- Add prompt editor modal with support for editing positive/negative prompts
- Add key-value editor for custom metadata fields (string and JSON modes)
- Cache EXIF data in database for faster retrieval
- Track manually edited prompts with exif_edited flag
- Add validation for required fields and unique key constraints
- Add full internationalization support (EN, ZH-Hans, ZH-Hant, DE)
- Update changelog with new features and screenshot
- Clean up gitignore to use wildcard for video files
- Add AI-powered tag analysis feature in full-screen context menu
- Analyze prompts using AI to suggest matching custom tags
- Add loading state with spinner during analysis
- Filter out already-added tags to avoid duplicates
- Support i18n for all user-facing messages (EN/ZH-Hans/ZH-Hant/DE)
- Keep system prompts in English for consistency
- Improve authentication error handling
- Add special marker for secret verification 401 errors
- Only trigger password modal for secret verification failures
- Prevent password modal from showing on other 401 errors
- Enhance Topic Search guide
- Add two advantage points highlighting semantic similarity grouping
- Add natural language semantic search capabilities
- Support i18n for new guide content
Backend optimizations:
- Refactor get_random_images() using SQLite ORDER BY RANDOM()
- Simplify from 60+ lines to ~20 lines with better performance
- Remove complex multi-cycle index calculations
- Maintain file existence check and auto-cleanup
ComfyUI support:
- Add fallback to 'parameters' field in PNG metadata
- Improve detection for ComfyUI-generated images
Frontend improvements:
- Smart prompt display: auto-detect tag vs natural language format
- Add getTextLength() with Chinese character weight (1 char = 3 letters)
- Refactor isTagStylePrompt() with clear rules:
* Any tag length > 50 natural language format
* Average tag length > 30 natural language format
- Natural language prompts shown as paragraphs
- Tag-style prompts shown as badges
- Better support for Chinese/English mixed content
Build:
- Update frontend asset references
- Add AutoTagMatcher singleton class for automatic tag application
- Support filtering by multiple fields (prompt, model, sampler, etc.)
- Add frontend UI for managing auto-tag rules in global settings
- Support AND logic for multiple conditions within a rule
- Integrate with image indexing process
- Add natural language vs tag-style prompt detection and rendering
- Include rule descriptions and usage guidance in UI
- Auto-reload rules when updated via API