ai-artist

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

AI Artist - Prompt Engineering

AI Artist - 提示词工程

Craft effective prompts for AI text and image generation models.

为AI文本和图像生成模型打造有效的提示词。

Core Principles

核心原则

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

清晰性 - 具体明确，避免歧义
上下文 - 提前设定场景、角色和约束条件
结构化 - 使用统一的格式（markdown、XML标签、分隔符）
迭代性 - 根据输出结果优化，进行A/B测试变体

Quick Patterns

快速模板

LLM Prompts (Claude/GPT/Gemini)

LLM提示词（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}

[角色] 你是一名专注于{领域}的{专家类型}。
[上下文] {背景信息和约束条件}
[任务] {需要执行的具体操作}
[格式] {输出结构 - JSON、markdown、列表等}
[示例] {如有需要，提供1-3个少样本示例}

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

图像生成提示词（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

[主体] {带有细节的主要主体}
[风格] {艺术风格、媒介、艺术家参考}
[构图] {取景、角度、光线}
[画质] {分辨率修饰词、渲染质量}
[负面提示] {需要避免的内容 - 仅在模型支持时使用}

示例：

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

References

参考资料

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

加载以下文件获取详细指导：

主题	文件	描述
LLM	`references/llm-prompting.md`	系统提示词、少样本、思维链（CoT）、输出格式
图像	`references/image-prompting.md`	风格关键词、模型语法、负面提示词
Nano Banana	`references/nano-banana.md`	Gemini图像提示词、叙事风格、多图像输入
高级技巧	`references/advanced-techniques.md`	元提示词、链式提示、A/B测试
领域索引	`references/domain-patterns.md`	通用模板、各领域文件链接
营销	`references/domain-marketing.md`	标题、产品文案、邮件、广告
代码	`references/domain-code.md`	函数、代码评审、重构、调试
写作	`references/domain-writing.md`	故事、角色、对话、编辑
数据	`references/domain-data.md`	提取、分析、对比

Model-Specific Tips

模型专属技巧

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

模型	关键语法
Midjourney	`--ar` , `--style` , `--chaos` , `--weird` , `--v 6.1`
DALL-E 3	自然语言，无需参数，支持高清画质选项
Stable Diffusion	加权标记 `(word:1.2)` 、LoRA、负面提示词
Flux	自然提示词、风格混合、 `--guidance`
Imagen/Veo	描述性文本、宽高比、风格参考

Anti-Patterns

反模式

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

模糊的指令（如“做得更好”）
冲突的约束条件
领域任务缺少上下文
提示词冗余过度
忽略模型的特定优势/限制