Image Generator

AI image generation skill using DALL-E, Stable Diffusion, or Midjourney API. Generate, edit, and vary images from text prompts.

Generate AI images using DALL-E, Stable Diffusion, or other providers.

When to Use

• User wants to generate an image from text
• Create variations of existing images
• Edit images with AI inpainting
• Generate thumbnails or illustrations

Configuration

# OpenAI DALL-E
export OPENAI_API_KEY="sk-xxx"

# Stability AI
export STABILITY_API_KEY="sk-xxx"

# Replicate (for SDXL, etc.)
export REPLICATE_API_TOKEN="r8_xxx"

Usage

Generate image

python3 scripts/generate_image.py \
  --prompt "A serene mountain landscape at sunset" \
  --size "1024x1024" \
  --output "./output.png"

Generate variations

python3 scripts/generate_image.py \
  --vary "./input.png" \
  --count 4 \
  --output-dir "./variations"

Edit image (inpainting)

python3 scripts/generate_image.py \
  --edit "./input.png" \
  --mask "./mask.png" \
  --prompt "Add a rainbow in the sky"

With style presets

python3 scripts/generate_image.py \
  --prompt "A futuristic city" \
  --style "cyberpunk" \
  --negative "blurry, low quality"

Output

{
  "success": true,
  "image_path": "./output.png",
  "revised_prompt": "A serene mountain landscape..."
}