{"id":21433030,"url":"https://github.com/randomtask2000/kohya_prep","last_synced_at":"2025-10-11T08:38:02.613Z","repository":{"id":218597050,"uuid":"746864381","full_name":"randomtask2000/Kohya_prep","owner":"randomtask2000","description":"Little image extractor and tagger from selfie video as input. The resulting images are meant to be used by Kohya to create a LoRA for something like SDLX","archived":false,"fork":false,"pushed_at":"2024-02-24T14:15:03.000Z","size":14,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-23T08:44:10.891Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/randomtask2000.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":"2024-01-22T20:29:03.000Z","updated_at":"2024-02-13T04:44:53.000Z","dependencies_parsed_at":"2024-01-26T05:31:59.829Z","dependency_job_id":"7875ef98-74d1-4f9d-a52b-3b357e5a1786","html_url":"https://github.com/randomtask2000/Kohya_prep","commit_stats":null,"previous_names":["randomtask2000/kohya_lora_vid2imgstagger","randomtask2000/kohya_prep"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/randomtask2000%2FKohya_prep","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/randomtask2000%2FKohya_prep/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/randomtask2000%2FKohya_prep/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/randomtask2000%2FKohya_prep/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/randomtask2000","download_url":"https://codeload.github.com/randomtask2000/Kohya_prep/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243945530,"owners_count":20372893,"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":[],"created_at":"2024-11-22T23:24:13.373Z","updated_at":"2025-10-11T08:37:57.573Z","avatar_url":"https://github.com/randomtask2000.png","language":"Python","readme":"# Kohya LoRA preprocessing\n\n## mov2Images.py\nLittle image extractor and tagger from selfie video as input. The resulting images are meant to be used by Kohya to create a LoRA for something like SDLX. The images reduced to 512x512.\n\n## resizeImages.py\nResizes images from a directory to an output directory. The images are reduced to 768x768.\n\n# Face Feature Extraction Program Installation \u0026 Execution Guide\n\nThis guide provides instructions on how to install the necessary dependencies and run the face feature extraction program.\n\n## Dependencies\n\n- Python 3.7 or higher\n- OpenCV\n- Face Recognition\n- NumPy\n\n## Installation\n\nFirst, ensure that you have Python 3.7 or higher installed on your system. You can download Python from the official website at https://www.python.org/downloads/.\n\nAfter installing Python, you can install the required Python packages using `pip`. Open a terminal or command prompt and run the following commands:\n\n```sh\npip install opencv-python\npip install face_recognition\npip install numpy\n```\n\n## Note\nThe image or video file path should point to a valid `.png`, `.jpg`, `.jpeg`, or `.mov` file.\nThe output directory should be a valid directory on your filesystem where the program has write access.\nIf processing a video, the program will process each frame asynchronously and may take some time to complete, depending on the video length and resolution.\n\nMake sure to copy the Python script into a file named `create.py` and follow the installation guide above to set up your environment. After installation, you'll be able to run the script as instructed.\n\n## Enjoy!\nMake this better if you can - cheers!\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frandomtask2000%2Fkohya_prep","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frandomtask2000%2Fkohya_prep","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frandomtask2000%2Fkohya_prep/lists"}