hub_readme.md

MiniMax H3 (Hailuo AI) - AI Video Workflows, Prompts & Local Deployment Hub

Official Hub for MiniMax H3 (minimaxh3.run) — An all-in-one open-source resource platform for MiniMax H3 (Hailuo AI 3.0), the state-of-the-art native multi-modal 2K AI video generation model with synchronized 3D stereo audio.

0 1 2 3


🚀 Key Features


📦 Quick Start

Prerequisites

Installation

# Clone the repository
git clone https://github.com/your-username/minimax-h3-hub.git

# Navigate into the project directory
cd minimax-h3-hub

# Install dependencies
npm install

# Start the development server
npm run dev

Visit http://localhost:3000 to access the hub locally.


🧩 ComfyUI Setup for MiniMax H3

  1. Install ComfyUI.
  2. Install custom nodes via ComfyUI Manager or git clone:
    cd ComfyUI/custom_nodes
    git clone https://github.com/Comfy-Org/ComfyUI-MiniMaxH3.git
  3. Download weights from Hugging Face or ModelScope into ComfyUI/models/checkpoints/:
    • minimax_h3_video_vae_fp16.safetensors
    • minimax_h3_audio_vae_fp32.safetensors
    • qwen3vl_32b_minimax_h3.safetensors (Text Encoder)
  4. Launch ComfyUI and import the generated .json workflow from minimaxh3.run.

💻 Tech Stack


⚠️ Disclaimer

minimaxh3.run is an independent, open-source community resource for AI video workflows and guides. We are not affiliated with, sponsored by, or endorsed by MiniMax Inc. or Hailuo AI. All product names, logos, and trademarks belong to their respective owners.


📄 License

This project is released under the MIT License.

下载此文件