processors, _ = load_model_and_preprocess(name=\"blip2_opt\", model_type=\"caption_coco_opt6.7b\", is_eval=True, device=self.device)\n\u003c/pre\u003e\n![bg](bg.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fleeyunjai%2Fimage2text","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fleeyunjai%2Fimage2text","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fleeyunjai%2Fimage2text/lists"}