{"id":19965494,"url":"https://github.com/rafaykhattak/captionify","last_synced_at":"2025-09-19T17:31:08.747Z","repository":{"id":161543471,"uuid":"636238351","full_name":"RafayKhattak/Captionify","owner":"RafayKhattak","description":"With Captionify, users can upload an image or enter an image URL to generate a descriptive caption that accurately describes the contents of the image.","archived":false,"fork":false,"pushed_at":"2023-05-04T14:17:11.000Z","size":17,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-02T16:50:52.253Z","etag":null,"topics":["deep-neural-networks","encoder-decoder-model","gpt-2","transfer-learning","transformer","vision-transformer"],"latest_commit_sha":null,"homepage":"https://rafaykhattak-captionify-app-btvva7.streamlit.app/","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/RafayKhattak.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-05-04T12:07:07.000Z","updated_at":"2025-01-13T20:26:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"09dbab41-b5f2-4efe-835d-52e2618f7605","html_url":"https://github.com/RafayKhattak/Captionify","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/RafayKhattak/Captionify","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RafayKhattak%2FCaptionify","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RafayKhattak%2FCaptionify/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RafayKhattak%2FCaptionify/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RafayKhattak%2FCaptionify/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RafayKhattak","download_url":"https://codeload.github.com/RafayKhattak/Captionify/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RafayKhattak%2FCaptionify/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":275974518,"owners_count":25562672,"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","status":"online","status_checked_at":"2025-09-19T02:00:09.700Z","response_time":108,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["deep-neural-networks","encoder-decoder-model","gpt-2","transfer-learning","transformer","vision-transformer"],"created_at":"2024-11-13T02:29:10.351Z","updated_at":"2025-09-19T17:31:08.499Z","avatar_url":"https://github.com/RafayKhattak.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Captionify\nCaptionify is a web application that generates a descriptive caption for an image using an encoder-decoder architecture. The application uses a pre-trained Transformer-based vision model (ViT) as an encoder and a pre-trained language model (GPT2) as a decoder to generate highly accurate captions for uploaded images or image URLs.\n![Screenshot (437)](https://user-images.githubusercontent.com/90026724/236234966-71693df3-f3a7-45f2-8a90-109c85315d6e.png)\n## Usage\nTo use Captionify, simply upload an image or enter an image URL on the web interface. The tool will then use the pre-trained models to generate a descriptive caption that accurately describes the contents of the image.\n## Getting Started\nTo install Captionify, simply clone this repository and install the necessary dependencies using pip:\n```\ngit clone https://github.com/\u003cusername\u003e/\u003crepository\u003e.git\ncd \u003crepository\u003e\n```\nInstall the required dependencies using the following command:\n```\npip install -r requirements.txt\n```\nThen run the app.py file using the following command:\n```\nstreamlit run app.py\n```\nThis will launch the application on your local machine. You can then upload an image or enter an image URL to generate a descriptive caption.\n## Architecture\nCaptionify uses an encoder-decoder architecture to generate captions for images. The encoder is a pre-trained Transformer-based vision model (ViT) that encodes the input image into a sequence of feature vectors. The decoder is a pre-trained language model (GPT2) that generates a descriptive caption for the image based on the encoded features.\n\n![vit_architecture](https://user-images.githubusercontent.com/90026724/236233200-745dae6a-569f-4558-9a12-3a56b0b8a872.jpg)\n## Dependencies\n- streamlit\n- requests\n- Pillow\n- transformers\n- torch\n## References\n- This project is based on the Encoder-Decoder architecture and uses pre-trained models from the Hugging Face Transformers library.\n- The application was developed using Streamlit, an open-source app framework for Machine Learning and Data Science projects.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frafaykhattak%2Fcaptionify","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frafaykhattak%2Fcaptionify","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frafaykhattak%2Fcaptionify/lists"}