Node Banana provides a visual, node-based interface for building and executing AI-powered image and text generation pipelines. It targets users who need to construct complex workflows without extensive coding, offering a drag-and-drop canvas to connect various generation and annotation nodes. The primary benefit is simplifying the creation of sophisticated AI content generation processes through an intuitive graphical environment.

How It Works

The application leverages a Next.js 16 (App Router) framework with TypeScript, utilizing @xyflow/react for its visual node editor and Konva.js for canvas rendering. Users construct workflows by connecting nodes representing different operations, such as AI image generation (via Google Gemini or OpenAI APIs), text generation, and image annotation tools. Workflows can be saved and loaded as JSON files, enabling pipeline reuse and modification. This approach allows for modular pipeline construction and visual debugging of complex AI tasks.

Quick Start & Requirements

• Primary install/run command: npm install, then npm run dev for development. Production build uses npm run build followed by npm run start.
• Prerequisites: Node.js 18+ is required. An API key for Google Gemini (GEMINI_API_KEY) must be configured in a .env.local file. An OpenAI API key (OPENAI_API_KEY) is optional.
• Links: Local development runs at http://localhost:3000. Example workflows are available in the /examples directory.

Highlighted Details

• Visual Node Editor: Features a drag-and-drop interface on an infinite canvas with pan and zoom capabilities.
• AI Integration: Supports image and text generation using Google Gemini and OpenAI APIs.
• Workflow Chaining: Enables the creation of complex pipelines by connecting multiple nodes.
• Image Annotation: Includes a full-screen editor with drawing tools (rectangles, circles, arrows, freehand, text).
• Save/Load Workflows: Allows exporting and importing pipelines as JSON files.

Maintenance & Community

No specific details regarding maintainers, community channels (like Discord/Slack), or a public roadmap were provided in the README snippet.

Licensing & Compatibility

The project is released under the MIT license, which permits commercial use and modification.

Limitations & Caveats

The project is noted to be in early development and has not been extensively tested, potentially containing issues. Users are specifically advised to use the Chrome browser, suggesting potential compatibility problems with other browsers.