diff --git a/README.md b/README.md
index 2ee3cd26..c6c6c008 100644
--- a/README.md
+++ b/README.md
@@ -1,41 +1,59 @@
-# Node Banana
+
-> **Important note:** This is in early development, it probably has some issues. Use Chrome. For support or raising any issues join the [discord](https://discord.com/invite/89Nr6EKkTf). See the [docs](https://node-banana-docs.vercel.app/) for help, installation guides, and user guides.
+

-Node Banana is node-based workflow application for generating images with Nano Banana Pro. Build image generation pipelines by connecting nodes on a visual canvas. Recent Fal and Replicate integration allows for complex image and video pipelines from any provider, but be aware this is still in testing.
+### The Visual Workflow Editor for AI Image Generation
-Built mainly with Opus 4.5.
+[](https://github.com/williavs/node-banana/stargazers)
+[](LICENSE)
+[](https://discord.com/invite/89Nr6EKkTf)
-
+
-## Features
+Build AI image and video generation pipelines by connecting nodes on a visual canvas.
+Multi-provider support. Prompt-to-workflow generation. Built mainly with Claude.
-- **Prompt to Workflow** - Generate complete workflows from natural language descriptions or choose from preset templates (Gemini only for now)
-- **Visual Node Editor** - Drag-and-drop nodes onto an infinite canvas with pan and zoom
-- **Image Annotation** - Full-screen editor with drawing tools (rectangles, circles, arrows, freehand, text)
-- **AI Image Generation** - Generate images using Google Gemini models
-- **Text Generation** - Generate text using Google Gemini or OpenAI models
-- **Workflow Chaining** - Connect multiple nodes to create complex pipelines
-- **Save/Load Workflows** - Export and import workflows as JSON files
-- **Group Locking** - Lock node groups to skip them during execution
+
-## Multi-Provider Support (Beta)
+[**Documentation**](https://node-banana-docs.vercel.app/) • [Discord](https://discord.com/invite/89Nr6EKkTf)
-In addition to Google Gemini, Node Banana now supports:
-- **Replicate** - Access thousands of open-source models
-- **fal.ai** - Fast inference for image and video generation
+
-Configure API keys in Project Settings to enable these providers.
+
-## Tech Stack
+## Build Complex AI Pipelines Visually
+
+Node Banana is a node-based workflow editor for AI image generation. Drag nodes onto an infinite canvas, connect them with typed handles, and execute pipelines that call AI APIs in dependency order.
+
+- **Generate workflows from natural language** or choose from preset templates
+- **Chain multiple AI models together** across providers in a single pipeline
+- **Annotate and edit images** with a full-screen drawing editor
+- **Lock node groups** to skip them during execution
+- **Save and share workflows** as portable JSON files
-- **Framework**: Next.js 16 (App Router)
-- **Language**: TypeScript
-- **Node Editor**: @xyflow/react (React Flow)
-- **Canvas**: Konva.js / react-konva
-- **State Management**: Zustand
-- **Styling**: Tailwind CSS
-- **AI**: Google Gemini API, OpenAI API, Replicate (Beta), fal.ai (Beta)
+## Features
+
+| Feature | Description |
+|:--------|:------------|
+| **Prompt to Workflow** | Generate complete workflows from natural language descriptions |
+| **Visual Node Editor** | Drag-and-drop nodes onto an infinite canvas with pan and zoom |
+| **Image Annotation** | Full-screen editor with drawing tools (rectangles, circles, arrows, freehand, text) |
+| **AI Image Generation** | Generate images using Google Gemini, Replicate, fal.ai, Kie.ai, and more |
+| **Text Generation** | Generate text using Google Gemini or OpenAI models |
+| **Workflow Chaining** | Connect multiple nodes to create complex multi-step pipelines |
+| **Group Locking** | Lock node groups to skip them during execution |
+| **Save/Load** | Export and import workflows as JSON files |
+
+## Supported Providers
+
+| Provider | Status |
+|:---------|:-------|
+| [Google Gemini](https://ai.google.dev/) | Fully supported |
+| [Replicate](https://replicate.com/) | Supported |
+| [fal.ai](https://fal.ai/) | Supported |
+| [Kie.ai](https://kie.ai/) | Supported |
+| [WaveSpeed](https://wavespeed.ai/) | Supported |
+| [OpenAI](https://openai.com/) | LLM only |
## Getting Started
@@ -44,6 +62,17 @@ Configure API keys in Project Settings to enable these providers.
- Node.js 18+
- npm
+### Quick Start
+
+```bash
+git clone https://github.com/williavs/node-banana.git
+cd node-banana
+npm install
+npm run dev
+```
+
+Open [http://localhost:3000](http://localhost:3000) in your browser.
+
### Environment Variables
Create a `.env.local` file in the root directory:
@@ -51,23 +80,10 @@ Create a `.env.local` file in the root directory:
```env
GEMINI_API_KEY=your_gemini_api_key
OPENAI_API_KEY=your_openai_api_key # Optional, for OpenAI LLM provider
-REPLICATE_API_KEY=your_replicate_api_key # Optional, beta
-FAL_API_KEY=your_fal_api_key # Optional, beta
-```
-
-### Installation
-
-```bash
-npm install
-```
-
-### Development
-
-```bash
-npm run dev
+KIE_API_KEY=your_kie_api_key # Optional, for Kie.ai models
```
-Open [http://localhost:3000](http://localhost:3000) in your browser.
+Additional provider API keys can be configured in Project Settings within the app.
### Build
@@ -78,39 +94,61 @@ npm run start
## Example Workflows
-The `/examples` directory contains some example workflow files from my personal projects. To try them:
+The `/examples` directory contains example workflow files. To try them:
1. Start the dev server with `npm run dev`
2. Drag any `.json` file from the `/examples` folder into the browser window
-3. Make sure you review each of the prompts before starting, these are fairly targetted to the examples.
+3. Review the prompts in each node before running — they're targeted to specific use cases
-## Usage
+## Node Types
-1. **Add nodes** - Click the floating action bar to add nodes to the canvas
-2. **Connect nodes** - Drag from output handles to input handles (matching types only)
-3. **Configure nodes** - Adjust settings like model, aspect ratio, or drawing tools
-4. **Run workflow** - Click the Run button to execute the pipeline
-5. **Save/Load** - Use the header menu to save or load workflows
+| Type | Purpose |
+|:-----|:--------|
+| **Image Input** | Load or upload reference images |
+| **Prompt** | Text prompt input |
+| **Generate** | AI image generation (multi-provider) |
+| **LLM** | AI text generation |
+| **Annotation** | Draw on images with full-screen editor |
+| **Split Grid** | Split image into grid cells |
+| **Audio** | AI audio/TTS generation |
+| **Output** | Display final result |
-## Connection Rules
+## Tech Stack
-- **Image** handles connect to **Image** handles only
-- **Text** handles connect to **Text** handles only
-- Image inputs on generation nodes accept multiple connections
-- Text inputs accept single connections
+