image-gen

Overview

AI image generation creates images from text prompts using diffusion models. This skill covers prompt engineering for consistent results, inpainting/outpainting for editing, ControlNet for precise control, and API integration for production workflows.

Capabilities

• Generate images from text prompts (DALL-E, Stable Diffusion, Midjourney)
• Engineer prompts with positive/negative prompts, style modifiers, and weights
• Edit existing images with inpainting and outpainting
• Use ControlNet for pose, depth, and edge-guided generation
• Batch generate images for content pipelines
• Integrate via API (OpenAI, Stability AI, Replicate)
• Set up local generation with ComfyUI or Automatic1111

When to Use

Trigger phrases:

• "image gen"

• "AI image generation — Stable Diffusion, Midjourney, DALL-E, ComfyUI"

• Creating marketing visuals, thumbnails, social media images

• Generating product mockups and concept art

• Building content pipelines that need custom images

• Editing photos (remove backgrounds, change styles)

• Creating consistent character/brand imagery

When NOT to Use

• Task is about content strategy, not creation (use strategy skills)
• Task is about content distribution (use distribution skills)
• You need to analyze content performance (use analytics skills)
• Task is about content moderation (use moderation tools)
• You don't have content guidelines
• Task requires domain expertise (consult experts)

Pseudo Code

The image-gen workflow follows a standard pipeline pattern.

Core flow:

# image-gen primary flow
input = prepare(raw_data)
result = process(input, config={comfyui, controlnet, dall, diffusion, engineering})
validate(result)
deliver(result)

Error handling:

on error:
  log(error_details)
  retry_with_backoff(max=3)
  if still_failing: alert_and_escalate()

Core Workflow

# image-gen primary flow
input = prepare(raw_data)
result = process(input, config={comfyui, controlnet, dall, diffusion, engineering})
validate(result)
deliver(result)