PromptFill addresses the complexity of crafting detailed prompts for AI art generators like Nano Banana and GPT. It offers a structured, visual "fill-in-the-blanks" interface, enabling users to efficiently build, manage, and iterate on intricate prompts. This tool is designed for AI art enthusiasts and professionals seeking a more organized and intuitive prompt engineering workflow.

How It Works

This web application utilizes React and Vite for a dynamic user experience. Its core is a visual editor where users drag and drop predefined variables from categorized, color-coded libraries into prompt templates. In preview mode, these variables transform into interactive dropdowns, allowing for quick selection. The system supports bidirectional synchronization between the library and template editing, custom category management, and independent value selection for multiple instances of the same variable within a template. All user data, including templates, libraries, and custom images, is automatically persisted locally via LocalStorage.

Quick Start & Requirements

• Primary Install/Run: Clone the repository, install dependencies using npm install, and run the development server with npm run dev. A start.command (macOS) or start.bat (Windows) script is also provided for direct execution.
• Prerequisites: Node.js (v18+ recommended).
• Links: Project repository: https://github.com/TanShilongMario/PromptFill

Highlighted Details

• Smart Library Management: Features categorized, color-coded libraries with bidirectional sync, allowing new options added during preview to automatically update the library.
• Multi-Template System: Supports creating and managing multiple independent prompt templates, with a clone function for A/B testing variations.
• Visual Interaction: Offers a WYSIWYG editor with drag-and-drop variable insertion, variables highlighted by category color, and dropdown selection in preview mode.
• Auto-Persistence: Utilizes LocalStorage to automatically save all templates, libraries, and configurations, preventing data loss on browser refresh or closure.
• Image Management: Allows associating custom preview images with templates, with options for uploading, viewing, and resetting images.
• Export Options: Provides one-click copying of the final prompt text and the ability to export the filled template as a high-resolution PNG image.

Maintenance & Community

The project is primarily maintained by TanShilongMario, with contributions noted from "角落工作室". Development activity is indicated by recent updates (v0.3.1 in December 2025). Community interaction is facilitated through GitHub Issues for bug reports and suggestions.

Licensing & Compatibility

The project is released under the MIT License. This permissive license allows for commercial use and integration into closed-source projects without significant restrictions.

Limitations & Caveats

Data persistence relies exclusively on browser LocalStorage, meaning data is tied to a specific browser profile and can be lost if local storage is cleared. Users are advised to regularly export their data. The application requires a Node.js environment for setup and development.