AI Artist - Prompt Engineering
Craft effective prompts for AI text and image generation models.
Core Principles
- Clarity - Be specific, avoid ambiguity
- Context - Set scene, role, constraints upfront
- Structure - Use consistent formatting (markdown, XML tags, delimiters)
- 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}
Example: Portrait of a cyberpunk hacker, neon lighting, cinematic composition, detailed face, 8k, artstation quality --ar 16:9 --style raw
References
Load for detailed guidance:
| Topic |
File |
Description |
| LLM |
references/llm-prompting.md |
System prompts, few-shot, CoT, output formatting |
| Image |
references/image-prompting.md |
Style keywords, model syntax, negative prompts |
| Nano Banana |
references/nano-banana.md |
Gemini image prompting, narrative style, multi-image input |
| Advanced |
references/advanced-techniques.md |
Meta-prompting, chaining, A/B testing |
| Domain Index |
references/domain-patterns.md |
Universal pattern, links to domain files |
| Marketing |
references/domain-marketing.md |
Headlines, product copy, emails, ads |
| Code |
references/domain-code.md |
Functions, review, refactoring, debugging |
| Writing |
references/domain-writing.md |
Stories, characters, dialogue, editing |
| Data |
references/domain-data.md |
Extraction, analysis, comparison |
Model-Specific Tips
| Model |
Key Syntax |
| Midjourney |
--ar, --style, --chaos, --weird, --v 6.1 |
| DALL-E 3 |
Natural language, no parameters, HD quality option |
| Stable Diffusion |
Weighted tokens (word:1.2), LoRA, negative prompt |
| Flux |
Natural prompts, style mixing, --guidance |
| Imagen/Veo |
Descriptive text, aspect ratio, style references |
Anti-Patterns
- Vague instructions ("make it better")
- Conflicting constraints
- Missing context for domain tasks
- Over-prompting with redundant details
- Ignoring model-specific strengths/limits
1---2name: ai-artist3description: Craft prompts for AI models (text, image, video). Use for Midjourney, DALL-E, Stable Diffusion, Flux, Veo, prompt engineering, style keywords, negative prompts, iterative refinement.4version: 1.0.05license: MIT6---78# AI Artist - Prompt Engineering910Craft effective prompts for AI text and image generation models.1112## Core Principles13141. **Clarity** - Be specific, avoid ambiguity152. **Context** - Set scene, role, constraints upfront163. **Structure** - Use consistent formatting (markdown, XML tags, delimiters)174. **Iteration** - Refine based on outputs, A/B test variations1819## Quick Patterns2021### LLM Prompts (Claude/GPT/Gemini)2223```24[Role] You are a {expert type} specializing in {domain}.25[Context] {Background information and constraints}26[Task] {Specific action to perform}27[Format] {Output structure - JSON, markdown, list, etc.}28[Examples] {1-3 few-shot examples if needed}29```3031### Image Generation (Midjourney/DALL-E/Stable Diffusion)3233```34[Subject] {main subject with details}35[Style] {artistic style, medium, artist reference}36[Composition] {framing, angle, lighting}37[Quality] {resolution modifiers, rendering quality}38[Negative] {what to avoid - only if supported}39```4041**Example**: `Portrait of a cyberpunk hacker, neon lighting, cinematic composition, detailed face, 8k, artstation quality --ar 16:9 --style raw`4243## References4445Load for detailed guidance:4647| Topic | File | Description |48|-------|------|-------------|49| LLM | `references/llm-prompting.md` | System prompts, few-shot, CoT, output formatting |50| Image | `references/image-prompting.md` | Style keywords, model syntax, negative prompts |51| Nano Banana | `references/nano-banana.md` | Gemini image prompting, narrative style, multi-image input |52| Advanced | `references/advanced-techniques.md` | Meta-prompting, chaining, A/B testing |53| Domain Index | `references/domain-patterns.md` | Universal pattern, links to domain files |54| Marketing | `references/domain-marketing.md` | Headlines, product copy, emails, ads |55| Code | `references/domain-code.md` | Functions, review, refactoring, debugging |56| Writing | `references/domain-writing.md` | Stories, characters, dialogue, editing |57| Data | `references/domain-data.md` | Extraction, analysis, comparison |5859## Model-Specific Tips6061| Model | Key Syntax |62|-------|------------|63| Midjourney | `--ar`, `--style`, `--chaos`, `--weird`, `--v 6.1` |64| DALL-E 3 | Natural language, no parameters, HD quality option |65| Stable Diffusion | Weighted tokens `(word:1.2)`, LoRA, negative prompt |66| Flux | Natural prompts, style mixing, `--guidance` |67| Imagen/Veo | Descriptive text, aspect ratio, style references |6869## Anti-Patterns7071- Vague instructions ("make it better")72- Conflicting constraints73- Missing context for domain tasks74- Over-prompting with redundant details75- Ignoring model-specific strengths/limits
ngxtm