Skip to content
Other

CROWN VFX & High-Speed Combat Boost

LoRA for VFX and Combat Scenes in MiniMax H3

2 min readupdated

This is a LoRA (a small add-on on top of a base model) built for the MiniMax H3 video generator (across Ref2VA, I2VA, and T2VA versions). It significantly improves the generation of fast-paced combat scenes, rapid weapon strikes, close-quarters fighting, and complex visual effects like shockwaves and sparks. At the same time, the adapter preserves the character's original facial features and native stereo audio. Trained on an NVIDIA cluster, this model is designed for creators working on high-energy action sequences.

Key features

  • Combat choreography: boosts the speed and impact of rapid strikes and weapon movements.
  • Dynamic camera angles: improves Z-axis camera movement and fly-around shots.
  • Visual effects: adds plasma trails, shockwaves, and flying debris particles.
  • Face preservation: keeps the character's original likeness intact without distortion.

What you can do

  • Action videos: generate high-speed sword fights or hand-to-hand combat scenes in ComfyUI.
  • Particle effects: add explosions, flashes, and energy trails to your videos.
  • Dynamic camera work: set up complex camera fly-throughs around your character.

Example

Use the trigger word crown_vfx_combat in your prompt and set the LoRA weight between 1.20 and 1.50 for best results.

Read moreDetails
Base model: minimax_h3_ref2va_bf16.safetensors
Recommended steps: 24 (euler + ManualSigmas, shift_video: 12.0, shift_audio: 3.0)
Training: Rank 64 / Alpha 64 on Video-Only Blocks 10–49
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-crown-vfx-high-speed-combat-boost-minimax-h3-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-crown-vfx-high-speed-combat-boost-minimax-h3-lora --local-dir ~/models/rh-crown-vfx-high-speed-combat-boost-minimax-h3-lora
    # The model is in ~/models. How to run it is in the model card (link above).
  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-crown-vfx-high-speed-combat-boost-minimax-h3-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-crown-vfx-high-speed-combat-boost-minimax-h3-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