{"id":15026512,"url":"https://github.com/yerfor/genefaceplusplus","last_synced_at":"2025-05-14T11:09:06.206Z","repository":{"id":220266273,"uuid":"751190653","full_name":"yerfor/GeneFacePlusPlus","owner":"yerfor","description":"GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code","archived":false,"fork":false,"pushed_at":"2024-10-18T09:10:53.000Z","size":38112,"stargazers_count":1689,"open_issues_count":137,"forks_count":243,"subscribers_count":27,"default_branch":"main","last_synced_at":"2025-04-19T09:22:40.950Z","etag":null,"topics":["nerf","talking-face-generation"],"latest_commit_sha":null,"homepage":"","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/yerfor.png","metadata":{"files":{"readme":"README-zh.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,"publiccode":null,"codemeta":null}},"created_at":"2024-02-01T05:28:57.000Z","updated_at":"2025-04-19T06:50:22.000Z","dependencies_parsed_at":"2024-09-20T20:31:14.174Z","dependency_job_id":"6f188320-d6db-424a-beb1-e13785a56df3","html_url":"https://github.com/yerfor/GeneFacePlusPlus","commit_stats":null,"previous_names":["yerfor/genefaceplusplus"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yerfor%2FGeneFacePlusPlus","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yerfor%2FGeneFacePlusPlus/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yerfor%2FGeneFacePlusPlus/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yerfor%2FGeneFacePlusPlus/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yerfor","download_url":"https://codeload.github.com/yerfor/GeneFacePlusPlus/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254129488,"owners_count":22019628,"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":["nerf","talking-face-generation"],"created_at":"2024-09-24T20:04:36.498Z","updated_at":"2025-05-14T11:09:06.180Z","avatar_url":"https://github.com/yerfor.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation\n\n[![arXiv](https://img.shields.io/badge/arXiv-Paper-%3CCOLOR%3E.svg)](https://arxiv.org/abs/2305.00787)| [![GitHub Stars](https://img.shields.io/github/stars/yerfor/GeneFacePlusPlus)](https://github.com/yerfor/GeneFacePlusPlus) | [![downloads](https://img.shields.io/github/downloads/yerfor/GeneFacePlusPlus/total.svg)](https://github.com/yerfor/GeneFacePlusPlus/releases) | ![visitors](https://visitor-badge.glitch.me/badge?page_id=yerfor/GeneFacePlusPlus)\n\n[English Readme](./README.md)\n\n这个仓库是GeneFace++的官方PyTorch实现，用于实现高嘴形对齐(lip-sync)、高视频真实度(video reality)、高系统效率(system efficiency)的虚拟人视频合成。您可以访问我们的[项目页面](https://genefaceplusplus.github.io/)以观看Demo视频, 阅读我们的[论文](https://arxiv.org/abs/2301.13430)以了解技术细节。\n\n\u003cp align=\"center\"\u003e\n    \u003cbr\u003e\n    \u003cimg src=\"assets/geneface++.png\" width=\"100%\"/\u003e\n    \u003cbr\u003e\n\u003c/p\u003e\n\n## 您可能同样感兴趣\n- 我们发布了Real3D-portrait (ICLR 2024 Spotlight), ([https://github.com/yerfor/Real3DPortrait](https://github.com/yerfor/Real3DPortrait)), 一个基于NeRF的单图驱动说话人合成系统, 仅需上传一张照片即可合成真实的说话人视频!\n\n## 快速上手！\n我们在这里提供一个最快体验GeneFace++的流程。\n\n- 步骤1：根据我们在`docs/prepare_env/install_guide.md`中的步骤，新建一个名为`geneface`的Python环境，并下载所需的3DMM文件。\n\n- 步骤2：下载预处理好的May的数据集 `trainval_dataset.npy` ([Google Drive](https://drive.google.com/drive/folders/1SwZ7uRa5ESzzq_Cd21-Lk5heAZxa9oZO?usp=sharing) 或 [BaiduYun Disk](https://pan.baidu.com/s/1U_FalVoxgb9sAb9FD1cZEw?pwd=98n4) 提取码: 98n4), 放置在`data/binary/videos/May/trainval_dataset.npy`路径下。\n\n- 步骤3：下载预训练好的通用的audio-to-motino模型 `audio2motion_vae.zip` ([Google Drive](https://drive.google.com/drive/folders/1M6CQH52lG_yZj7oCMaepn3Qsvb-8W2pT?usp=sharing) 或 [BaiduYun Disk](https://pan.baidu.com/s/1U_FalVoxgb9sAb9FD1cZEw?pwd=98n4) 提取码: 98n4) 和专用于May的motion-to-video模型 `motion2video_nerf.zip` ([Google Drive](https://drive.google.com/drive/folders/1M6CQH52lG_yZj7oCMaepn3Qsvb-8W2pT?usp=sharing) 或 [BaiduYun Disk](https://pan.baidu.com/s/1U_FalVoxgb9sAb9FD1cZEw?pwd=98n4) 提取码: 98n4), 解压到`./checkpoints/`目录下。\n\n做完上面的步骤后，您的 `checkpoints`和`data` 文件夹的结构应该是这样的：\n\n```shell\n\u003e checkpoints\n    \u003e audio2motion_vae\n    \u003e motion2video_nerf\n        \u003e may_head\n        \u003e may_torso\n\u003e data\n    \u003e binary\n        \u003e videos\n            \u003e May\n                trainval_dataset.npy\n```\n\n- 步骤4: 激活`geneface`的Python环境，然后执行: \n```bash\nexport PYTHONPATH=./\npython inference/genefacepp_infer.py --a2m_ckpt=checkpoints/audio2motion_vae --head_ckpt= --torso_ckpt=checkpoints/motion2video_nerf/may_torso --drv_aud=data/raw/val_wavs/MacronSpeech.wav --out_name=may_demo.mp4\n```\n  - 或者可以使用我们提供的Gradio WebUI: \n```bash\nexport PYTHONPATH=./\npython inference/app_genefacepp.py --a2m_ckpt=checkpoints/audio2motion_vae --head_ckpt= --torso_ckpt=checkpoints/motion2video_nerf/may_torso\n```\n  - 抑或可以使用我们提供的[Google Colab](https://colab.research.google.com/github/yerfor/GeneFacePlusPlus/blob/main/inference/genefacepp_demo.ipynb)，运行其中的所有cell。\n\n## 在自己的视频上训练GeneFace++\n如果您想在您自己的目标人物视频上训练GeneFace++，请遵循 `docs/process_data`和`docs/train_and_infer/`中的步骤。\n\n## ToDo\n- [x] **Release Inference Code of Audio2Motion and Motion2Video.**\n- [x] **Release Pre-trained weights of Audio2Motion and Motion2Video.**\n- [x] **Release Training Code of Motino2Video Renderer.**\n- [x] **Release Gradio Demo.**\n- [x] **Release Google Colab.**\n- [ ] **Release Training Code of Audio2Motion and Post-Net.**\n\n## 引用\n如果这个仓库对你有帮助，请考虑引用我们的工作:\n```\n@article{ye2023geneface,\n  title={GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis},\n  author={Ye, Zhenhui and Jiang, Ziyue and Ren, Yi and Liu, Jinglin and He, Jinzheng and Zhao, Zhou},\n  journal={arXiv preprint arXiv:2301.13430},\n  year={2023}\n}\n@article{ye2023geneface++,\n  title={GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation},\n  author={Ye, Zhenhui and He, Jinzheng and Jiang, Ziyue and Huang, Rongjie and Huang, Jiawei and Liu, Jinglin and Ren, Yi and Yin, Xiang and Ma, Zejun and Zhao, Zhou},\n  journal={arXiv preprint arXiv:2305.00787},\n  year={2023}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyerfor%2Fgenefaceplusplus","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyerfor%2Fgenefaceplusplus","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyerfor%2Fgenefaceplusplus/lists"}