HairDeck: Tsinghua's diffusion model turns one image into animation-ready stylized hair cards
Tsinghua · hf · 2026-10-30
HairDeck, from Tsinghua University with CMU and CUHK, generates animation-ready stylized hair cards and spring-bone animations from a single image.
- Represents hair cards and spring-bone rigs as unordered token sets, generated with a diffusion transformer.
- Improves both accuracy and speed over prior methods.
- Directly useful for game and anime asset pipelines needing stylized, animatable hair.
More from Multimodal
- Open source image model grumble: Moss underdelivers while Krea 2 wins by default — Neggy5 · 2026-10-30
- DataTalksClub and Nebius launch free course on production AI agents for generative media — Al_Grigor · 2026-10-30
- AI-generated Hindi podcast pits Bhagat Singh against Gandhi in a virtual studio — purifiedwater1234 · 2026-10-30
- FontBox LoRA brings bbox-based intuitive text editing to FLUX.3 Klein — SillyLilithh · 2026-10-30
- Pika launches H3 Flex video model: 15s 768p clips in 7 seconds, open weights soon — heyshrutimishra · 2026-10-30
- AI-designed 'Dumpling Bag' goes viral: silicone shell nailed the pleated look — Delahuntagram · 2026-10-30