Image Generation Skill

Purpose

Generate images, videos, and music from text descriptions using advanced multimodal AI models.

When to Use

• User requests image generation
• Video creation requests
• Music/audio generation
• Visualization of concepts
• Design mockups needed

Capabilities

Image Generation

• Text-to-image from descriptions
• Image editing (modify existing)
• Style transfer
• Multi-image composition

Video Generation

• Text-to-video
• Image-to-video
• Video editing/extension

Music Generation

• Text-to-music
• Genre and mood control
• Instrument selection
• Tempo specifications

Parameters

Parameter	Type	Required	Description
type	string	Yes	"image", "video", or "music"
prompt	string	Yes	Detailed description
style	string	No	Art style (realistic, cartoon, abstract, etc.)
duration	number	No	For video/music in seconds

Example Usage

{
  "skill": "image_generation",
  "parameters": {
    "type": "image",
    "prompt": "a futuristic cityscape at sunset with flying cars",
    "style": "cyberpunk"
  }
}

Best Practices

• Use detailed, specific prompts
• Include style and mood descriptions
• Specify key elements to include
• Iterate if first result isn't satisfactory