{"data":{"slug":"pkhungurn-talking-head-anime-3-demo","name":"talking-head-anime-3-demo","tagline":"Demo programs for generating anime talking heads with body movement.","github_url":"https://github.com/pkhungurn/talking-head-anime-3-demo","owner":"pkhungurn","repo":"talking-head-anime-3-demo","owner_avatar_url":"https://avatars.githubusercontent.com/u/25254747?v=4","primary_language":"Python","stars":1044,"forks":106,"topics":["ai","anime","computer-graphics","computer-vision","machine-learning","python","pytorch","vtuber"],"archived":false,"github_pushed_at":"2023-08-29T08:12:25+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/pkhungurn-talking-head-anime-3-demo","markdown_url":"https://www.graphcanon.com/tools/pkhungurn-talking-head-anime-3-demo.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pkhungurn-talking-head-anime-3-demo","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pkhungurn-talking-head-anime-3-demo","description":"Demo Programs for the \"Talking Head(?) Anime from a Single Image 3: Now the Body Too\" Project","homepage_url":"http://pkhungurn.github.io/talking-head-anime-3/","license":"MIT","open_issues":11,"watchers":12,"ai_summary":"The repository contains Python-based demo programs using PyTorch to generate and manipulate animated anime characters that can talk and move based on input from video feeds processed by iOS devices.","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 Nvidia Titan RTX. However, I think recent high-end gaming GPUs such as the RTX 2080, the RTX 3080, or better would do just as well.\n\nThe `ifacialmocap_puppeteer` requires an iOS device that is capable of computing [blend shape parameters](https://developer.apple.com/documentation/arkit/arfaceanchor/2928251-blendshapes) from a video feed. This means that the device must be able to run iOS 11.0 or higher and must have a TrueDepth front-facing camera. (See [this page](https://developer.apple.com/documentation/arkit/content_anchors/tracking_and_visualizing_faces) for more info.) In other words, if you have the iPhone X or something better, you should be all set. Personally, I have used an iPhone 12 mini.","github_created_at":"2022-06-29T19:33:20+00:00","created_at":"2026-07-11T12:26:44.300001+00:00","updated_at":"2026-07-31T12:00:30.545083+00:00","categories":[{"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":"ai","name":"ai"},{"slug":"anime","name":"anime"},{"slug":"computer-graphics","name":"computer-graphics"},{"slug":"gpu-intensive","name":"gpu-intensive"},{"slug":"ios-device-interaction","name":"ios-device-interaction"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"pytorch","name":"pytorch"},{"slug":"vtuber","name":"vtuber"}],"trust":{"provenance":{"is_fork":false,"github_id":508822336,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-31T12:00:29.499Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1067,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:26:47.591Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-31T12:00:30.244Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-31T12:00:30.244Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-31T12:00:30.244Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["The project necessitates a powerful Nvidia GPU such as the Titan RTX or high-end gaming GPUs like RTX 2080/3080 series."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["Desire to generate high-fidelity talking head animations with nuanced body movements from a single image or live video feed captured by an iOS device.","Seeking to create detailed Anime-style VTubers that can emulate complex facial expressions and bodily motions for real-time interaction."],"when_not_to_use":["Need for deployment on hardware lacking recent high-end GPU capabilities such as the Nvidia Titan RTX or similar models like RTX 2080, RTX 3080.","Requirement of an iOS device with TrueDepth camera and running iOS 11.0 or higher to process blend shape parameters from video feed inputs."],"source":"enrich:decision_facts","observed_at":"2026-07-16T20:43:10.785Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"The project necessitates a powerful Nvidia GPU such as the Titan RTX or high-end gaming GPUs like RTX 2080/3080 series."},{"label":"Adopt for","value":"Demonstrative of advanced facial and body animation synthesis for anime-style characters through input video feeds on iOS devices using powerful GPUs."}]}}