{"data":{"slug":"pkhungurn-talking-head-anime-2-demo","name":"talking-head-anime-2-demo","tagline":"Demo programs for the Talking Head Anime from a Single Image 2: More Expressive project.","github_url":"https://github.com/pkhungurn/talking-head-anime-2-demo","owner":"pkhungurn","repo":"talking-head-anime-2-demo","owner_avatar_url":"https://avatars.githubusercontent.com/u/25254747?v=4","primary_language":"Python","stars":1154,"forks":150,"topics":["ai","anime","computer-graphics","computer-vision","deep-learning","machine-learning","python","pytorch","vtuber"],"archived":false,"github_pushed_at":"2022-06-29T20:26:56+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/pkhungurn-talking-head-anime-2-demo","markdown_url":"https://www.graphcanon.com/tools/pkhungurn-talking-head-anime-2-demo.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pkhungurn-talking-head-anime-2-demo","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pkhungurn-talking-head-anime-2-demo","description":"Demo programs for the Talking Head Anime from a Single Image 2: More Expressive project.","homepage_url":"http://pkhungurn.github.io/talking-head-anime-2/","license":"MIT","open_issues":11,"watchers":20,"ai_summary":null,"readme_excerpt":"## Hardware Requirements\n\nBoth programs require a recent and powerful Nvidia GPU to run. I could personally ran them at good speed with the \n[Nvidia Titan RTX](https://www.nvidia.com/en-us/deep-learning-ai/products/titan-rtx/). However, I think recent high-end\ngaming GPUs such as the [RTX 2080](https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2080/), the \n[RTX 3080](https://www.nvidia.com/en-us/geforce/graphics-cards/30-series/rtx-3080/), or better would do just as well. \n\nThe `ifacialmocap_puppeteer` requires an iOS device that is capable of computing \n[blend shape parameters](https://developer.apple.com/documentation/arkit/arfaceanchor/2928251-blendshapes) from a video \nfeed. This means that the device must be able to run iOS 11.0 or higher and must have a TrueDepth front-facing camera.\n(See [this page](https://developer.apple.com/documentation/arkit/content_anchors/tracking_and_visualizing_faces) for \nmore info.) In other words, if you have the iPhone X or something better, you should be all set. Personally, I have\nused an iPhone 12 mini.\n\n---\n\n## Software Requirements\n\nBoth programs were written in Python 3. To run the GUIs, the following software packages are required:\n\n  * Python >= 3.8\n  * PyTorch >= 1.7.1 with CUDA support\n  * SciPY >= 1.6.0\n  * wxPython >= 4.1.1\n  * Matplotlib >= 3.3.4\n\nIn particular, I created the environment to run the programs with [Anaconda](https://www.anaconda.com/), using the\nfollowing commands:\n```\n> conda create -n talking-head-anime-2-demo python=3.8\n> conda activate talking-head-anime-2-demo\n> conda install pytorch torchvision cudatoolkit=10.2 -c pytorch\n> conda install scipy\n> pip install wxPython\n> conda install matplotlib\n```\n\n**Note:** You may find that the particular versions of Python (3.8) and CUDA Toolkit (10.2) might not work for your particular computer setup. When this happens, replace these versions with those that work with your hardware. The command would become:\n```\n> conda create -n talking-head-anime-2-demo python=[YOUR-PYTHON-VERSION]\n> conda activate talking-head-anime-2-demo\n> conda install pytorch torchvision cudatoolkit=[YOUR-CUDA-TOOLKIT-VERSION] -c pytorch\n> conda install scipy\n> pip install wxPython\n> conda install matplotlib\n```\nIn general, the latest version of Python and the latest version of CUDA Toolkit shown on [PyTorch's website](http://pytorch.org) would work.\n\nTo run the Jupyter notebook version of the `manual_poser`, you also need:\n\n  * Jupyter Notebook >= 6.2.0\n  * IPyWidgets >= 7.6.3\n\nThis means that, in addition to the commands above, you also need to run:\n```\n> conda install -c conda-forge notebook\n> conda install -c conda-forge ipywidgets\n> jupyter nbextension enable --py widgetsnbextension\n```\n\nLastly, the `ifacialmocap_puppeteer` requires iFacialMocap, which is \n[available in the App Store](https://apps.apple.com/us/app/ifacialmocap/id1489470545) for 980 yen. You also need to \ninstall the [paired desktop application](https://www.ifacialmocap.com/download/) on your PC or Mac. (Linux users, \nI'm sorry!) Your iOS and your computer must also use the same network. (For example, you may connect them to the same \nwireless router.)","github_created_at":"2021-03-02T16:14:39+00:00","created_at":"2026-07-11T12:26:25.484301+00:00","updated_at":"2026-07-11T12:26:41.534855+00:00","categories":[{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"}],"tags":[{"slug":"deep-learning","name":"deep-learning"},{"slug":"anime","name":"anime"},{"slug":"ai","name":"ai"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"python","name":"python"},{"slug":"pytorch","name":"pytorch"},{"slug":"computer-graphics","name":"computer-graphics"},{"slug":"computer-vision","name":"computer-vision"}],"trust":{"provenance":{"is_fork":false,"github_id":343834897,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T12:26:33.733Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1472,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:26:36.980Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T12:26:34.934Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-11T12:26:34.934Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-11T12:26:34.934Z"}}}}