n8n-nodes-pollinations

n8n community nodes for Pollinations.AI - Generate images, text, and audio using AI models directly in your n8n workflows.

Features

• 🖼️ Image Generation - Create images from text prompts using various AI models
• 💬 Text Generation - Generate text with simple or advanced conversation modes
• 🎙️ Audio Generation - Text-to-speech and speech-to-text capabilities
• 👁️ Vision Analysis - Analyze and describe images using multimodal AI
• 🔐 Flexible Authentication - Support for API tokens or referrer-based auth

Installation

In n8n (Self-hosted)

1. Go to Settings → Community Nodes
2. Click Install a community node
3. Enter: n8n-nodes-pollinations
4. Click Install

Manual Installation

npm install n8n-nodes-pollinations

Then restart n8n.

Development Installation

# Clone the repository
git clone https://github.com/pollinations/n8n-nodes-pollinations.git
cd n8n-nodes-pollinations

# Install dependencies
npm install

# Build the package
npm run build

# Link to n8n (for local development)
npm link
cd ~/.n8n/custom
npm link n8n-nodes-pollinations

Authentication

Get Your API Token

1. Visit auth.pollinations.ai
2. Sign in with GitHub
3. Get your API token from your account settings

Configure Credentials

⚠️ Authentication Required

All Pollinations.AI nodes require authentication to ensure reliable access to models and prevent errors.

1. In n8n, add a Pollinations.AI API credential
2. Enter your API token from auth.pollinations.ai
3. Optionally add a referrer domain for web app authentication

For AI Agent Integration: Use the Pollinations.AI Chat node as a tool within AI Agent (see Chat Model Provider section below)

Get Your API Token:

1. Visit auth.pollinations.ai
2. Sign in with GitHub
3. Copy your API token from your account settings

Using Pollinations.AI with n8n AI Agent

⚠️ Important Limitation

n8n's AI Agent chat model providers (OpenAI, Anthropic, OpenRouter, etc.) are hardcoded in n8n's core and cannot be extended through community nodes. This means Pollinations.AI cannot appear directly in the AI Agent's "Chat Model" dropdown.

✅ Solution: Use Pollinations.AI Chat as a Tool

The best way to use Pollinations.AI with AI Agent is to use the Pollinations.AI Chat node as a Tool:

Step-by-Step:

1. Add a Pollinations.AI Chat node to your workflow
2. Configure it:
   • Operation: "Chat" or "Chat with System Prompt"
   • Model: Select your preferred model (openai, mistral, etc.)
   • Add your API token in credentials
3. In your AI Agent node:
   • Add the Pollinations.AI Chat node as a Tool
   • AI Agent will call Pollinations.AI when it needs to generate responses

Benefits:

• ✅ Full control over when Pollinations.AI is called
• ✅ Can use different models for different tasks
• ✅ Works seamlessly with AI Agent's tool system
• ✅ Maintains conversation context

Example Workflow:

AI Agent
  └─ Tools:
      ├─ Pollinations.AI Chat (for text generation)
      ├─ Pollinations.AI Image (for image generation)
      └─ Other tools...

This approach gives you the same functionality as using it as a chat model provider, with even more flexibility!

Nodes

Pollinations.AI Chat (NEW - AI Agent Ready)

Optimized chat node for AI Agent integration with conversation state management.

Operations

• Chat - Simple chat with conversation history
• Chat with System Prompt - Chat with custom system instructions

Features

• ✅ AI Agent Compatible - Designed for n8n AI Agent workflows
• ✅ Conversation History - Maintains context across messages
• ✅ System Prompts - Customize AI behavior
• ✅ Multiple Models - OpenAI, Mistral, Gemini Search, DeepSeek
• ✅ Reasoning Control - Adjust AI thinking depth
• ✅ Streaming Support - Real-time responses

Example: Simple Chat

Operation: Chat
Model: openai
Message: "What is the capital of France?"

Example: Chat with System Prompt

Operation: Chat with System Prompt
Model: openai
System Prompt: "You are a helpful coding assistant"
User Message: "How do I sort an array in JavaScript?"

Example: With Conversation History

Operation: Chat
Model: openai
Message: "What's the weather like?"
Conversation History:
  - Role: user, Content: "Hello"
  - Role: assistant, Content: "Hi! How can I help?"

Output Format

The node returns:

• response - The AI's response text
• assistantMessage - Formatted assistant message object
• conversation - Full conversation including the new response
• messages - All messages sent to the API
• model - Model used

Perfect for AI Agent workflows where you need to maintain conversation context!

Pollinations.AI Image

Generate images from text prompts.

Operations

• Generate Image - Create an image from a text description
• List Models - Get available image generation models

Example: Generate an Image

Prompt: "a serene mountain landscape at sunrise"
Model: flux
Width: 1920
Height: 1080

The node returns:

• Binary data with the generated image
• JSON with image metadata and base64-encoded image data

Parameters

• Prompt (required) - Text description of the image
• Model - AI model to use (flux, turbo, etc.)
• Width/Height - Image dimensions in pixels
• Seed - Number for consistent results
• Remove Watermark - Remove Pollinations watermark (requires account)
• Enhance Prompt - Let AI improve your prompt
• Private - Hide from public feeds
• Safe Content Filter - Enable NSFW filtering
• Image-to-Image - Transform existing images (requires kontext model)

Pollinations.AI Text

Generate text using AI models.

Operations

• Generate Text (Simple) - Quick text generation from a prompt
• Generate Text (Advanced) - Full conversation with system prompts
• List Models - Get available text models

Example: Simple Text Generation

Prompt: "Explain quantum computing simply"
Model: openai
Temperature: 0.7

Example: Advanced Text Generation

Messages:
  - Role: system, Content: "You are a helpful assistant"
  - Role: user, Content: "Write a haiku about AI"
Model: openai
Temperature: 1.0
Max Tokens: 100

Parameters (Simple)

• Prompt (required) - Your question or task
• Model - AI model to use
• Temperature - Creativity level (0.0-3.0)
• Seed - For consistent responses
• System Prompt - Instructions for AI behavior
• JSON Response - Get response in JSON format
• Stream - Get real-time chunks

Parameters (Advanced)

• Messages - Conversation messages array
• Model - AI model to use
• Temperature - Creativity level
• Max Tokens - Maximum response length
• Reasoning Effort - How deeply AI thinks (minimal/low/medium/high)
• Stream - Real-time response chunks

Pollinations.AI Audio

Convert text to speech or transcribe audio.

Operations

• Text to Speech - Convert text to spoken audio
• Speech to Text - Transcribe audio files

Example: Text to Speech

Text: "Welcome to my app!"
Voice: nova

Returns binary audio data (MP3 format).

Example: Speech to Text

Audio Input: Binary Data
Binary Property: data
Audio Format: wav

Parameters (TTS)

• Text (required) - Text to convert
• Voice - Voice style (alloy, echo, fable, onyx, nova, shimmer)

Parameters (STT)

• Audio Input - Binary data or URL
• Binary Property - Name of binary property (if using binary)
• Audio URL - URL of audio file (if using URL)
• Audio Format - Format of audio (wav, mp3, m4a, ogg)

Pollinations.AI Vision

Analyze and describe images.

Operations

• Analyze Image - Describe or answer questions about images

Example: Analyze Image

Image Input: Binary Data
Binary Property: data
Prompt: "What's in this image?"
Model: openai
Max Tokens: 500

Parameters

• Model - Vision model (openai, openai-large, claude-hybridspace)
• Image Input - Binary data or URL
• Binary Property - Name of binary property (if using binary)
• Image URL - URL of image (if using URL)
• Prompt - Question or instruction about the image
• Max Tokens - Maximum response length

Usage Examples

Workflow: Generate Image and Analyze It

1. Pollinations.AI Image node

   • Operation: Generate Image
   • Prompt: "a cat wearing sunglasses"
   • Model: flux

2. Pollinations.AI Vision node

   • Operation: Analyze Image
   • Image Input: Binary Data
   • Binary Property: data (from previous node)
   • Prompt: "Describe this image in detail"

Workflow: Text to Speech Pipeline

1. Pollinations.AI Text node

   • Operation: Generate Text (Simple)
   • Prompt: "Write a short motivational quote"

2. Pollinations.AI Audio node

   • Operation: Text to Speech
   • Text: Use expression {{ $json.response }}
   • Voice: nova

Workflow: Transcribe Audio and Generate Summary

1. Pollinations.AI Audio node

   • Operation: Speech to Text
   • Audio Input: Binary Data
   • Binary Property: data

2. Pollinations.AI Text node

   • Operation: Generate Text (Advanced)
   • Messages:
     • System: "You are a helpful assistant that summarizes audio transcriptions"
     • User: {{ $json.transcription }}
   • Prompt: "Summarize this transcription"

Rate Limits

| Tier | Rate Limit | Access | |------|------------|--------| | Anonymous | 1 request every 15s | No signup | | Seed | 1 request every 5s | Free registration | | Flower | 1 request every 3s | Paid tier | | Nectar | No limits | Enterprise |

Register at auth.pollinations.ai for higher limits!

Models

Image Models

• flux
• turbo
• stable-diffusion
• kontext (for image-to-image)

Text Models

• openai
• mistral
• searchgpt
• gemini-search

Audio Models

• openai-audio

Vision Models

• openai
• openai-large
• claude-hybridspace

Resources

• Pollinations.AI Documentation
• Pollinations.AI Authentication
• n8n Documentation

License

MIT License - see LICENSE file for details.

Support

• GitHub Issues: Create an issue
• Pollinations.AI: Support

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Made with ❤️ by the Pollinations.AI team