- zh-hans: 智能整理 -> AI整理
- zh-hant: 智能整理 -> AI整理
- en: Smart Organize -> AI Organize
- de: Smart Organize -> AI Organize
Co-Authored-By: Claude <noreply@anthropic.com>
- Add smart organize feature that groups similar images based on prompt semantics
- AI generates meaningful folder names in user's preferred language
- Preview before action: review proposed organization, skip or adjust as needed
- Background processing for large folders
- Support move or copy, configurable min cluster size, include subfolders option
Backend changes:
- Add organize_files.py with job management and file operations
- Add recursive parameter to embedding and clustering APIs
- Default recursive=true for Topic Search (backward compatible)
- Default recursive=false for Smart Organize (first-level only)
- Update database on file move to preserve tags
Frontend changes:
- Add SmartOrganizeConfigModal for configuration
- Add OrganizeJobsPanel for progress tracking
- Add OrganizePreview for reviewing and confirming
- Add smart organize button to address bar
- Add i18n translations for zh-hans, zh-hant, en, de
Documentation:
- Update README.md and README-zh.md with feature description
- Update change.log.md with screenshots and video demo
Co-Authored-By: Claude <noreply@anthropic.com>
- Add autoUpdateIndex setting to global settings (enabled by default)
- When disabled, show manual update prompt instead of auto-updating expired index
- Add feature tip alert shown on first use
- Localize new strings in all languages (en, zh-hans, zh-hant, de)
- Rebuild vue dist assets with updated code
- Tag.get_or_create now returns None for invalid tag names instead of creating error tags
- Add null checks before using tag.id in all callers
- Adjust tag validation: non-Chinese tags now limited to 8 words or 40 characters
- Change Tag.get_or_create to return None for invalid tag names
- Add None checks at all call sites to prevent AttributeError
- Protects against invalid Chinese names (>16 chars) and other language names (>8 words)
- Ensures system stability when encountering problematic tag data
Important performance optimization for handling large tag datasets:
- When total tags > 8192, limit 'pos' type tags to top 4096 by count
- Return all non-pos tags without limitation
- Significantly reduces memory usage and load time for large databases
- Maintains functionality while improving performance with massive tag counts
- Add tag name validation in Tag.get_or_create method
- Chinese names: max 16 characters
- Other languages: max 8 words
- Return error tags with uppercase English names when validation fails
- Ensure error tags are created through get_or_create to maintain database consistency
- Clean up database: removed 487,938 non-custom tags, keeping only 12 custom tags
- Add IIB_COMFYUI_EXTRACT_ALL_PROMPTS environment variable
- When enabled, extract all CLIPTextEncode prompts instead of following KSampler chain
- Note: All prompts will be merged into positive prompt field
- Add IIB_COMFYUI_EXTRACT_ALL_PROMPTS environment variable
- When enabled, extract all CLIPTextEncode prompts instead of following KSampler chain
- Note: All prompts will be merged into positive prompt field
- Add keyword count limit (default 600) for Tag layer to improve performance
- Implement irregular node layout with random perturbations
- Add layer spacing based on adjacent layer widths for consistent gaps
- Add cache result banner with collapse/expand functionality
- Add streaming response utility for LLM API calls
- Update i18n translations for new cache banner texts
- Optimize tag graph: increase max tags to 500, add level-2 tiered requirements
- Fix keyword deduplication and null handling in tag graph
- Add get_all_keywords_frequency method to TopicTitleCache
- Initialize keyword frequency from historical cached cluster keywords
- Prioritize top 100 high-frequency keywords when generating new keywords
- Update LLM prompt to prefer existing keywords from frequency list
- Reduce duplicate/similar keyword generation across clusters
- Add streaming support for tag_graph LLM requests
- Increase LLM timeout and retry limits for better reliability
zanllp
wuqinchuan