cyberneticlibrary
← library

Generate and edit images automatically

generate-imagesskillsetup L2★17
cfircoo/claude-code-toolkit ↗
What it does

Generate images from text prompts using diffusion models or generative APIs

Best for

Rapidly prototypes visual assets without hiring artists, useful for mockups, thumbnails, and design exploration.

Inputs
  • · [object Object]
  • · [object Object]
  • · [object Object]
Outputs
  • · [object Object]
  • · [object Object]
  • · [object Object]
Requires
  • · Stable Diffusion
  • · DALL-E API
  • · Midjourney API
  • · Ollama (local)
Preconditions

API keys configured or local GPU for inference

Failure modes

Vague prompts produce random outputs; model hallucinations (extra limbs, text garbling); token limits on prompt length

Trust signals
  • · Diffusion model selection per use case
  • · Seed control for reproducibility
  • · Style/aesthetic modifiers