LeonQ8/ComfyUI-ALLinONE-MinimaxH3

All-in-one MiniMax H3 node for ComfyUI - T2V, T2I, I2V, R2V, Masking, audio drive, keyframes, extend & Motion Context chains in a single node.

What it solves

This project provides a simplified, single-node interface for the MiniMax H3 video generation pipeline in ComfyUI. It eliminates the need to build complex node graphs, connect wires, or search through multiple custom node packs to find the correct workflow for different video tasks.

How it works

The tool integrates various MiniMax H3 capabilities into one node with multiple operational modes. Users can select a mode and provide prompts or reference materials to generate content. It supports several specialized functions:

  • Image Mode: Generates still images via text, image editing, or reference mixing.
  • T2V/I2V/R2V: Handles text-to-video, image-to-video (with optional end-frame morphing), and reference-driven video generation.
  • Character Sheet: Creates a stitched turnaround sheet from up to 9 reference images.
  • Audio Drive: Synchronizes mouth movements (lip sync) to an audio track.
  • Keyframes & Extend: Allows pinning images at specific frames and seamlessly continuing existing videos.
  • Chain: Enables multi-clip continuation using H3 Motion Context.
  • Mask: Replaces specific regions of a video using painting or text descriptions.
  • Upscale: Integrates RTX/Seed2VR Video Super Resolution.

Additionally, it includes a "Compare & Stitch" feature to play clips side-by-side in sync or export them as a single combined clip.

Who it’s for

Content creators and ComfyUI users who want to access the powerful features of MiniMax H3 without the manual effort of building and managing complex node graphs.

Highlights

  • Single-Node Interface: Consolidates all H3 pipeline functions into one node.
  • Comprehensive Mode Suite: Supports everything from T2V and I2V to lip-sync and character sheets.
  • ** uma a live preview of videos during sampling.
  • Integrated Library & History: Searchable history with prompt reuse and a centralized output library.
  • Integrated Masking: Built-in tools for painting or describing regions for video replacement.
  • VRAM Optimization: Optional support for memory optimization chips to lower peak VRAM usage.

Related

  • 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.

  • Project
    toyxyz/ComfyUI_toyxyz_test_nodes

    A set of ready‑made ComfyUI nodes that add webcam capture, mask/region tools, 3‑D pose editing, video trimming/concatenation, and Qwen‑based prompt generation (image‑to‑Danbooru tags, MiniMax‑H3 audiovisual prompts). Install by cloning into `custom_nodes` and running a setup script; then use the nodes in any ComfyUI workflow.

  • 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.

  • Project
    nkxx188/ComfyUI-MiniMaxH3-Easy

    A practical node suite for ComfyUI that simplifies MiniMax H3 video generation, offering unified media management and tools for creating long, continuous videos via connected segments.

  • Project
    WhatDreamsCost/WhatDreamsCost-ComfyUI

    WhatDreamsCost‑ComfyUI is a collection of custom ComfyUI nodes that add video‑ and audio‑editing capabilities (timeline editor, load/trim nodes, IC‑LoRA support, audio in‑painting, etc.) for AI‑generated media workflows.