Files
character-browser/README.md

3.3 KiB

Character Browser & Generator

A local web-based GUI for managing character profiles (JSON) and generating consistent images using ComfyUI.

Features

  • Character Gallery: Automatically scans your characters/ folder and builds a searchable, sortable database.
  • Granular Prompt Control: Every field in your character JSON (Identity, Wardrobe, Styles) has a checkbox. You decide exactly what is sent to the AI.
  • ComfyUI Integration:
    • SDXL Optimized: Designed for high-quality SDXL workflows.
    • Localized ADetailer: Automated Face and Hand detailing with focused prompts (e.g., only eye color and expression are sent to the face detailer).
    • LoRA Support: Automatically detects and applies LoRAs specified in your character sheets.
    • Real-time Progress: Live progress bars and queue status via WebSockets (with a reliable polling fallback).
  • Batch Processing:
    • Fill Missing: Generate covers for every character missing one with a single click.
    • Refresh All: Unassign all current covers and generate a fresh set for the whole collection.
  • Advanced Generator: A dedicated page to mix-and-match characters with different checkpoints (Illustrious/Noob support) and custom prompt additions.
  • Smart URLs: Sanitized, human-readable URLs (slugs) that handle special characters and slashes gracefully.

Prerequisites

  1. Python 3.10+
  2. ComfyUI running locally (default: http://127.0.0.1:8188).
  3. ComfyUI Custom Nodes:
  4. Models:
    • Ensure your Checkpoints are in the folders defined in app.py.
    • Face detection model: bbox/face_yolov9c.pt (or update comfy_workflow.json).
    • Hand detection model: bbox/hand_yolov8s.pt.

Setup & Installation

  1. Clone the repository to your local machine.
  2. Configure Paths: Open app.py and update the following variables to match your system:
    app.config['COMFYUI_URL'] = 'http://127.0.0.1:8188'
    app.config['ILLUSTRIOUS_MODELS_DIR'] = '/path/to/your/Illustrious/models'
    app.config['NOOB_MODELS_DIR'] = '/path/to/your/Noob/models'
    
  3. Launch: Simply run the launch script. It will handle the virtual environment and dependencies automatically.
    chmod +x launch.sh
    ./launch.sh
    

Usage

  • Rescan: Use the "Rescan Character Files" button if you've added new JSON files or manually edited them.
  • Save Defaults: On a character page, select your favorite prompt combination and click "Save as Default Selection" to remember it for future quick generations.

Generation

  • Preview: Generates an image and shows it to you without replacing your current cover.
  • Replace: Generates an image and sets it as the character's official gallery cover.
  • Clean Start: If you want to wipe the database and all generated images to start fresh:
    ./launch.sh --clean
    

File Structure

  • /characters: Your character JSON files.
  • /static/uploads: Generated images (organized by character subfolders).
  • /templates: HTML UI using Bootstrap 5.
  • app.py: Flask backend and prompt-building logic.
  • comfy_workflow.json: The API-format workflow used for generations.
  • models.py: SQLite database schema.