#166 · Primary category: Video & Animation
ComfyUI_MiniMaxH3_Director
ComfyUI MiniMax H3 Director workflow
Project last updated:08/04/26
GitHub Stars
816
Forks
87
Contributors
1
License
Apache-2.0
Why we included this project
MiniMax H3 is a capable video model, but getting it running inside ComfyUI means wiring up the right custom node and model files. This repo bundles five ready-to-import workflows covering the main generation modes: text-to-video, image-to-video, first/last-frame animation, reference-driven generation, and segment-by-segment video editing. They're a copy of the upstream Director plugin's examples, kept here for easy download and testing, so you get a verified starting point instead of assembling node graphs from scratch. The README is refreshingly concrete about what runs on a 4090-class card, which weights each mode needs, and how to do things like swap a face in a source clip using a reference image and optional audio; it also explains the Director's per-segment caching and frame handoff, so you know when editing one shot won't force a full re-render. For anyone evaluating MiniMax H3 locally, it's a solid reference for learning the node wiring and running controlled A/B tests.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
yt-dlp
A feature-rich command-line audio/video downloader
MoneyPrinterTurbo
Generate HD short videos from a topic or keyword with an automated AI workflow.
Deep-Live-Cam
real time face swap and one-click video deepfake with only a single image
manim
Animation engine for explanatory math videos
anime
JavaScript animation engine