{"id":15027856,"url":"https://github.com/mchong6/jojogan","last_synced_at":"2025-05-16T06:04:38.331Z","repository":{"id":38612773,"uuid":"439414271","full_name":"mchong6/JoJoGAN","owner":"mchong6","description":"Official PyTorch repo for JoJoGAN: One Shot Face Stylization","archived":false,"fork":false,"pushed_at":"2022-09-29T18:53:09.000Z","size":78444,"stargazers_count":1427,"open_issues_count":18,"forks_count":204,"subscribers_count":25,"default_branch":"main","last_synced_at":"2025-05-16T06:04:22.923Z","etag":null,"topics":["anime","gans","image-translation"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/mchong6.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}},"created_at":"2021-12-17T17:40:39.000Z","updated_at":"2025-05-15T02:14:15.000Z","dependencies_parsed_at":"2022-07-16T10:30:32.654Z","dependency_job_id":null,"html_url":"https://github.com/mchong6/JoJoGAN","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mchong6%2FJoJoGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mchong6%2FJoJoGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mchong6%2FJoJoGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mchong6%2FJoJoGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mchong6","download_url":"https://codeload.github.com/mchong6/JoJoGAN/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254478186,"owners_count":22077675,"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":["anime","gans","image-translation"],"created_at":"2024-09-24T20:07:11.368Z","updated_at":"2025-05-16T06:04:38.307Z","avatar_url":"https://github.com/mchong6.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# JoJoGAN: One Shot Face Stylization\n[![arXiv](https://img.shields.io/badge/arXiv-2112.11641-b31b1b.svg)](https://arxiv.org/abs/2112.11641)\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mchong6/JoJoGAN/blob/main/stylize.ipynb)\n[![Replicate](https://replicate.com/mchong6/jojogan/badge)](https://replicate.com/mchong6/jojogan)\n[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/akhaliq/JoJoGAN)\n[![Wandb Report](https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg)](https://wandb.ai/akhaliq/jojogan/reports/JoJoGAN-One-Shot-Face-Stylization-with-Wandb-and-Gradio---VmlldzoxNDMzNzgx)\n\n\n![](teasers/teaser.jpg)\n\nThis is the PyTorch implementation of [JoJoGAN: One Shot Face Stylization](https://arxiv.org/abs/2112.11641).\n\n\n\u003e**Abstract:**\u003cbr\u003e\nWhile there have been recent advances in few-shot image stylization, these methods fail to capture stylistic details\nthat are obvious to humans. Details such as the shape of the eyes, the boldness of the lines, are especially difficult\nfor a model to learn, especially so under a limited data setting. In this work, we aim to perform one-shot image stylization that gets the details right. Given\na reference style image, we approximate paired real data using GAN inversion and finetune a pretrained StyleGAN using\nthat approximate paired data. We then encourage the StyleGAN to generalize so that the learned style can be applied\nto all other images.\n\n## Updates\n\n* `2021-12-22` Integrated into [Replicate](https://replicate.com) using [cog](https://github.com/replicate/cog). Try it out [![Replicate](https://replicate.com/mchong6/jojogan/badge)](https://replicate.com/mchong6/jojogan)\n\n* `2022-02-03` Updated the paper. Improved stylization quality using discriminator perceptual loss. Added sketch model\n\u003cbr\u003e\u003cimg src=\"teasers/sketch.gif\" width=\"50%\" height=\"50%\"/\u003e\n* `2021-12-26` Added wandb logging. Fixed finetuning bug which begins finetuning from previously loaded checkpoint instead of the base face model. Added art model \u003cdetails\u003e\u003cbr\u003e\u003cimg src=\"teasers/art.gif\" width=\"50%\" height=\"50%\"/\u003e\u003c/details\u003e\n\n* `2021-12-25` Added arcane_multi model which is trained on 4 arcane faces instead of 1 (if anyone has more clean data, let me know!). Better preserves features \u003cdetails\u003e\u003cimg src=\"teasers/arcane.gif\" width=\"50%\" height=\"50%\"/\u003e\u003c/details\u003e\n\n* `2021-12-23` Paper is uploaded to [arxiv](https://arxiv.org/abs/2112.11641).\n* `2021-12-22` Integrated into [Huggingface Spaces 🤗](https://huggingface.co/spaces) using [Gradio](https://github.com/gradio-app/gradio). Try it out [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/akhaliq/JoJoGAN)\n* `2021-12-22` Added pydrive authentication to avoid download limits from gdrive! Fixed running on cpu on colab.\n\n\n\n## How to use\nEverything to get started is in the [colab notebook](https://colab.research.google.com/github/mchong6/JoJoGAN/blob/main/stylize.ipynb).\n\n## Citation\nIf you use this code or ideas from our paper, please cite our paper:\n```\n@article{chong2021jojogan,\n  title={JoJoGAN: One Shot Face Stylization},\n  author={Chong, Min Jin and Forsyth, David},\n  journal={arXiv preprint arXiv:2112.11641},\n  year={2021}\n}\n```\n\n## Acknowledgments\nThis code borrows from [StyleGAN2 by rosalinity](https://github.com/rosinality/stylegan2-pytorch), [e4e](https://github.com/omertov/encoder4editing). Some snippets of colab code from [StyleGAN-NADA](https://github.com/rinongal/StyleGAN-nada)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmchong6%2Fjojogan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmchong6%2Fjojogan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmchong6%2Fjojogan/lists"}