Skip to content

Songssx /ComfyUI-MiniMaxH3-TimelineDirector

ComfyUI nodes for editing a reference-media timeline in MiniMax H3
ComfyUI workflowGPL-3.0English README
Stars
541
30 days
New
Last push
9 days ago

About ComfyUI-MiniMaxH3-TimelineDirector

Lay clips, soundtracks, images and audio on one editable timeline for MiniMax H3 Reference to Video. This ComfyUI node pack renders them together. It splits long videos into segments and joins them in a single run, so faces drift less. You'll need a recent ComfyUI build, the H3 Ref2VA model, and some guides are Chinese-only.

Best for: Timeline editors who already run MiniMax H3 Reference to Video and want long-form or digital-human shots.

What it does

  • Moves, trims, splits and snaps clips on a multi-clip timeline
  • Sets each clip as Fixed Guide, Editable Reference or Boundary Only
  • Continues each segment from the last one's AV latent tail to cut drift
  • Runs two-stage sampling: low-res steps, latent lift, then high-res steps
  • Locks original audio so lip-sync follows your uploaded soundtrack
  • Exports and imports timeline presets, with or without the media files

Quickstart

Rewritten from the README. Check the repo for the latest steps.

  1. 1
    Clone the repo into your custom nodes folder: cd ComfyUI/custom_nodes then the command below
    git clone https://github.com/Songssx/ComfyUI-MiniMaxH3-TimelineDirector.git
  2. 2
    Restart ComfyUI and search the node menu for MiniMax H3
  3. 3
    Load the all-in-one workflow from example_workflows/
  4. 4
    Set width, height and generation_seconds, then add video, image and audio files
  5. 5
    Move, trim or split clips and put the cyan generation range over the part you want
  6. 6
    Connect the Material Planner's Segment Plan to Finite Segment Sampling and run

Models and languages

Models it works with

  • MiniMax H3

Interface and docs

  • English
  • Chinese

Alternatives

Other comfyui workflow projects people compare with ComfyUI-MiniMaxH3-TimelineDirector.

A few ComfyUI nodes for MiniMax H3 video, with less hand-wiring

ComfyUI workflow
  • MiniMax H3
  • Ollama
798 GitHub stars2 days agoMIT

Longer MiniMax H3 sequences with motion and sound carried across cuts

ComfyUI workflow
  • MiniMax H3
1k GitHub stars24 days agoGPL-3.0

ComfyUI nodes for character and location reference sheets from one camera move

ComfyUI workflow
  • MiniMax H3
  • Qwen3-VL
  • Krea2
72 GitHub stars1 month agoMIT

Puts WanVideo and related video models inside ComfyUI

ComfyUI workflow
  • Wan 2.1
  • Wan 2.2
  • SkyReels V2
  • +7
6.7k GitHub stars4 months agoApache-2.0

Featured on OpenMicroDrama

Do you maintain ComfyUI-MiniMaxH3-TimelineDirector? Add this badge to your README so English speakers can find our write-up.

Featured on OpenMicroDrama
markdown
[![Featured on OpenMicroDrama](https://openmicrodrama.com/badges/featured.svg)](https://openmicrodrama.com/projects/songssx-comfyui-minimaxh3-timelinedirector)

The badge links to this page. Want your description changed? Email support@openmicrodrama.com.

Reviewed Oct 1, 2026. Bundles a MiniMax H3 version of SelfLift two-stage sampling; you don't need comfyui-SelfLift installed separately. We write these descriptions ourselves. The repo's own docs are the final word.