skills.rest
jau123
jau123COMMUNITY
Explore all skills by this author →
𝕏@meigen7982GitHub

AI Image & Video Generator — GPT Image 2, Seedance, ComfyUI

Generate images and videos from text prompts and reference images.

1.7k|219|Updated Feb 7, 2026
Search Tags:#image generation#mcp server#video generation#ai design#comfyui#reference images#prompt enhancement
One-click install
npx skills add https://github.com/jau123/MeiGen-AI-Design-MCP --skill ai-image-video-generator-gpt-image-2-seedance-comfyui
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: AI Image & Video Generator — GPT Image 2, Seedance, ComfyUI
Source: https://github.com/jau123/MeiGen-AI-Design-MCP/tree/main/openclaw
Command: npx skills add https://github.com/jau123/MeiGen-AI-Design-MCP --skill ai-image-video-generator-gpt-image-2-seedance-comfyui

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the friction of managing multiple image and video generation tools by giving you one workflow for prompt enhancement, model selection, reference-image editing, and local or cloud-backed generation.

Core Features & Use Cases

  • Prompt-to-Image Generation: Turn short ideas or detailed briefs into polished images using multiple providers and models.
  • Prompt Enhancement: Expand rough concepts into production-ready prompts with style-aware guidance for realistic, anime, or illustration outputs.
  • Inspiration and Asset Search: Search a curated library of prompts, inspect examples, and reuse successful creative directions.
  • Reference Image Workflows: Generate edits, variations, and style-guided outputs from uploaded images or local files.
  • ComfyUI and Provider Routing: Switch between MeiGen cloud, OpenAI-compatible APIs, and local ComfyUI workflows without changing your creative process.
  • Use Case: A marketer can draft a product-shot concept, enhance the prompt, generate several variations, and then reuse the best image as a reference for mockups.

Quick Start

Ask the AI to generate a polished image or video from your idea, and include any style, aspect ratio, reference image, or provider preference you want applied.

Frequently Asked Questions about AI Image & Video Generator — GPT Image 2, Seedance, ComfyUI

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI images and videos from text prompts and reference images?▼

You can generate AI images and videos by providing text prompts, reference images, and style preferences. The Skill applies style-aware prompt enhancement and routes the request across cloud or local ComfyUI workflows to produce the final visual assets.

Can I use ComfyUI workflows for local video generation alongside cloud APIs?▼

Yes, ComfyUI workflow management supports local generation alongside MeiGen cloud and OpenAI-compatible APIs. Multi-provider routing allows you to switch generation environments without altering your creative process.

How does prompt enhancement work for anime illustrations and realistic product shots?▼

Prompt enhancement expands rough concepts into production-ready prompts using style-aware guidance. It tailors the prompt vocabulary specifically for realistic, anime, or illustration outputs before executing the generation task.

Do I need an existing reference image to generate style variations?▼

You do not need a reference image to start, but providing one enables deterministic reference image workflows. The Skill uses uploaded images or local files to generate edits, variations, and style-guided outputs.

What is the best way to find prompt templates for design production and concept exploration?▼

The best way is searching the built-in prompt gallery, which provides a curated library of successful creative directions. You can inspect examples and reuse proven templates for your specific design production needs.

Are there limitations when switching between multi-provider routing for AI design tasks?▼

The main limitation is ensuring provider compatibility with your specific generation parameters and reference images. While multi-provider routing supports cloud and local ComfyUI workflows, deterministic handling depends on the selected provider's capabilities.

Related Skills

Explore More Design & Creative Skills→
resultanyildiziresultanyildizi
4

nano-banana-pro

Generate and edit images via Google's Gemini 3 Pro Image API.

Community
Intermediate
renatoasserenatoasse
2.0k

image-ai-generator

Generate branded AI images from text prompts and save them locally.

Community
Intermediate
icyzhicyzh
1

comfyui

Execute generative AI workflows for images, video, and audio via ComfyUI APIs.

Community
Advanced
xtekkyxtekky
66.5k

gpt4free

Access multiple AI providers and models through a unified interface.

Community
Advanced