Prompt Builder
Build production-quality AI prompts using patterns extracted from 2,500+ curated prompts.
Build Workflow
Step 1: Determine Intent
Ask the user (if not already clear):
- Output type: Image, Video, or Text?
- Target model: Which AI model? (Midjourney, Flux, DALL-E, Leonardo, Sora, etc.)
- Subject: What should the prompt create?
- Style/mood: Any specific aesthetic?
Step 2: Find Reference Prompts
Search the database for similar prompts to use as inspiration:
python3 {PROMPT_ENGINE_DIR}/scripts/search_prompts.py "SUBJECT" --model MODEL --limit 5
Step 3: Construct the Prompt
Use this universal structure (adapt per model):
Image Prompts:
[Subject/Action] + [Setting/Environment] + [Lighting/Mood] + [Camera/Lens] +
[Style Reference] + [Technical Parameters]
Video Prompts:
[Camera Movement] + [Subject/Action] + [Setting] + [Lighting] +
[Duration/Speed] + [Style] + [Technical]
Text Prompts:
[Role/Context] + [Task] + [Constraints] + [Format] + [Tone] + [Examples]
Step 4: Apply Model-Specific Syntax
Load {PROMPT_ENGINE_DIR}/references/model-guide.md for model-specific formatting rules:
- Midjourney: Use
--ar,--v,--style,--s,--chaos - Flux: Natural language, detailed descriptions work best
- DALL-E: Direct, descriptive, avoid negative prompts
- Leonardo AI: Use model-specific keywords (Phoenix, Alchemy)
- Sora: Camera movements, scene transitions, temporal descriptions
Step 5: Review and Refine
Present the prompt with:
- The full prompt text
- Recommended parameters/settings
- Similar prompts from the database for comparison
- Suggested variations (3 alternatives)
Quality Gates
- Prompt must be > 30 characters
- Must include subject + at least one modifier (style, lighting, or camera)
- Must use model-appropriate syntax
- No conflicting instructions (e.g., "realistic" + "cartoon")
Converted and distributed by TomeVault — claim your Tome and manage your conversions.