MiniMax-AI/MiniMax-H3

Generative mediaPython

2.0 Cooling Magnitude out of 10. Star growth looks organic. Data as of September 14, 2026.

About the project

MiniMax H3 is an omni-modal generative system that understands text, images, video and audio and generates video with native stereo audio up to 2K and 15 seconds. The repository bundles prompt-writing and style-specific video generation skills.

Useful for

Install the h3-prompt-writing skill to craft video prompts in Claude Code or Cursor
Build a Ref2VA prompt using multiple reference images, videos and audio clips
Generate a video in a specific style (3D animation, music video, ad) via the MiniMax Hub canvas workflow

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

0 stars so far today, about 24 expected by the end of the day.
Interest is fading: the two-day pace is 31% of the previous week and a half.
The repository is 46 days old and already has 8,569 stars.
Top new repositories in the last 4 months: #40.
About 6 forks a day — people are taking the code.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 8,569
Stars in a day: 24
Forks: 594
Issues and pull requests: 73
Watchers: 66
Language: Python
Created: July 30, 2026
Last push: August 15, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 14, 2026Top new repositories in the last 4 months: #40
September 13, 2026Top new repositories in the last 4 months: #40

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/MiniMax-AI/MiniMax-H3.svg?lang=en)](https://gitnova.dev/en/r/MiniMax-AI/MiniMax-H3)

Similar projects

7.0
multimodal-art-projection/YuE
YuE2 is a music generation model: from lyrics and a style prompt it builds an editable melody-and-chord plan, then renders a full song with vocals and accompaniment. It supports zero-shot covers and agentic composition…

BreakoutGenerative mediaPython+303 stars in a day
5.9
debpalash/VoiceStudio
A fully local, open-source ElevenLabs alternative for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation on your own hardware, with no account or API key. Supports 16 TTS and 11…

BreakoutGenerative mediaPython+1,785 stars in a day
5.0
eternityspring/reelbench-skills
A set of Claude Code and Codex skills for video work: video-shots breaks a finished clip into a shot-by-shot analysis table (duration, shot size, camera moves), video-sync renders video with a side panel of shot info…

Early signalGenerative mediaHTML+132 stars in a day
4.4
calesthio/OpenMontage
Open-source agentic video production system: an AI coding assistant researches, scripts, generates assets, edits and renders a finished video from a plain-language prompt. 12 pipelines, 100+ tools and 700+ agent skill…

BreakoutGenerative mediaPython+420 stars in a day
4.4
govin-ai/dunhuang-aura-skill
An AI Skill for generating and editing commercial visuals in the Dunhuang mineral aesthetic, usable in Codex, Claude Code and other SKILL.md-compatible agent environments.

Early signalGenerative mediaPython+41 stars in a day
4.2
heygen-com/hyperframes
Framework for turning HTML, CSS, media and seekable animations into deterministic MP4 videos. Runs locally via CLI or from AI coding agents through a set of skills.

SteadyGenerative mediaTypeScript+315 stars in a day