{"id":13497218,"url":"https://github.com/wangsuzhen/Audio2Head","last_synced_at":"2025-03-28T21:32:10.562Z","repository":{"id":47025224,"uuid":"419642468","full_name":"wangsuzhen/Audio2Head","owner":"wangsuzhen","description":"code for paper \"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion\" in the conference of IJCAI 2021","archived":false,"fork":false,"pushed_at":"2024-02-15T07:19:47.000Z","size":1068,"stargazers_count":326,"open_issues_count":14,"forks_count":60,"subscribers_count":8,"default_branch":"main","last_synced_at":"2024-10-31T13:34:16.668Z","etag":null,"topics":["codes","ijcai2021","multi-modal","paper","talking-face","talking-head"],"latest_commit_sha":null,"homepage":"","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/wangsuzhen.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":"2021-10-21T08:31:16.000Z","updated_at":"2024-10-29T14:45:32.000Z","dependencies_parsed_at":"2024-01-07T22:19:16.066Z","dependency_job_id":"30c14bcf-9ecf-4f89-b8c8-26069ce6812d","html_url":"https://github.com/wangsuzhen/Audio2Head","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/wangsuzhen%2FAudio2Head","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangsuzhen%2FAudio2Head/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangsuzhen%2FAudio2Head/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wangsuzhen%2FAudio2Head/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wangsuzhen","download_url":"https://codeload.github.com/wangsuzhen/Audio2Head/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246105354,"owners_count":20724300,"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":["codes","ijcai2021","multi-modal","paper","talking-face","talking-head"],"created_at":"2024-07-31T20:00:26.940Z","updated_at":"2025-03-28T21:32:10.090Z","avatar_url":"https://github.com/wangsuzhen.png","language":"Python","funding_links":[],"categories":["Video Tools","GitHub projects"],"sub_categories":[],"readme":"# Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion (IJCAI 2021)\r\n\r\n#### [Paper](https://www.ijcai.org/proceedings/2021/0152.pdf) | [Demo](https://www.youtube.com/watch?v=xvcBJ29l8rA)\r\n\r\n#### Requirements\r\n\r\n- Python 3.6 , Pytorch \u003e= 1.6 and ffmpeg\r\n\r\n- Other requirements are listed in the 'requirements.txt'\r\n\r\n  \r\n\r\n#### Pretrained Checkpoint\r\n\r\nPlease download the pretrained checkpoint from [google-drive](https://drive.google.com/file/d/1tvI43ZIrnx9Ti2TpFiEO4dK5DOwcECD7/view?usp=sharing) and put it within the folder (`/checkpoints`).\r\n\r\n\r\n\r\n#### Generate Demo Results\r\n\r\n```\r\npython inference.py --audio_path xxx.wav --img_path xxx.jpg\r\n```\r\n\r\nNote that the input images must keep the same height and width and the face should be appropriately cropped as in `/demo/img`.\r\n\r\n\r\n\r\n#### License and Citation\r\n\r\n```\r\n@InProceedings{wang2021audio2head,\r\nauthor = Suzhen Wang, Lincheng Li, Yu Ding, Changjie Fan, Xin Yu\r\ntitle = {Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion},\r\nbooktitle = {the 30th International Joint Conference on Artificial Intelligence (IJCAI-21)},\r\nyear = {2021},\r\n}\r\n```\r\n\r\n\r\n\r\n#### Acknowledgement\r\n\r\nThis codebase is based on [First Order Motion Model](https://github.com/AliaksandrSiarohin/first-order-model), thanks for their contribution.\r\n\r\n\r\n\r\n\r\n\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwangsuzhen%2FAudio2Head","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwangsuzhen%2FAudio2Head","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwangsuzhen%2FAudio2Head/lists"}