Skip to content
Other

InstantHMR для ComfyUI

3D-тело человека в five размерах

1 min readupdated

Это веса InstantHMR, переупакованные в отдельные .safetensors для нод-пака ComfyUI-InstantHMR. Каждый файл содержит сеть и MHR-скелет, поэтому не требует других моделей. Выход — MHR-тело, совместимое с нативными нодами SAM 3D Body: сглаживание, рендер и экспорт GLB/BVH.

Ключевые особенности

  • Пять вариантов от nano до medium на бэкбонах HGNetV2-B0…B4, 20–32,2 млн параметров.
  • На выходе MHR-риг, готовый для сглаживания, рендера и экспорта GLB/BVH в ComfyUI.
  • Файлы кладутся в ComfyUI/models/detection и выбираются в Load InstantHMR Model.
  • nano, tiny, small и medium — только некоммерческое использование по SAM License.
  • medium_commercial можно использовать коммерчески по SAM License, но качество ниже: 50,7 мм против 40,0.
  • Конвертированы из официальных ONNX; сверка с onnxruntime даёт расхождение около 1e-5.

Пример

Сценарий: положите instanthmr_medium.safetensors в ComfyUI/models/detection, выберите его в Load InstantHMR Model и подключите выход к нодам SAM 3D Body для сглаживания и экспорта GLB/BVH.

Подробнее3DPW PA-MPJPE: 46,6 мм у nano, 44,0 у tiny, 41,7 у small, 40,0 у medium и 50,7 у medium_commercial.
Параметры: 20,0–32,2 млн; бэкбоны HGNetV2-B0…B4.
Лицензия SAM License: четыре базовых файла только для некоммерческого использования, medium_commercial — можно коммерчески.
MHR-риг внутри файлов — Apache-2.0.
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.2 GB · ready files0.7 GB
  • FP8 / INT8recommendedweights 0.1 GB0.6 GB
  • 4-bitweights 0.0 GB0.6 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

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.

    # jtydhr88/ComfyUI-InstantHMR
    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 jtydhr88/ComfyUI-InstantHMR --local-dir ~/models/ComfyUI-InstantHMR
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to ComfyUI-InstantHMR
  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 InstantHMR (quants, finetunes, LoRAs) will show up under the bell.

Fine-tunes 1All on Hugging Face

About the model

jtydhr88/ComfyUI-InstantHMR
Author
jtydhr88
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

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

Comments