Skip to content
Other

rh-h3-lora-dance-lora

LoRA for better dance moves in minimax-h3

1 min readupdated

This LoRA (a lightweight add-on for a base model) fixes and refines dance movements generated by the minimax-h3 base model. It requires no trigger words and makes outputs look more natural, working especially well for TikTok and otaku-style dances. Built by the RunningHub platform, it is recommended for use alongside the Dance Beat-Sync Slider and is geared toward creators generating dynamic choreography videos.

Key features

  • Makes the base model's dance movements look more natural and refined.
  • Requires no special trigger words to activate.
  • Recommended for use alongside the Dance Beat-Sync Slider.
  • Ships as a 148 MiB .safetensors weights file.

What you can do

  • Create smooth, high-quality dance videos for TikTok and other platforms.
  • Generate otaku-style choreography by pairing it with RunningHub and ComfyUI.

Example

Use the model in ComfyUI or on RunningHub by loading the `DANCE-minimax-h3.safetensors` weights file (148 MiB) on top of the minimax-h3 base model alongside the beat-sync slider.

Read moreDetails
Base model: minimax-h3
Type: LoRA
Weights file: DANCE-minimax-h3.safetensors (148 MiB)
Platforms: ComfyUI / RunningHub / Hugging Face
Discuss Telegram 0

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.

    # RunningHubAI/rh-h3-lora-dance-lora
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    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 RunningHubAI/rh-h3-lora-dance-lora --local-dir ~/models/rh-h3-lora-dance-lora
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to rh-h3-lora-dance-lora
  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.

MiniMax H3 prompts

All prompts

Ready prompts with the resulting video: copy and try.

Model family

New posts about versions of rh-h3-lora-dance-lora (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

RunningHubAI/rh-h3-lora-dance-lora
Author
RunningHubAI
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