AI Artist - Prompt Engineering

Core Principles

1. Clarity - Be specific, avoid ambiguity
2. Context - Set scene, role, constraints upfront
3. Structure - Use consistent formatting (markdown, XML tags, delimiters)
4. Iteration - Refine based on outputs, A/B test variations

Quick Patterns

LLM Prompts (Claude/GPT/Gemini)

[Role] You are a {expert type} specializing in {domain}.
[Context] {Background information and constraints}
[Task] {Specific action to perform}
[Format] {Output structure - JSON, markdown, list, etc.}
[Examples] {1-3 few-shot examples if needed}

Image Generation (Midjourney/DALL-E/Stable Diffusion)

[Subject] {main subject with details}
[Style] {artistic style, medium, artist reference}
[Composition] {framing, angle, lighting}
[Quality] {resolution modifiers, rendering quality}
[Negative] {what to avoid - only if supported}

Portrait of a cyberpunk hacker, neon lighting, cinematic composition, detailed face, 8k, artstation quality --ar 16:9 --style raw

References

references/llm-prompting.md

references/image-prompting.md

references/nano-banana.md

references/advanced-techniques.md

references/domain-patterns.md

references/domain-marketing.md

references/domain-code.md

references/domain-writing.md

references/domain-data.md

Model-Specific Tips

--ar

--style

--chaos

--weird

--v 6.1

(word:1.2)

--guidance

Anti-Patterns

• Vague instructions ("make it better")
• Conflicting constraints
• Missing context for domain tasks
• Over-prompting with redundant details
• Ignoring model-specific strengths/limits