{"id":13487721,"url":"https://github.com/ZichengDuan/TheChosenOne","last_synced_at":"2025-03-27T23:31:32.179Z","repository":{"id":208569294,"uuid":"720625137","full_name":"ZichengDuan/TheChosenOne","owner":"ZichengDuan","description":"Unofficial implementation of the paper \"The Chosen One: Consistent Characters in Text-to-Image Diffusion Models\"","archived":false,"fork":false,"pushed_at":"2024-12-10T07:55:48.000Z","size":7081,"stargazers_count":250,"open_issues_count":13,"forks_count":24,"subscribers_count":9,"default_branch":"main","last_synced_at":"2024-12-10T08:32:11.860Z","etag":null,"topics":["deep-learning","diffusion","dinov2","generative-art","generative-model"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2311.10093","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/ZichengDuan.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":"2023-11-19T03:51:01.000Z","updated_at":"2024-12-10T07:55:51.000Z","dependencies_parsed_at":"2024-10-30T23:40:40.569Z","dependency_job_id":null,"html_url":"https://github.com/ZichengDuan/TheChosenOne","commit_stats":null,"previous_names":["zichengduan/the-chosen-one","zichengduan/the_chosen_one"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZichengDuan%2FTheChosenOne","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZichengDuan%2FTheChosenOne/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZichengDuan%2FTheChosenOne/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ZichengDuan%2FTheChosenOne/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ZichengDuan","download_url":"https://codeload.github.com/ZichengDuan/TheChosenOne/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245944019,"owners_count":20697945,"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":["deep-learning","diffusion","dinov2","generative-art","generative-model"],"created_at":"2024-07-31T18:01:02.727Z","updated_at":"2025-03-27T23:31:32.162Z","avatar_url":"https://github.com/ZichengDuan.png","language":"Python","funding_links":[],"categories":["Personalized Restoration"],"sub_categories":[],"readme":"# The Chosen One: Consistent Characters in Text-to-Image Diffusion Models (Unofficial implementation)\n# [Dec 2024] Please note that this Repo is not actively maintained.\n\nThis repository contains the **unofficial** PyTorch implementation of the paper [The Chosen One: Consistent Characters in Text-to-Image Diffusion Models](https://arxiv.org/abs/2311.10093), using the Diffuser framework. \n\n![Main pipeline](https://github.com/ZichengDuan/TheChosenOne/blob/main/misc/main.png?raw=true)\n![Result](https://github.com/ZichengDuan/TheChosenOne/blob/main/misc/result_1.png?raw=true)\n\n(Note that I didn't carefully adjust the hyperparameters for generating the results above and they are still good enough.)\n\n## Getting Started\n\n### Installation and Prerequisites\nInstall diffuser `0.24.0.dev0`:\n```\ngit clone https://github.com/huggingface/diffusers\ncd diffusers\npip install .\n```\n\nClone the repository and install the required packages:\n```\ngit clone git@github.com:ZichengDuan/TheChosenOne.git\ncd TheChosenOne\npip install -r requirements.txt\n```\nYou also need to modify your configuration file in `config/theChosenOne.yaml` to fit your local environment.\n\n### Data backup folder preparation\nYou need to create a backup data folder to store the initial images generated in the first loop for faster training start up next time if you want to train on the same character again.\nThis is set up in the configuration file as follows:\n``` \nbackup_data_dir_root: Your absolute path to the data folder\n```\n\n## Run the codes\n### Training\n```\npython main.py\n```\n\n### Inference\nSimply run:\n```\npython inference.py\n```\nThe script will load the model you designated in the `inference.py` and your config file.\n\n\n### Citing the paper\nPlease always remember to respect the authors and cite their work properly. 🫡\n```\n@article{avrahami2023chosen,\n  title={The Chosen One: Consistent Characters in Text-to-Image Diffusion Models},\n  author={Avrahami, Omri and Hertz, Amir and Vinker, Yael and Arar, Moab and Fruchter, Shlomi and Fried, Ohad and Cohen-Or, Daniel and Lischinski, Dani},\n  journal={arXiv preprint arXiv:2311.10093},\n  year={2023}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FZichengDuan%2FTheChosenOne","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FZichengDuan%2FTheChosenOne","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FZichengDuan%2FTheChosenOne/lists"}