image-gen

name	image-gen
description	Generate images from text descriptions using AI models
metadata	{"triggers":"generate image, draw, create picture, make image, image of, picture of, illustration, render, visualize, ^draw.*, ^create.*image","tags":"image, generation, ai, creative","allowed_tools":"image"}

Image Generation Skill

Create images from text descriptions.

Capabilities

• Generate images from text prompts
• Multiple style options
• Various aspect ratios
• Iterative refinement
• Image variations

Prompt Guidelines

Good prompts include:

1. Subject: What's in the image
2. Style: Art style, medium, aesthetic
3. Composition: Framing, perspective
4. Lighting: Mood, time of day
5. Details: Colors, textures, specific features

Example Prompts

Basic: "A cat sitting on a windowsill"

Detailed: "A fluffy orange tabby cat sitting on a sunny windowsill, looking outside at falling autumn leaves, warm afternoon light, cozy home interior, photorealistic"

Artistic: "A cat on a windowsill, Studio Ghibli style, soft watercolors, peaceful atmosphere"

Aspect Ratios

• Square (1:1): Social media, avatars
• Landscape (16:9): Wallpapers, presentations
• Portrait (9:16): Phone wallpapers, stories
• Wide (21:9): Cinematic, banners

Examples

• "Generate an image of a sunset over mountains"
• "Draw a cartoon robot"
• "Create a picture of a cozy coffee shop"
• "Make an illustration for my blog post about AI"

Limitations

• Cannot generate real people's faces
• May struggle with text in images
• Complex scenes may need multiple attempts