- Add forensic-level image analysis for near-accurate reproduction - Add detailed subject analysis: ethnicity, skin tones with undertones - Add facial features: eyes (gaze direction), nose, lips, eyebrows - Add comprehensive pose analysis: all body parts, hand/palm orientation - Add clothing coverage: neckline, exposure levels, materials, gaps - Add cosmetics extraction: foundation, eye makeup, lips, blush - Add structured JSON output with categorized sections - Add LLM interaction tracking for debugging (all queries/responses) - Add token-optimized prompts respecting max limits - Add prompt template system (SOLID principles) - Add multi-iteration Deep mode for local GGUF models - Create CHANGELOG.md with full version history 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
16 lines
404 B
Python
16 lines
404 B
Python
"""
|
|
Prompt Templates Module
|
|
|
|
SOLID-compliant prompt template system for different LLM providers.
|
|
Each provider can have optimized prompts for best results.
|
|
"""
|
|
|
|
from .base_prompt_template import BasePromptTemplate
|
|
from .template_factory import get_prompt_template_for_provider, PromptTemplateType
|
|
|
|
__all__ = [
|
|
"BasePromptTemplate",
|
|
"get_prompt_template_for_provider",
|
|
"PromptTemplateType",
|
|
]
|