Meigen design

Skill ed1son99/skills/skills/ai-media/meigen-design

Multi-model AI image and video generation via MeiGen — supports GPT Image 2, Nanobanana 2, Seedream 5.0, Midjourney V8.1, Flux 2 Klein, Seedance 2.0, Happyhorse 1.0, Veo 3.1, and local ComfyUI. Use when the user wants to generate, edit, or transform images and videos using state-of-the-art AI models.From its SKILL.md

Install

npx -y skills add ed1son99/skills --skill meigen-design

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 364 tokens by cl100k_base, as published. Nobody here has run it

MeiGen AI Design

Generate images and videos using 9 leading AI models through a single MCP server.

Setup

Add to your mcp_servers config:

mcp_servers:
  meigen:
    command: npx
    args: ["-y", "@jau/meigen-mcp"]
    env:
      MEIGEN_API_KEY: "${MEIGEN_API_KEY}"
    timeout: 300 # video gen can take minutes

Get a key at MeiGen cloud or use your own OpenAI-compatible API endpoint.

Supported Models

Model	Type	Best For
GPT Image 2	Image	General purpose, photorealistic
Midjourney V8.1	Image	Artistic, stylized
Flux 2 Klein	Image	Fast, high quality
Seedream 5.0	Image	Cinematic, dreamlike
Nanobanana 2	Image	Anime, illustrations
Seedance 2.0	Video	Short video clips
Happyhorse 1.0	Video	Fast video gen
Veo 3.1	Video	High quality video
ComfyUI (local)	Both	Fully offline, custom workflows

Usage

# Generate image
meigen generate --model "midjourney-v8-1" --prompt "a serene mountain lake at sunset"

# Generate video
meigen generate --model "veo-3-1" --prompt "a dog running on a beach"

# Edit image
meigen edit --image path/to/image.jpg --prompt "add a rainbow in the sky"

What ships with it: 13 files

2284.7 KB alongside SKILL.md