Skip to content
3D

HairDeck

причёска из одной картинки, готовая к анимации

1 min read

HairDeck — исследовательский пайплайн от Tsinghua University, Carnegie Mellon University и CUHK. По одному изображению персонажа он создаёт стилизованные hair cards с UV-развёрткой для каждой карты и spring-bone chains для анимации, а затем позволяет собрать VRM 0.x.

Ключевые особенности

  • Превращает одно изображение персонажа в стилизованные hair cards с per-card UVs.
  • Генерирует spring-bone chains для анимации и выдаёт волосы в виде GLB-мешей.
  • Поддерживает экспорт VRM 0.x: волосы крепятся к предоставленному телу аватара.
  • Основной пайплайн — Image DiT + Card VAE + Chain DiT; отдельно выпущен Point-cloud DiT для генерации по облаку точек.
  • Есть онлайн-демо и локальный запуск; в примере инференс выдаёт четыре варианта причёски.

Пример запуска

export HAIRDECK_ROOT=/path/to/workspace
python scripts/setup/download_weights.py
python scripts/image_to_hair.py character.png --out results/my_character --n 4
python -m hairdeck.vrm.export results/my_character/character 0
ПодробнееЧекпоинты HairDeck распространяются под Apache-2.0.
Для локального запуска нужны Linux, Python 3.12 и CUDA GPU; также нужно принять лицензии SAM 3 и DINOv3.
В карточке нет числовых бенчмарков и требований к VRAM; для оценки предусмотрены отдельные скрипты point-cloud и chain-бенчмарков.
Видео-пример
Discuss Telegram 35 1.3K

Will it run?

Working out the memory needs

The bot is still collecting this model's weight sizes; the estimate will appear here in a few minutes. Meanwhile you can rent a GPU with headroom.

Massed ComputeOpen Massed Compute

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # hyz317/HairDeck
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download hyz317/HairDeck --local-dir ~/models/HairDeck
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to HairDeck
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of HairDeck (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

hyz317/HairDeck
Author
hyz317
Category
3D
Released
Posted

On NeyroLearn

Hugging Face

1.3K35

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments

3D

Idol

Idol