{"name":"HairDeck","repo":"hyz317/HairDeck","url":"https://midorreal.com/project/hyz317-hairdeck","repository":"https://github.com/hyz317/HairDeck","description":"HairDeck: Animation-Ready Stylized Hair Cards from a Single Image","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/hyz317/HairDeck","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/hyz317/HairDeck","checked":"22 Nov 2026"},"releases":{"value":"0","source":"https://github.com/hyz317/HairDeck/releases","checked":"21 Nov 2026"},"contributors":{"value":"3","source":"https://github.com/hyz317/HairDeck/graphs/contributors","checked":"21 Nov 2026"},"archived":{"value":"no","source":"https://github.com/hyz317/HairDeck","checked":"22 Nov 2026"}},"stars":1206.0,"writeup":{"what_it_is":"HairDeck is a research project that generates stylized hair cards and spring-bone chains from a single image. Each hair card is encoded as one token, and a set diffusion transformer generates the hairstyle as a whole. The output can be exported as a GLB mesh or attached to an avatar and exported as VRM.","audience":"Researchers and developers working on 3D hair, avatars and character animation.","claims":[{"kind":"specific","claim":"Generates hair cards and spring-bone chains from a single image","excerpt":"generates stylized hair cards and the spring-bone chains that animate them from a single image","status":"not_checked"},{"kind":"specific","claim":"Provides per-card UV coordinates","excerpt":"The output preserves individual hair cards and provides per-card UV coordinates.","status":"not_checked"},{"kind":"specific","claim":"A color model predicts colors along every card, including two-tone hair and accessories","excerpt":"A color model predicts the colors along every card, including two-tone hair and accessories.","status":"not_checked"},{"kind":"specific","claim":"Runs on Linux, native Windows and Apple silicon Macs","excerpt":"HairDeck runs on Linux and native Windows with an NVIDIA CUDA GPU, Python 3.12, PyTorch 2.8 and CUDA 12.8.","status":"not_checked"},{"kind":"specific","claim":"Fast sampler gives 2-3x faster sampling at small batch sizes","excerpt":"2-3x faster sampling at small batch sizes, measured on NVIDIA and AMD","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-16"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":62,"reality":33,"gap":30,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-29T17:16:13+00:00","text":"Repository created","source":"https://github.com/hyz317/HairDeck"}],"cite":"HairDeck is a GitHub project at https://github.com/hyz317/HairDeck written mainly in Python, described there as \"HairDeck: Animation-Ready Stylized Hair Cards from a Single Image\".","attribution":"Data from Mid or Real, https://midorreal.com/project/hyz317-hairdeck, checked 22 November 2026. Attribution with a link is required.","still_real":null}