{"id":14561179,"url":"https://github.com/bytedance/X-Portrait","last_synced_at":"2025-09-04T05:32:50.262Z","repository":{"id":250815152,"uuid":"830739025","full_name":"bytedance/X-Portrait","owner":"bytedance","description":"Source code for the SIGGRAPH 2024 paper \"X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention\"","archived":false,"fork":false,"pushed_at":"2024-08-01T23:30:57.000Z","size":9539,"stargazers_count":510,"open_issues_count":12,"forks_count":43,"subscribers_count":16,"default_branch":"main","last_synced_at":"2025-05-25T02:07:31.682Z","etag":null,"topics":["research"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bytedance.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2024-07-18T22:21:40.000Z","updated_at":"2025-05-24T01:09:51.000Z","dependencies_parsed_at":"2025-01-14T23:52:39.932Z","dependency_job_id":null,"html_url":"https://github.com/bytedance/X-Portrait","commit_stats":null,"previous_names":["bytedance/x-portrait"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bytedance/X-Portrait","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bytedance%2FX-Portrait","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bytedance%2FX-Portrait/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bytedance%2FX-Portrait/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bytedance%2FX-Portrait/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bytedance","download_url":"https://codeload.github.com/bytedance/X-Portrait/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bytedance%2FX-Portrait/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273555898,"owners_count":25126436,"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":"2025-09-04T02:00:08.968Z","response_time":61,"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":["research"],"created_at":"2024-09-07T01:01:12.234Z","updated_at":"2025-09-04T05:32:49.633Z","avatar_url":"https://github.com/bytedance.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"\u003c!-- # magic-edit.github.io --\u003e\n\n\u003cp align=\"center\"\u003e\n\n  \u003ch2 align=\"center\"\u003eX-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention\u003c/h2\u003e\n  \u003cp align=\"center\"\u003e\n                \u003ca href=\"https://scholar.google.com/citations?user=FV0eXhQAAAAJ\u0026hl=en\"\u003eYou Xie\u003c/a\u003e,\n                \u003ca href=\"https://hongyixu37.github.io/homepage/\"\u003eHongyi Xu\u003c/a\u003e,\n                \u003ca href=\"https://guoxiansong.github.io/homepage/index.html\"\u003eGuoxian Song\u003c/a\u003e,\n                \u003ca href=\"https://chaowang.info/\"\u003eChao Wang\u003c/a\u003e,\n                \u003ca href=\"https://seasonsh.github.io/\"\u003eYichun Shi\u003c/a\u003e,\n                \u003ca href=\"http://linjieluo.com/\"\u003eLinjie Luo\u003c/a\u003e\n    \u003cbr\u003e\n    \u003cb\u003e\u0026nbsp;  ByteDance Inc. \u003c/b\u003e\n    \u003cbr\u003e\n    \u003cbr\u003e\n        \u003ca href=\"https://arxiv.org/abs/2403.15931\"\u003e\u003cimg src='https://img.shields.io/badge/arXiv-X--Portrait-red' alt='Paper PDF'\u003e\u003c/a\u003e\n        \u003ca href='https://byteaigc.github.io/x-portrait/'\u003e\u003cimg src='https://img.shields.io/badge/Project_Page-X--Portrait-green' alt='Project Page'\u003e\u003c/a\u003e\n        \u003ca href='https://youtu.be/VGxt5XghRdw'\u003e\n        \u003cimg src='https://img.shields.io/badge/YouTube-X--Portrait-rgb(255, 0, 0)' alt='Youtube'\u003e\u003c/a\u003e\n    \u003cbr\u003e\n  \u003c/p\u003e\n  \n  \u003ctable align=\"center\"\u003e\n    \u003ctr\u003e\n    \u003ctd\u003e\n      \u003cimg src=\"assets/teaser/teaser.png\"\u003e\n    \u003c/td\u003e\n    \u003c/tr\u003e\n  \u003c/table\u003e\n\nThis repository contains the video generation code of SIGGRAPH 2024 paper [X-Portrait](https://arxiv.org/pdf/2403.15931). \n\n## Installation\nNote: Python 3.9 and Cuda 11.8 are required.\n```shell\nbash env_install.sh\n```\n\n## Model\nPlease download pre-trained model from [here](https://drive.google.com/drive/folders/1Bq0n-w1VT5l99CoaVg02hFpqE5eGLo9O?usp=sharing), and save it under \"checkpoint/\"\n\n## Testing\n```shell\nbash scripts/test_xportrait.sh\n```\nparameters:  \n**model_config**: config file of the corresponding model  \n**output_dir**: output path for generated video  \n**source_image**: path of source image  \n**driving_video**: path of driving video  \n**best_frame**: specify the frame index in the driving video where the head pose best matches the source image (note: precision of best_frame index might affect the final quality)  \n**out_frames**: number of generation frames  \n**num_mix**: number of overlapping frames when applying prompt travelling during inference  \n**ddim_steps**: number of inference steps (e.g., 30 steps for ddim)     \n\n## Performance Boost\n**efficiency**: Our model is compatible with LCM LoRA (https://huggingface.co/latent-consistency/lcm-lora-sdv1-5), which helps reduce the number of inference steps.  \n**expressiveness**: Expressiveness of the results could be boosted if results of other face reenactment approaches, e.g., face vid2vid, could be provided via parameter \"--initial_facevid2vid_results\".  \n\n## 🎓 Citation\nIf you find this codebase useful for your research, please use the following entry.\n```BibTeX\n@inproceedings{xie2024x,\n  title={X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention},\n  author={Xie, You and Xu, Hongyi and Song, Guoxian and Wang, Chao and Shi, Yichun and Luo, Linjie},\n  journal={arXiv preprint arXiv:2403.15931},\n  year={2024}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbytedance%2FX-Portrait","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbytedance%2FX-Portrait","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbytedance%2FX-Portrait/lists"}