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-artist-23description: Write and optimize prompts for AI-generated outcomes across text and image models. Use when crafting prompts for LLMs (Claude, GPT, Gemini), image generators (Midjourney, DALL-E, Stable Diffusion, Imagen, Flux), or video generators (Veo, Runway). Covers prompt structure, style keywords, negative prompts, chain-of-thought, few-shot examples, iterative refinement, and domain-specific patterns for marketing, code, and creative writing.4license: MIT5---6
7# AI Artist - Prompt Engineering
8
9Craft effective prompts for AI text and image generation models.
10
11## Core Principles
12
131. **Clarity** - Be specific, avoid ambiguity
142. **Context** - Set scene, role, constraints upfront
153. **Structure** - Use consistent formatting (markdown, XML tags, delimiters)
164. **Iteration** - Refine based on outputs, A/B test variations
17
18## Quick Patterns
19
20### LLM Prompts (Claude/GPT/Gemini)
21
22```
23[Role] You are a {expert type} specializing in {domain}.
24[Context] {Background information and constraints}
25[Task] {Specific action to perform}
26[Format] {Output structure - JSON, markdown, list, etc.}
27[Examples] {1-3 few-shot examples if needed}
28```
29
30### Image Generation (Midjourney/DALL-E/Stable Diffusion)
31
32```
33[Subject] {main subject with details}
34[Style] {artistic style, medium, artist reference}
35[Composition] {framing, angle, lighting}
36[Quality] {resolution modifiers, rendering quality}
37[Negative] {what to avoid - only if supported}
38```
39
40**Example**: `Portrait of a cyberpunk hacker, neon lighting, cinematic composition, detailed face, 8k, artstation quality --ar 16:9 --style raw`
41
42## References
43
44Load for detailed guidance:
45
46| Topic | File | Description |
47|-------|------|-------------|
48| LLM | `references/llm-prompting.md` | System prompts, few-shot, CoT, output formatting |
49| Image | `references/image-prompting.md` | Style keywords, model syntax, negative prompts |
50| Nano Banana | `references/nano-banana.md` | Gemini image prompting, narrative style, multi-image input |
51| Advanced | `references/advanced-techniques.md` | Meta-prompting, chaining, A/B testing |
52| Domain Index | `references/domain-patterns.md` | Universal pattern, links to domain files |
53| Marketing | `references/domain-marketing.md` | Headlines, product copy, emails, ads |
54| Code | `references/domain-code.md` | Functions, review, refactoring, debugging |
55| Writing | `references/domain-writing.md` | Stories, characters, dialogue, editing |
56| Data | `references/domain-data.md` | Extraction, analysis, comparison |
57
58## Model-Specific Tips
59
60| Model | Key Syntax |
61|-------|------------|
62| Midjourney | `--ar`, `--style`, `--chaos`, `--weird`, `--v 6.1` |
63| DALL-E 3 | Natural language, no parameters, HD quality option |
64| Stable Diffusion | Weighted tokens `(word:1.2)`, LoRA, negative prompt |
65| Flux | Natural prompts, style mixing, `--guidance` |
66| Imagen/Veo | Descriptive text, aspect ratio, style references |
67
68## Anti-Patterns
69
70- Vague instructions ("make it better")
71- Conflicting constraints
72- Missing context for domain tasks
73- Over-prompting with redundant details
74- Ignoring model-specific strengths/limits
diegosouzapw