nkxx188/ComfyUI-MiniMaxH3-Easy

The easiest way to use MiniMax H3. One compact workflow for T2V, I2V, first/last-frame, and reference video generation, with a unified multi-media input, powerful @ references, and inline dialogue blocks. Less wiring. More creative control.

What it solves

This project simplifies the use of MiniMax H3 for video generation in ComfyUI. It replaces complex manual setups with a unified node suite that handles text-to-video, image-to-video, reference-based generation, and digital human creation, while providing advanced tools for managing media assets and generating long-form content through connected segments.

How it works

The suite provides a streamlined workflow where a single main node handles multiple generation modes. It introduces a Media Loader for visual management of images, audio, and video, and a Context Segments system that breaks long videos into shots. Each segment can have its own prompt and media references, while maintaining continuity through various modes (Motion Context, RGB Guide, or AV Prefix).

To reference media within prompts, the system uses an @ symbol (e.g., @Image1), which the node converts into the required H3 tags at runtime. It also includes a built-in prompt optimizer that can use LLMs (via OpenAI, Gemini, or Ollama) to expand ideas into structured, multi-segment scripts.

Who it’s for

ComfyUI users who want a more intuitive, less cluttered interface for MiniMax H3 video generation, particularly those creating complex, multi-shot videos or digital humans with synchronized audio.

Highlights

  • Unified Generation Node: One node for text, image, first/last frame, reference, and digital human modes.
  • Visual Media Management: A dedicated loader for dragging, pasting, and caching decoded video references to speed up preparation.
  • Long Video Continuity: Tools to generate connected segments with configurable continuity modes to ensure visual and audio consistency across shots.
  • @ Media Referencing: Direct insertion of media assets into prompts using a simple mention system.
  • Per-Segment Refinement: Built-in options for Pixel Resize and 3D Latent Upscaling to improve quality on a per-shot basis.
  • LLM-Powered Prompt Optimization: Integrated support for multiple LLM providers to automatically generate or refine segment-specific prompts.

Related

  • Project
    LeonQ8/ComfyUI-ALLinONE-MinimaxH3

    A single-node ComfyUI interface that consolidates the entire MiniMax H3 video pipeline, simplifying text-to-video, image-to-video, and video editing tasks.

  • Project
    AIMixer/ComfyUI_MiniMaxH3_Director

    A professional director's console for ComfyUI that streamlines long-form video generation using the MiniMax H3 model through a visual timeline and multi-segment management.

  • Project
    Songssx/ComfyUI-MiniMaxH3-TimelineDirector

    A ComfyUI plugin for MiniMax H3 that enables seamless, unlimited-length video generation and multimodal reference management via an integrated timeline editor.

  • Project
    huangserva/ComfyUI_MiniMaxH3_Director

    A collection of ComfyUI workflows for MiniMax H3 Director, enabling text-to-video, image-to-video, and advanced video-to-video editing with reference materials.

  • Dispatch
    MiniMax H3 Support in ComfyUI

    ComfyUI introduces day-zero support for MiniMax H3, an open-weights omni-modal video model capable of generating 2K video with native stereo audio on consumer hardware.