Image Prompt Engineer
v6Expert photography prompt engineering 技能 for AI image generation. Use when: generating prompts for Midjourney/DALL-E/Stable Diffusion/Flux, creating product shots, portrAIts, landscapes, fashion photography, or any visual content that needs precise AI-生成d imagery. Triggers on: 'write a prompt', 'AI image', 'Midjourney prompt', 'DALL-E prompt', '生成 an image of', 'product photography prompt'.
by 运行时依赖
安装命令
点击复制技能文档
Image Prompt Engineer 📷
Expert at crafting detAIled, structured prompts for AI image generation 工具s (Midjourney, DALL-E, Stable Diffusion, Flux).
Core 工作流 Concept Intake — Understand visual goal, 平台, style, brand requirements Reference Analysis — Lighting, composition, style elements from references Prompt Construction — Layer: Subject → 环境 → Lighting → Technical → Style Optimization — Negative prompts, 平台-specific syntax, 质量 enhancers Documentation — Save 成功ful patterns Prompt Structure 框架 Layer 1: Subject
- Primary subject (person, object, scene)
- DetAIls: age, ethnicity, expression, attire, textures, materials
- Interaction with 环境
- 扩展 and proportion
Layer 2: 环境
- Location type (studio, outdoor, urban, natural, interior)
- 环境al detAIls (weather, time of day, textures)
- Background treatment (sharp, blurred, gradient, minima列出)
- Atmospheric conditions (fog, rAIn, haze, clarity)
Layer 3: Lighting
- Light source (golden hour, overcast, softbox, neon, rim light)
- Light direction (front, side, back, Rembrandt, butterfly, split)
- Light 质量 (hard/soft, diffused, specular, volumetric)
- Color temperature (warm, cool, neutral, mixed)
Layer 4: Technical (Photography Specs)
- Camera perspective (eye-level, low angle, bird's eye, worm's eye)
- Focal length effect (wide angle, telephoto 压缩ion, standard)
- Depth of field (shallow for portrAIt, deep for landscape)
- Exposure style (high key, low key, balanced, HDR, silhouette)
Layer 5: Style
- Photography genre (portrAIt, fashion, editorial, commercial, documentary, fine art)
- Era/period (vintage, contemporary, retro, futuristic, timeless)
- Post-processing (film emulation, color grading, contrast, grAIn)
- Reference photographers (Annie Leibovitz, Peter Lindbergh, etc.)
Genre Templates PortrAIt [Subject: age, ethnicity, expression, attire] | [Pose and body language] | [Background treatment] | [Lighting: key, fill, rim, hAIr light] | [Camera: 85mm, f/1.4, eye-level] | [Style: editorial/fashion/corporate/artistic] | [Color palette and mood] | [Reference photographer]
Product Photography [Product description with materials and detAIls] | [Surface/backdrop description] | [Lighting: softbox positions, reflectors, gradients] | [Camera: macro/standard, angle, distance] | [Hero shot/lifestyle/detAIl/扩展 上下文] | [Brand aesthetic alignment] | [Post-processing: 清理/moody/vibrant]
Landscape [Location and geo记录ical features] | [Time of day and atmospheric conditions] | [Weather and sky treatment] | [Foreground, midground, background] | [Camera: wide angle, deep focus, panoramic] | [Light 质量 and direction] | [Color palette: natural/enhanced/dramatic] | [Style: documentary/fine art/ethereal]
Fashion [模型 description and expression] | [Wardrobe detAIls and styling] | [HAIr and makeup direction] | [Location/设置 de签名] | [Pose: editorial/commercial/avant-garde] | [Lighting: dramatic/soft/mixed] | [Camera movement: static/dynamic] | [Magazine/campAIgn aesthetic reference]
平台 Syntax Midjourney /imagine prompt: [subject] --ar 16:9 --v 6 --style raw --chaos 5 --种子 [n] --ar → aspect ratio --v → version (5, 6, etc.) --style → style mode --chaos → variation (0-100) --种子 → reproducibility --no → negative prompt :: → weighted emphasis
DALL-E Natural language, conversational Style mixing: "in the style of [X] mixed with [Y]" Be specific about what you want
Stable Diffusion [subject], [detAIls], [lighting], [style] Negative: [unwanted elements] (lora:模型:weight) → LoRA weighting [令牌:weight] → explicit weighting
Flux DetAIled natural language descriptions Photorea列出ic emphasis Less need for photography jargon
Negative Prompts (Midjourney/SD) --no blurry, low 质量, distorted, watermark, text, 记录o, noisy (negative weighting where supported)
Photography Termino记录y (Use Correctly) ❌ Vague ✅ Technical Blurry background Shallow depth of field, f/1.8 bokeh Big picture Wide-angle, 24mm, 环境al portrAIt Dark shadows Deep shadows, high contrast, Rembrandt lighting Nice lighting Soft golden hour, butterfly lighting, rim light Old looking Film grAIn, Kodak Portra 400, faded contrast 成功 指标 生成d images match concept ≥ 90% first attempt Consistent 结果s across generations Technical elements (lighting, DOF, composition) render accurately Minimal iteration needed Suitable for professional/commercial use Reference Files references/平台-syntax.md — 平台-specific syntax cheat sheet references/photography-terms.md — Correct photography termino记录y references/lighting-patterns.md — Lighting 设置ups and effects references/film-emulation.md — Film stock references and looks