ComfyUI Extension: ComfyUI_PromptManager
A powerful ComfyUI custom node that extends the standard text encoder with persistent prompt storage, advanced search capabilities, and an automatic image gallery system using SQLite.
Custom Nodes (0)
README
ComfyUI Prompt Manager
A comprehensive ComfyUI custom node that extends the standard text encoder with persistent prompt storage, advanced search capabilities, automatic image gallery system, and powerful ComfyUI workflow metadata analysis using SQLite.
Overview
ComfyUI Prompt Manager provides two powerful node types for comprehensive prompt management:
PromptManager (CLIP Encoding Node)
A drop-in replacement for ComfyUI's standard CLIPTextEncode
node with database features:
- š Drop-in Replacement: Works exactly like the standard text encoder
- š¤ CLIP Encoding: Outputs CONDITIONING for use with samplers and other CLIP-dependent nodes
PromptManagerText (Text-Only Node)
A text-focused variant that outputs raw STRING for maximum flexibility:
- š Pure Text Output: Outputs STRING type for use with any text-accepting node
- š Text Concatenation: Built-in prepend/append functionality for dynamic text assembly
- ā” Lightweight Processing: No CLIP encoding overhead for text-only workflows
Shared Features
Both nodes include the complete PromptManager feature set:
- š¾ Persistent Storage: Automatically saves all prompts to a local SQLite database
- š Advanced Search: Query past prompts with text search, category filtering, and metadata
- š¼ļø Automatic Image Gallery: Automatically links generated images to their prompts
- š·ļø Rich Metadata: Add categories, tags, ratings, notes, and workflow names to prompts
- š« Duplicate Prevention: Uses SHA256 hashing to detect and prevent duplicate storage
- š Advanced Web Interface: Comprehensive admin dashboard with metadata analysis
- š Analytics: Track prompt usage patterns and effectiveness over time
- š¬ Workflow Analysis: Extract and analyze ComfyUI workflow data from PNG images
- š Metadata Viewer: Standalone tool for analyzing ComfyUI-generated images
- š ļø System Management: Built-in diagnostics, backup/restore, and maintenance tools
Features
Core Functionality
PromptManager (CLIP Encoding)
- Text Encoding: Standard CLIP text encoding for ComfyUI workflows
- Conditioning Output: Produces CONDITIONING for samplers and generation nodes
- Full Compatibility: Drop-in replacement for CLIPTextEncode nodes
PromptManagerText (Text-Only)
- String Output: Produces STRING for use with any text-accepting node
- Text Concatenation: Prepend and append fields for dynamic text assembly
- Lightweight: No CLIP encoding overhead for pure text workflows
- Flexible Integration: Works with custom nodes, text processors, and other STRING inputs
Shared Features
- Auto-Save: Every prompt is automatically saved to the database
- Metadata Support: Optional categories, tags, ratings (1-5), notes, and workflow names
- Hash-based Deduplication: Prevents storing identical prompts multiple times
š¼ļø Advanced Gallery with Full Media Support
The comprehensive gallery system provides complete management of all ComfyUI output with professional viewing capabilities:
š Output-Wide Gallery Mode
- Complete Output Monitoring: Automatically scans and displays ALL content from your ComfyUI output directory
- Multi-Format Support: Handles images (.png, .jpg, .jpeg, .webp, .gif) and videos (.mp4, .webm, .avi, .mov, .mkv, .m4v, .wmv)
- Intelligent Organization: View all generated content regardless of which workflow created it
- Advanced Filtering: Filter by media type, date range, file size, and generation parameters
- Performance Optimized: Efficient scanning with thumbnail generation and lazy loading
š¬ Full Video Support
- Native Video Playback: HTML5 video player with custom controls for all supported formats
- Video Thumbnails: Automatic thumbnail generation with OpenCV, ffmpeg, or placeholder fallback
- Playback Controls: Autoplay, mute, loop settings with persistent preferences
- Video Navigation: Seamless navigation between videos with keyboard shortcuts
- Video Metadata: Display duration, resolution, aspect ratio, and file information
- Mixed Media Gallery: Videos and images integrated seamlessly in the same interface
š Professional Image Viewer (ViewerJS Integration)
- Full-Featured Viewing: Zoom, rotation, slideshow modes with professional controls
- Advanced Navigation: Smooth transitions, thumbnail strip, and keyboard shortcuts
- Zoom Controls: Mouse wheel zoom, drag to pan, and touch gesture support
- Toolbar Features: Comprehensive toolbar with zoom, rotate, flip, reset, and fullscreen
- Dark Theme Integration: Seamless styling that matches the admin interface
š¬ Advanced Metadata Analysis
- Real-time PNG Parsing: Extract ComfyUI workflow data from any generated image
- Integrated Metadata Panel: Live workflow analysis with copy functionality
- Generation Parameters: CFG scale, steps, sampler, seed, and model information
- One-click Copying: Copy prompts, parameters, and workflow data directly
- File Path Integration: Direct access to files in your output directory
- Cross-Platform Support: Works on desktop, tablet, and mobile devices
ā” Performance Features
- Smart Thumbnail System: Generates optimized thumbnails for faster loading
- Lazy Loading: Load content as needed for smooth browsing of large galleries
- Grid & List Views: Choose between compact grid or detailed list display
- Pagination: Efficient browsing of thousands of generated files
- Search & Filter: Real-time search across filenames and metadata
Powered by ViewerJS for professional image viewing capabilities.
š¬ ComfyUI Workflow Analysis
- PNG Metadata Parsing: Advanced PNG chunk analysis to extract embedded ComfyUI data
- Workflow Data Extraction: Complete ComfyUI workflow JSON recovery from images
- Prompt Recovery: Extract positive/negative prompts from any ComfyUI-generated image
- Generation Parameters: Recover steps, CFG scale, sampler, seed, and model information
- Multi-Node Support: Handles PromptManager, CLIPTextEncode, and other node types
- Copy & Export: One-click copying of prompts and workflow JSON download
- Standalone Viewer: Dedicated metadata analysis tool at
/prompt_manager/metadata.html
- Drag & Drop Interface: Easy analysis by dropping PNG files directly into the viewer
- Error Handling: Robust parsing with NaN value cleaning and malformed JSON recovery
š Standalone Metadata Viewer
- Independent Tool: Access at
http://localhost:8188/prompt_manager/metadata.html
- Real-time Analysis: Instant PNG metadata extraction and display
- Comprehensive Display: Shows all discoverable ComfyUI workflow information
- Export Capabilities: Download workflow JSON files for reuse
- File Path Integration: Click to reveal file locations in your system
- Visual Interface: Clean, organized presentation of complex workflow data
Search & Retrieval
- Full-text search across all stored prompts
- Category filtering for organized prompt collections
- Tag-based search with support for multiple tags
- Rating filters to find your best prompts
- Date range filtering for temporal searches
- Recent prompts quick access
- Top-rated prompts for quality discovery
- Image search by file properties and metadata
š Advanced Web Interface
- Admin Dashboard: Comprehensive browser-based management interface with modern dark theme
- Responsive Design: Works on desktop, tablet, and mobile devices
- Real-time Search: Instant search results as you type
- Bulk Operations: Edit multiple prompts simultaneously with batch tools
- Settings Panel: Configure behavior and display options
- System Management: Complete toolset for database operations:
- š Metadata Viewer: Launch standalone PNG analysis tool
- šø Scan Images: Bulk scan output directories for ComfyUI images
- š¾ Backup/Restore: Database backup and recovery operations
- š§ Maintenance: Database optimization and cleanup tools including orphaned prompt removal
- š Logs: Comprehensive logging system with download capability
- š Diagnostics: System health checks and troubleshooting
- Export Tools: Download prompts and metadata in various formats
- Progress Tracking: Real-time progress indicators for long operations
- Error Handling: Graceful error display with recovery suggestions
Database Management
- SQLite backend for reliable local storage
- Automatic schema creation and management
- Database optimization with proper indexing and maintenance tools
- Export functionality to JSON or CSV formats
- Backup and restore capabilities
- Relationship tracking between prompts and generated images
- Orphaned prompt cleanup to remove prompts without linked images
Installation
For ComfyUI Users
-
Clone the repository into your ComfyUI custom_nodes directory:
cd ComfyUI/custom_nodes/ git clone https://github.com/ComfyAssets/ComfyUI_PromptManager cd ComfyUI_PromptManager
-
Install dependencies:
pip install -r requirements.txt
-
Restart ComfyUI to load the new node
-
Add the nodes to your workflow:
- PromptManager: Look for "Prompt Manager" in the conditioning category - use exactly like "CLIP Text Encode"
- PromptManagerText: Look for "Prompt Manager Text" in the PromptManager/Text category - outputs STRING for any text node
-
Access the web interface:
- Admin Dashboard:
http://localhost:8188/prompt_manager/admin
- Full management interface - Metadata Viewer:
http://localhost:8188/prompt_manager/metadata.html
- Standalone PNG analysis tool - Simple Interface:
http://localhost:8188/prompt_manager/
- Basic prompt browser
- Admin Dashboard:
Prerequisites
- ComfyUI installation
- Python 3.8 or higher
- SQLite3 (included with Python)
watchdog
library for automatic image monitoring
Usage
Basic Usage
Using PromptManager (CLIP Encoding)
Replace any CLIPTextEncode
node with PromptManager
:
- Add the PromptManager node to your workflow
- Connect CLIP model (same as standard text encoder)
- Enter your prompt in the text field
- Connect the CONDITIONING output to your sampler node
Using PromptManagerText (Text-Only)
For text-only workflows or when you need STRING output:
- Add the PromptManagerText node to your workflow
- Enter your prompt in the text field
- Optionally use prepend/append for dynamic text assembly:
- Prepend Text: Text added before your main prompt
- Append Text: Text added after your main prompt
- Connect the STRING output to any node that accepts text input
Shared Metadata Options
Both nodes support the same metadata fields:
- Category: "portraits", "landscapes", "abstract", etc.
- Tags: "detailed, anime, masterpiece" (comma-separated)
- Rating: 1-5 stars for prompt quality (web interface only)
- Notes: Any additional information (web interface only)
- Workflow Name: Name of your workflow for organization (web interface only)
Both nodes will automatically save prompts to the database and link any generated images to the prompt.
š¼ļø Using the Output-Wide Gallery
The comprehensive gallery system provides complete access to all your ComfyUI output:
š Accessing the Gallery
- Open the admin interface at
http://localhost:8188/prompt_manager/admin
- Click the "š¼ļø Gallery" button to open the output-wide gallery
- Browse all content from your ComfyUI output directory
š¬ Video & Image Support
- Mixed Media Viewing: Images and videos appear together in the same gallery
- Video Thumbnails: Videos show with play button overlays and š¬ icons
- Smart Filtering: Filter by media type (All, Images, Videos) using the dropdown
āļø Gallery Settings
Configure your viewing experience in the settings panel:
- Performance Settings: Grid columns, image quality, lazy loading
- Video Settings: Autoplay, mute by default, loop videos
- Thumbnail Management: Generate optimized thumbnails for faster loading
š¼ļø Image Viewing Experience
- Click any image to open the professional viewer with:
- Full-screen viewing with zoom, rotation, and slideshow controls
- Integrated metadata panel showing workflow data and generation parameters
- Navigation arrows and keyboard shortcuts (ā/ā arrow keys)
- Copy functionality for prompts, parameters, and workflow data
- Use keyboard shortcuts:
- Arrow keys (ā/ā) for navigation
- ESC to close viewer
- Space for slideshow mode
š¬ Video Viewing Experience
- Click any video to open the video player with:
- HTML5 video controls with play, pause, seek, and fullscreen
- Custom control buttons for mute/unmute and loop toggle
- Video information panel showing duration, resolution, and file details
- Navigation between videos using arrow keys or buttons
- Playback settings are remembered across sessions
š Advanced Features
- Real-time Search: Search across filenames and metadata
- View Modes: Switch between grid and list views
- Sorting Options: Sort by date, size, or filename
- Pagination: Efficiently browse thousands of files
- Thumbnail Generation: Create optimized thumbnails for better performance
š¬ Analyzing ComfyUI Images
Use the standalone metadata viewer to analyze any ComfyUI-generated PNG:
- Open the metadata viewer at
http://localhost:8188/prompt_manager/metadata.html
- Drag and drop any PNG file with ComfyUI workflow data
- View extracted information:
- Prompts: Copy positive/negative prompts with one click
- Parameters: See all generation settings used
- Model Info: Identify checkpoint and settings
- Workflow: Download complete workflow JSON
- Copy data using the built-in copy buttons
- Export workflow as JSON file for reuse in ComfyUI
šø Bulk Image Scanning
Import existing ComfyUI images into your database:
- Open admin dashboard and click "šø Scan Images"
- Start scan to analyze your entire output directory
- Monitor progress with real-time status updates
- Review results showing:
- Images found and processed
- Prompts extracted and linked
- Any errors or issues encountered
- Access imported data through the normal gallery interface
š Web Interface Features
The comprehensive web interface provides:
- Search Bar: Real-time search across all prompts
- Filter Options: Filter by category, tags, rating, and date
- Bulk Operations: Select multiple prompts for batch editing
- Export Tools: Download your prompt collection
- Settings Panel: Configure auto-save and display options
- Diagnostics: System health checks and troubleshooting
š§ Database Maintenance
Keep your database optimized with built-in maintenance tools:
- Open the admin dashboard and click "š§ Maintenance"
- Select maintenance operations:
- Remove Duplicates: Find and merge duplicate prompts while preserving images
- Vacuum Database: Optimize database file size and performance
- Clean Orphaned Images: Remove image records for missing files
- š® Prune Orphaned Prompts: Remove prompts that have no linked images
- Check Consistency: Verify database integrity and relationships
- Database Statistics: Generate detailed database reports
- Run selected operations and monitor progress in real-time
- Review results showing detailed information about each operation
Database Location
By default, the database is saved as example_prompts.db
in the node directory. This file contains all your prompts and linked images and can be backed up or shared.
Searching Prompts
Use the web interface for intuitive searching, or access the database directly:
from database.operations import PromptDatabase
db = PromptDatabase()
# Search for landscape prompts
results = db.search_prompts(text="landscape", limit=10)
# Find highly rated prompts
results = db.search_prompts(rating_min=4)
# Search by category and tags
results = db.search_prompts(
category="portraits",
tags=["anime", "detailed"]
)
# Get recent prompts
recent = db.get_recent_prompts(limit=20)
# Get images for a prompt
images = db.get_prompt_images(prompt_id="123")
Examples
PromptManager (CLIP Encoding) Examples
Example 1: Basic Prompt Storage
Input: "A beautiful sunset over a mountain lake"
Category: "landscapes"
Tags: "nature, sunset, mountains, water"
ā Outputs: CONDITIONING for sampler nodes
Example 2: Character Prompt
Input: "Portrait of a cyberpunk hacker with neon implants"
Category: "characters"
Tags: "cyberpunk, portrait, sci-fi, neon"
ā Outputs: CONDITIONING for sampler nodes
PromptManagerText (Text-Only) Examples
Example 3: Dynamic Text Assembly
Main Text: "beautiful landscape"
Prepend Text: "masterpiece, ultra detailed,"
Append Text: ", 8k resolution, trending on artstation"
ā Final Output: "masterpiece, ultra detailed, beautiful landscape, 8k resolution, trending on artstation"
Example 4: Text Processing Pipeline
Input: "A serene mountain lake at sunset"
Category: "landscapes"
Tags: "nature, peaceful, golden hour"
ā Outputs: STRING for use with text processors, style nodes, or other custom nodes
Example 5: Multi-Node Text Workflow
PromptManagerText ā Text Processor ā Style Applicator ā Final Text Node
"cyberpunk city" ā style processing ā "neon-lit cyberpunk metropolis at night"
Traditional Examples
Example 6: Abstract Art
Input: "Swirling colors in an abstract geometric pattern"
Category: "abstract"
Tags: "geometric, colorful, pattern, modern"
Rating: 3 (set via web interface)
Notes: "Good for experimental art" (set via web interface)
Database Schema
-- Prompts table
CREATE TABLE prompts (
id INTEGER PRIMARY KEY AUTOINCREMENT,
text TEXT NOT NULL,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
workflow_name TEXT,
category TEXT,
tags TEXT, -- JSON array of tags
rating INTEGER CHECK(rating >= 1 AND rating <= 5),
notes TEXT,
hash TEXT UNIQUE -- SHA256 hash for deduplication
);
-- Generated images table
CREATE TABLE generated_images (
id INTEGER PRIMARY KEY AUTOINCREMENT,
prompt_id TEXT NOT NULL,
image_path TEXT NOT NULL,
filename TEXT NOT NULL,
generation_time TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
file_size INTEGER,
width INTEGER,
height INTEGER,
format TEXT,
workflow_data TEXT, -- JSON workflow metadata
prompt_metadata TEXT, -- JSON prompt parameters
parameters TEXT, -- JSON generation parameters
FOREIGN KEY (prompt_id) REFERENCES prompts(id)
);
Architecture
Core Components
prompt_manager.py
- Main ComfyUI node implementation (CLIP encoding)prompt_manager_text.py
- Text-only node implementation (STRING output)database/models.py
- Database schema and connection managementdatabase/operations.py
- CRUD operations and search functionalitypy/api.py
- Web API endpoints for the interfacepy/config.py
- Configuration managementutils/hashing.py
- SHA256 hashing for deduplicationutils/validators.py
- Input validation and sanitizationutils/image_monitor.py
- Automatic image detection systemutils/prompt_tracker.py
- Prompt execution trackingutils/metadata_extractor.py
- PNG metadata analysis engineutils/logging_config.py
- Comprehensive logging systemutils/diagnostics.py
- System diagnostics and health checksweb/admin.html
- Advanced admin dashboard with metadata panelweb/index.html
- Simple web interfaceweb/prompt_manager.js
- JavaScript functionalityweb/metadata.html
- Standalone PNG metadata viewer
File Structure
ComfyUI_PromptManager/
āāā __init__.py # Node registration
āāā prompt_manager.py # Main node implementation (CLIP encoding)
āāā prompt_manager_text.py # Text-only node implementation (STRING output)
āāā database/
ā āāā __init__.py
ā āāā models.py # Database schema
ā āāā operations.py # Database operations
āāā py/
ā āāā __init__.py
ā āāā api.py # Web API endpoints
ā āāā config.py # Configuration
āāā utils/
ā āāā __init__.py
ā āāā hashing.py # Hashing utilities
ā āāā validators.py # Input validation
ā āāā image_monitor.py # Automatic image detection
ā āāā prompt_tracker.py # Prompt execution tracking
ā āāā metadata_extractor.py # PNG metadata analysis
ā āāā logging_config.py # Logging system
ā āāā diagnostics.py # System diagnostics
āāā web/
ā āāā admin.html # Advanced admin dashboard
ā āāā index.html # Simple web interface
ā āāā metadata.html # Standalone metadata viewer
ā āāā prompt_manager.js # JavaScript functionality
āāā tests/
ā āāā __init__.py
ā āāā test_basic.py # Test suite
āāā requirements.txt # Dependencies
āāā example_usage.py # Standalone examples
āāā example_prompts.db # Example database
āāā README.md # This file
Configuration
Database Settings
You can customize the database path by modifying the configuration:
# In py/config.py
DATABASE_PATH = "custom_path/prompts.db"
Gallery & Monitoring Settings
Configure the automatic image detection and gallery system:
# Gallery monitoring configuration (GalleryConfig class)
MONITORING_ENABLED = True
MONITORING_DIRECTORIES = [] # Auto-detect ComfyUI output if empty
SUPPORTED_EXTENSIONS = ['.png', '.jpg', '.jpeg', '.webp', '.gif']
PROCESSING_DELAY = 2.0 # Delay before processing new images
PROMPT_TIMEOUT = 120 # Seconds to keep prompt context active
CLEANUP_INTERVAL = 300 # Seconds between cleanup of expired prompts
# Performance settings
MAX_CONCURRENT_PROCESSING = 3
METADATA_EXTRACTION_TIMEOUT = 10 # Seconds for PNG analysis
IMAGES_PER_PAGE = 20
THUMBNAIL_SIZE = 256
Web Interface Settings
Configure the web interface behavior:
# Web UI settings (PromptManagerConfig class)
RESULT_TIMEOUT = 5 # Seconds to auto-hide results in ComfyUI node
WEBUI_DISPLAY_MODE = 'newtab' # 'popup' or 'newtab' for Web UI button
SHOW_TEST_BUTTON = False # Show API test button in node UI
Performance Tuning
- The database automatically creates indexes for optimal search performance
- Regular
VACUUM
operations keep the database optimized - Consider backing up the database periodically
Advanced Features
Export Your Prompts
from database.operations import PromptDatabase
db = PromptDatabase()
# Export to JSON
db.export_prompts("my_prompts.json", format="json")
# Export to CSV
db.export_prompts("my_prompts.csv", format="csv")
Database Statistics
info = db.model.get_database_info()
print(f"Total prompts: {info['total_prompts']}")
print(f"Average rating: {info['average_rating']}")
Backup and Restore
# Create backup
db.model.backup_database("backup_prompts.db")
# The database file can be copied directly for backup
Development
Running Tests
cd KikoTextEncode
python -m pytest tests/ -v
Code Style
The project follows PEP 8 guidelines with:
- Black formatter (88 character line limit)
- Type hints for all functions
- Comprehensive docstrings
- Proper error handling
Contributing
- Fork the repository
- Create a feature branch
- Add tests for new functionality
- Ensure all tests pass
- Submit a pull request
Troubleshooting
Common Issues
Database Permission Errors
- Ensure the ComfyUI process has write permissions to the node directory
- Check that the database file isn't locked by another process
Import Errors
- Verify ComfyUI is properly installed
- Check that all required dependencies are available
Performance Issues
- Run
VACUUM
on the database occasionally - Consider archiving old prompts if the database becomes very large
Debug Mode
For debugging, you can enable verbose logging in the node:
# Add to kiko_text_encode.py
import logging
logging.basicConfig(level=logging.DEBUG)
License
MIT License - see LICENSE file for details.
Support
- Issues: Report bugs and request features via GitHub Issues
- Documentation: See the Wiki for detailed guides
- Community: Join the discussion in ComfyUI Discord
Roadmap
Completed in v3.0.0
- ā PNG Metadata Analysis: Complete ComfyUI workflow extraction from images
- ā Standalone Metadata Viewer: Dedicated tool for analyzing any ComfyUI image
- ā Advanced Admin Dashboard: Comprehensive management interface with modern UI
- ā Integrated Metadata Panel: Real-time workflow analysis in image viewer
- ā Bulk Image Scanning: Mass import of existing ComfyUI images
- ā System Management Tools: Backup, restore, diagnostics, and maintenance
- ā Enhanced Error Handling: Robust PNG parsing with NaN value cleaning
Planned Features
- āļø Cloud Sync: Optional cloud backup and sync
- š¤ Collaboration: Share prompt collections with other users
- š§ AI Suggestions: Recommend similar prompts based on metadata analysis
- š Advanced Analytics: Detailed usage statistics and trends with workflow insights
- š Plugin System: Support for third-party extensions and custom analyzers
- šØ Enhanced Batch Processing: Advanced bulk operations with metadata editing
- š Workflow Templates: Save and reuse common workflow patterns
- š Visual Analytics: Charts and graphs for prompt effectiveness analysis
Integration Ideas
- Auto-tagging: Use AI to automatically categorize prompts
- Workflow linking: Connect prompts to specific workflow templates
- Image analysis: Analyze generated images to improve suggestions
- Version control: Track prompt iterations and effectiveness
Changelog
v3.0.9 (Output-Wide Gallery & Video Support)
- š Output-Wide Gallery Mode: Complete gallery redesign to show ALL content from ComfyUI output directory
- š¬ Full Video Support: Native video playback with HTML5 player for .mp4, .webm, .avi, .mov, .mkv, .m4v, .wmv formats
- š¼ļø Video Thumbnail Generation: Automatic video thumbnails using OpenCV, ffmpeg, or placeholder fallback
- āļø Video Settings Panel: Configurable autoplay, mute, and loop settings with persistent preferences
- š® Video Navigation: Seamless navigation between videos with keyboard shortcuts and custom controls
- š Video Metadata Display: Show duration, resolution, aspect ratio, and detailed file information
- š Mixed Media Integration: Videos and images seamlessly integrated in the same gallery interface
- ā” Enhanced Performance: Optimized thumbnail generation for both images and videos
- šļø Advanced Gallery Settings: Comprehensive settings panel with video controls and performance options
- š±ļø Improved Click Handling: Fixed thumbnail failures to preserve click functionality
- š± Mobile Compatibility: Enhanced responsive design for video playback on all devices
v3.0.5 (Text-Only Node Release)
- š PromptManagerText Node: New text-only variant that outputs STRING instead of CONDITIONING
- š Text Concatenation: Built-in prepend/append functionality for dynamic text assembly
- ā” Lightweight Processing: No CLIP encoding overhead for pure text workflows
- š Dual Node Architecture: Choose between CLIP encoding (PromptManager) or text-only (PromptManagerText)
- š·ļø Shared Metadata System: Both nodes use the same database and metadata features
- š¼ļø Unified Gallery: Images from both node types appear in the same gallery system
- š Enhanced Tracking: Improved prompt tracking with prepend/append context preservation
- š Enhanced Tracking: Improved prompt tracking with prepend/append context preservation
v3.0.3 (ViewerJS Integration & Enhanced Gallery)
- š¼ļø Professional Image Viewer: Complete gallery redesign with ViewerJS integration
- ā” Advanced Image Navigation: Zoom, rotation, slideshow, and professional viewing controls
- šØ Dark Theme Integration: Seamless ViewerJS styling that matches the admin interface
- š¬ Enhanced Metadata Parsing: Improved ComfyUI workflow parameter extraction with targeted parsing
- š Real-time Parameter Display: Live CFG, steps, sampler, and seed extraction from workflow nodes
- š Integrated Copy Functionality: One-click copying of prompts and generation parameters
- š ļø Robust Value Detection: Smart parsing that targets specific node types and validates parameters
- āØļø Keyboard Navigation: Full keyboard support for gallery navigation and viewer controls
- š± Responsive Design: Enhanced mobile and tablet compatibility
v3.0.0 (Metadata Analysis Release)
- š¬ PNG Metadata Analysis: Advanced ComfyUI workflow extraction from PNG images
- š Standalone Metadata Viewer: Dedicated tool at
/web/metadata.html
for analyzing any ComfyUI image - š¼ļø Integrated Metadata Panel: Real-time workflow analysis in the image viewer
- šø Bulk Image Scanning: Mass import and analysis of existing ComfyUI output directories
- š ļø System Management Suite: Complete backup, restore, maintenance, and diagnostic tools
- š® Orphaned Prompt Cleanup: Remove prompts that have no linked images for database optimization
- š Advanced Logging: Comprehensive logging system with web-based log viewer
- šØ Enhanced Admin Dashboard: Modern dark theme with improved UX and management tools
- š§ Robust Error Handling: Advanced PNG parsing with NaN value cleaning and error recovery
- š File Path Integration: Direct file path display and system integration
- ā” Performance Optimizations: Improved metadata extraction and database operations
v2.0.0 (Gallery Release)
- š¼ļø Automatic Image Gallery: Complete image tracking and gallery system
- š Advanced Web Interface: Comprehensive admin dashboard with responsive design
- š± Image Viewer: Full-screen modal with navigation and keyboard shortcuts
- š Enhanced Search: Real-time search with advanced filtering options
- ā” Performance Improvements: Optimized database operations
- š ļø Basic Diagnostics: Initial system diagnostics and health monitoring
- š Bulk Operations: Multi-select prompt editing and management
v1.0.0 (Initial Release)
- Core text encoding with database storage
- Search and filtering functionality
- Metadata support (categories, tags, ratings, notes)
- Hash-based deduplication
- SQLite backend with optimized schema
- Basic web interface
- Export functionality