Image Generation Prompt Best Practices
Prompt Structure
Enhance every image generation prompt around three core elements:
1. SUBJECT (What)
- Physical characteristics: textures, materials, colors, scale
- Actions, poses, expressions if applicable
- Distinctive features that define the subject
2. CONTEXT (Where/When)
- Setting, background, spatial relationships (foreground, midground, background)
- Time of day, weather, atmospheric conditions
- Mood and emotional tone of the scene
3. STYLE (How)
- Artistic or photographic approach: reference specific artists, movements, or styles
- Camera/lens choices: specify focal length, aperture, and shooting angle when photographic
Core Principles
- Preserve intent — Add visual details (lighting, texture, composition) only in areas the user left unspecified; keep all user-specified elements unchanged
- Positive descriptions only — Describe what should be present; rephrase any exclusion as an inclusion
- Specific over vague — "golden hour sunlight at 15° angle" beats "nice lighting"
- Natural flow — Weave elements into a single flowing description, not a bullet list
Output Format
Return the enhanced prompt as a single flowing paragraph. When the user provides multiple requests, return each as a separate enhanced prompt under a labeled heading.
Enhancement Patterns
Hyper-Specific Details
Add concrete visual details for any Subject/Context/Style element not specified by the user:
- Lighting → direction, quality, color temperature, shadow behavior
- Textures → surface materials, weathering, reflectivity
- Atmosphere → particulates, humidity, depth haze
- Scale → relative sizes, distances, proportions
Camera Control Terminology
When a photographic look is appropriate:
- Lens type: "shot with 85mm portrait lens", "wide-angle 24mm"
- Aperture: "shallow depth of field at f/1.8", "deep focus at f/11"
- Angle: "low angle emphasizing height", "bird's eye view"
- Motion: "motion blur on the paws", "frozen mid-action"
Atmospheric Enhancement
Convey mood through environmental details:
- Emotional tone with visual indicators: "serene (soft diffused light, muted palette)", "ominous (low contrast, heavy shadows, desaturated)", "jubilant (high saturation, warm tones, dynamic motion)"
- Weather/air: "morning mist", "dust particles in a sunbeam"
Text in Images
When the image should contain readable text (signs, labels, titles, typography):
- Specify the exact text content in quotes:
"OPEN 24 HOURS" in bold sans-serif
- Describe visual treatment: font style, weight, size relative to the scene
- Define placement and integration: "centered on the storefront awning", "hand-lettered on the chalkboard"
Feature Patterns
Character Consistency
When the same character must be recognizable across multiple images:
- Include at least 3 recognizable visual markers (distinctive scar, signature clothing, unique hairstyle, characteristic accessory)
- Use anchoring words: "distinctive", "signature", "always wears", "always has"
- Be specific: "round tortoiseshell glasses" not just "glasses"
Compositional Integration
When combining multiple visual elements in one scene:
- Define spatial relationships with proportions: "foreground (40% of frame)", "midground", "background"
- Define how elements interact spatially and visually: overlap, reflection, shared lighting, color echo between foreground and background
- Specify relative scale and interaction between elements
Real-World Accuracy
When depicting real places, cultures, or historical elements:
- Use specific terminology: "traditional Edo-period architecture", "authentic Moroccan zellige tilework"
- Include culturally accurate details
- Reference geographical or historical specifics
Purpose-Driven Enhancement
Tailor the prompt to the intended use:
| Purpose |
Emphasis |
| Product photo |
Clean background, studio lighting, commercial appeal |
| UI mockup |
Flat design elements, consistent spacing, screen-appropriate |
| Presentation slide |
Bold composition, clear focal point, text-friendly layout |
| Social media |
Eye-catching, vibrant, crop-friendly aspect ratio |
| Book/album cover |
Typography space, dramatic mood, symbolic elements |
Image Editing
When modifying an existing image:
- Preserve the original's core characteristics: color palette, lighting style, composition
- Use anchoring phrases: "maintain the existing...", "preserve the original...", "keep the same..."
- Be specific about what to change vs what to keep unchanged
- Describe modifications relative to the existing image, not from scratch
Ambiguous Cases
- When user intent is unclear between photographic and illustrative style, ask before enhancing
- When enhancement would significantly change the user's concept, present the original interpretation alongside the enhanced version
- When cultural or historical accuracy cannot be verified, flag the uncertainty rather than guessing
Scope
This skill covers static image prompt enhancement only. It does not cover video generation, 3D rendering, or image analysis/description.
Example
Input: "A happy dog in a park"
Enhanced: "Golden retriever mid-leap catching a red frisbee, ears flying, tongue out in joy, in a sunlit urban park. Soft morning light filtering through oak trees creates dappled shadows on emerald grass. Background shows families on picnic blankets, slightly out of focus. Shot from low angle emphasizing the dog's athletic movement, with motion blur on the paws suggesting speed."
1---
2name: image-generation
3description: Optimizes image generation prompts using Subject-Context-Style structure. Use this skill when generating images, creating illustrations, photos, visual assets, editing images, or crafting prompts for any image generation model.
4---
5
6# Image Generation Prompt Best Practices
7
8## Prompt Structure
9
10Enhance every image generation prompt around three core elements:
11
12### 1. SUBJECT (What)
13
14- Physical characteristics: textures, materials, colors, scale
15- Actions, poses, expressions if applicable
16- Distinctive features that define the subject
17
18### 2. CONTEXT (Where/When)
19
20- Setting, background, spatial relationships (foreground, midground, background)
21- Time of day, weather, atmospheric conditions
22- Mood and emotional tone of the scene
23
24### 3. STYLE (How)
25
26- Artistic or photographic approach: reference specific artists, movements, or styles
27- Camera/lens choices: specify focal length, aperture, and shooting angle when photographic
28
29## Core Principles
30
31- **Preserve intent** — Add visual details (lighting, texture, composition) only in areas the user left unspecified; keep all user-specified elements unchanged
32- **Positive descriptions only** — Describe what should be present; rephrase any exclusion as an inclusion
33- **Specific over vague** — "golden hour sunlight at 15° angle" beats "nice lighting"
34- **Natural flow** — Weave elements into a single flowing description, not a bullet list
35
36## Output Format
37
38Return the enhanced prompt as a single flowing paragraph. When the user provides multiple requests, return each as a separate enhanced prompt under a labeled heading.
39
40## Enhancement Patterns
41
42### Hyper-Specific Details
43
44Add concrete visual details for any Subject/Context/Style element not specified by the user:
45
46- Lighting → direction, quality, color temperature, shadow behavior
47- Textures → surface materials, weathering, reflectivity
48- Atmosphere → particulates, humidity, depth haze
49- Scale → relative sizes, distances, proportions
50
51### Camera Control Terminology
52
53When a photographic look is appropriate:
54
55- Lens type: "shot with 85mm portrait lens", "wide-angle 24mm"
56- Aperture: "shallow depth of field at f/1.8", "deep focus at f/11"
57- Angle: "low angle emphasizing height", "bird's eye view"
58- Motion: "motion blur on the paws", "frozen mid-action"
59
60### Atmospheric Enhancement
61
62Convey mood through environmental details:
63
64- Emotional tone with visual indicators: "serene (soft diffused light, muted palette)", "ominous (low contrast, heavy shadows, desaturated)", "jubilant (high saturation, warm tones, dynamic motion)"
65- Weather/air: "morning mist", "dust particles in a sunbeam"
66
67### Text in Images
68
69When the image should contain readable text (signs, labels, titles, typography):
70
71- Specify the exact text content in quotes: `"OPEN 24 HOURS" in bold sans-serif`
72- Describe visual treatment: font style, weight, size relative to the scene
73- Define placement and integration: "centered on the storefront awning", "hand-lettered on the chalkboard"
74
75## Feature Patterns
76
77### Character Consistency
78
79When the same character must be recognizable across multiple images:
80
81- Include **at least 3 recognizable visual markers** (distinctive scar, signature clothing, unique hairstyle, characteristic accessory)
82- Use anchoring words: "distinctive", "signature", "always wears", "always has"
83- Be specific: "round tortoiseshell glasses" not just "glasses"
84
85### Compositional Integration
86
87When combining multiple visual elements in one scene:
88
89- Define spatial relationships with proportions: "foreground (40% of frame)", "midground", "background"
90- Define how elements interact spatially and visually: overlap, reflection, shared lighting, color echo between foreground and background
91- Specify relative scale and interaction between elements
92
93### Real-World Accuracy
94
95When depicting real places, cultures, or historical elements:
96
97- Use specific terminology: "traditional Edo-period architecture", "authentic Moroccan zellige tilework"
98- Include culturally accurate details
99- Reference geographical or historical specifics
100
101### Purpose-Driven Enhancement
102
103Tailor the prompt to the intended use:
104
105| Purpose | Emphasis |
106|---------|----------|
107| Product photo | Clean background, studio lighting, commercial appeal |
108| UI mockup | Flat design elements, consistent spacing, screen-appropriate |
109| Presentation slide | Bold composition, clear focal point, text-friendly layout |
110| Social media | Eye-catching, vibrant, crop-friendly aspect ratio |
111| Book/album cover | Typography space, dramatic mood, symbolic elements |
112
113## Image Editing
114
115When modifying an existing image:
116
117- **Preserve** the original's core characteristics: color palette, lighting style, composition
118- Use anchoring phrases: "maintain the existing...", "preserve the original...", "keep the same..."
119- Be specific about what to change vs what to keep unchanged
120- Describe modifications relative to the existing image, not from scratch
121
122## Ambiguous Cases
123
124- When user intent is unclear between photographic and illustrative style, ask before enhancing
125- When enhancement would significantly change the user's concept, present the original interpretation alongside the enhanced version
126- When cultural or historical accuracy cannot be verified, flag the uncertainty rather than guessing
127
128## Scope
129
130This skill covers static image prompt enhancement only. It does not cover video generation, 3D rendering, or image analysis/description.
131
132## Example
133
134**Input:** "A happy dog in a park"
135
136**Enhanced:** "Golden retriever mid-leap catching a red frisbee, ears flying, tongue out in joy, in a sunlit urban park. Soft morning light filtering through oak trees creates dappled shadows on emerald grass. Background shows families on picnic blankets, slightly out of focus. Shot from low angle emphasizing the dog's athletic movement, with motion blur on the paws suggesting speed."
137
shinpr