minimax-h3-video SKILL.md skillA

minimax-h3-video from artokun/comfyui-mcp is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add artokun/comfyui-mcp/minimax-h3-video@git:20260903.a04162b

Pins git:20260903.a04162b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
artokun/comfyui-mcp
Path
plugin/skills/minimax-h3-video/SKILL.md
Versions recorded
3
Latest version
git:20260903.a04162b, committed Sep 3, 2026
First version recorded
Aug 19, 2026
Size
13,869 bytes
Repository stars
896
License
MIT

Build MiniMax H3 (Hailuo) local video workflows with native T2V/I2V/R2V nodes, Comfy-Org INT8 weights, turbo LoRAs for 8GB VRAM, 15-second stereo-audio clips, and the official MiniMax prompting guides (cite by link, do not copy).

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# MiniMax H3 (Hailuo) — local video

This skill teaches the **local-weights** MiniMax H3 path in ComfyUI. It is the
pilot for `#1155` (Official vs Empirical sources) because MiniMax publishes a
real prompting guide. **Cite that guide by URL. Do not copy it into this repo.**

## Two products, two cost models — pick one

They share a brand and **must not be mixed**.

| Path | Nodes | Cost | VRAM | When |
|---|---|---|---|---|
| **Local weights** (this skill) | `MiniMaxH3ImageToVideo`, `MiniMaxH3ReferenceToVideo`, `EmptyMiniMaxH3LatentAV`, `MiniMaxH3SigmaShift`, `MiniMaxH3MemoryEfficientSageAttentionPatch` | Free after download | Yes — INT8 + turbo LoRA is the 8 GB story | User wants 4–15 s stereo clips on their GPU |
| **Partner API** | `MinimaxHailuo03TextToVideoNode`, `MinimaxHailuo03FirstLastFrameNode`, `MinimaxHailuo03ReferenceNode`, `MinimaxTextToVideoNode`, `MinimaxImageToVideoNode`, `MinimaxHailuoVideoNode` | Paid per generation | None | User has a MiniMax / Hailuo API key and does not want local weights |

API nodes do not take `MiniMaxH3SigmaShift` or Sage-attention patches. Local
nodes do not spend API credits. If the user asked for Hailuo *cloud*, stop and
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add artokun/comfyui-mcp/minimax-h3-video@sha256:747f0276507f3747

The line at the top of this page pins the label git:20260903.a04162b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_lthjoy7j2hffyhn3.svg)](https://markdownregistry.com/a/art_lthjoy7j2hffyhn3)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Aug 19, 2026 and Sep 3, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20260903.a04162b latest2026-09-03 a04162b 13,869 BA view · diff
git:20260825.973d5782026-08-25 973d578 13,700 BA view · diff
git:20260819.f9584a12026-08-19 f9584a1 13,717 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (13869 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

artokun/comfyui-mcp · 896 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lthjoy7j2hffyhn3
GET https://markdownregistry.com/api/v1/resolve?ref=artokun/comfyui-mcp/minimax-h3-video
GET https://markdownregistry.com/api/v1/blob/747f0276507f3747d9eb698e49555f85b848ee4c0822ce93a976f2f1e99c9e6e

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from artokun/comfyui-mcp

ai-toolkit-trainer SKILL.md skill
artokun/comfyui-mcp · plugin/skills/ai-toolkit-trainer/SKILL.md · Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base…
git:20260825.cab59a6 · audit A · 896 stars
anima-base SKILL.md skill
artokun/comfyui-mcp · plugin/skills/anima-base/SKILL.md · Anime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT). Use for anime, manga, illustrated characters; accepts…
git:20260827.6cfca93 · audit A · 896 stars
anima-lora-trainer SKILL.md skill
artokun/comfyui-mcp · plugin/skills/anima-lora-trainer/SKILL.md · Train a custom anime LoRA on the ANIMA base model with Citron's local Gradio trainer (kohya sd-scripts), <6GB VRAM…
git:20260825.cab59a6 · audit B · 896 stars
civitai SKILL.md skill
artokun/comfyui-mcp · plugin/skills/civitai/SKILL.md · Discover Civitai models with the BUILT-IN download_model action:"search_civitai" and install/generate them locally…
git:20260825.cab59a6 · audit A · 896 stars
color-correction SKILL.md skill
artokun/comfyui-mcp · plugin/skills/color-correction/SKILL.md · Diagnose and fix video/image color OBJECTIVELY with the get_image (action:"analyze_color") tool (scopes/stats such as…
git:20260825.cab59a6 · audit A · 896 stars
comfyui-core SKILL.md skill
artokun/comfyui-mcp · plugin/skills/comfyui-core/SKILL.md · Core ComfyUI knowledge covering workflow format, node types, pipeline patterns, and MCP tool usage
git:20261025.d36a05c · audit A · 896 stars
comfyui-frontend-extensions SKILL.md skill
artokun/comfyui-mcp · plugin/skills/comfyui-frontend-extensions/SKILL.md · Authoring ComfyUI v2 frontend extensions with @comfyorg/extension-api, covering…
git:20260825.cab59a6 · audit A · 896 stars
comfyui-launch-flags SKILL.md skill
artokun/comfyui-mcp · plugin/skills/comfyui-launch-flags/SKILL.md · Pick the right ComfyUI startup flags for VRAM, attention, caching, and speed. The full decision matrix for OOM…
git:20260825.cab59a6 · audit A · 896 stars
comfyui-node-registry SKILL.md skill
artokun/comfyui-mcp · plugin/skills/comfyui-node-registry/SKILL.md · Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec…
git:20260825.cab59a6 · audit A · 896 stars
debug-render SKILL.md skill
artokun/comfyui-mcp · plugin/skills/debug-render/SKILL.md · Debug a WRONG or imperfect render (not a hard error) by inspecting inputs and intermediate steps with run-to-node…
git:20260825.cab59a6 · audit A · 896 stars
director SKILL.md skill
artokun/comfyui-mcp · plugin/skills/director/SKILL.md · Full production pipeline covering story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips…
git:20260825.cab59a6 · audit A · 896 stars
ernie-image SKILL.md skill
artokun/comfyui-mcp · plugin/skills/ernie-image/SKILL.md · Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise…
git:20260825.cab59a6 · audit A · 896 stars

Every file in artokun/comfyui-mcp

Browse by kind, by grade A, or by owner.