by Yaron Been
Paigedutcher2 Paige AI Generator Description "Custom AI model trained on Paige — bold, curvy, confident energy. Think Barbie meets boss. Great for glam, fantasy, seductive, and influencer-style prompts. Use trigger word CharacterPGE to activate the model. Overview This n8n workflow integrates with the Replicate API to use the paigedutcher2/paige model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: paigedutcher2/paige API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Yaron Been
Digitalhera Heranathalie AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the digitalhera/heranathalie model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: digitalhera/heranathalie API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Yaron Been
Ligua033 Lorealcantara AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the ligua033/lorealcantara model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: ligua033/lorealcantara API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Yaron Been
Settyan Flash V2.0.0 Beta.4 AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the settyan/flash-v2.0.0-beta.4 model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: settyan/flash-v2.0.0-beta.4 API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Yaron Been
Settyan Flash V2.0.0 Beta.1 AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the settyan/flash-v2.0.0-beta.1 model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: settyan/flash-v2.0.0-beta.1 API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Yaron Been
Settyan Flash V2.0.0 Beta.7 AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the settyan/flash-v2.0.0-beta.7 model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: settyan/flash-v2.0.0-beta.7 API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Yaron Been
Settyan Flash V2.0.0 Beta.0 AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the settyan/flash-v2.0.0-beta.0 model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: settyan/flash-v2.0.0-beta.0 API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Dahiana
Monitor website performance with PageSpeed Insights and save to Google Sheets with alerts This n8n template automatically monitors website performance using Google's PageSpeed Insights API, compiles detailed reports, and tracks performance trends over time in Google Sheets. Use cases: Agency client monitoring, competitor analysis, performance regression detection, SEO reporting, site migration monitoring, A/B testing performance impact, and maintaining performance SLAs. Who's it for Digital agencies monitoring client websites SEO professionals tracking site performance DevOps teams maintaining performance SLAs Business owners wanting automated site monitoring How it works Automated Testing:** Scheduled audits of multiple websites using PageSpeed Insights API Core Web Vitals:** Tracks LCP, FID, CLS, and overall performance scores Historical Tracking:** Maintains performance history for trend analysis Alert System:** Sends notifications when performance drops below thresholds Detailed Reporting:** Captures specific recommendations and optimization opportunities Two Workflow Paths Scheduled Audit: Automatically tests all URLs from Google Sheet on schedule On-Demand Testing: Webhook endpoint for immediate single-URL testing How to set up Get a free PageSpeed Insights API key from Google Cloud Console Create Google Sheet with columns: URL, Site Name, Category, Alert Threshold, Last_Processed_Date and Device. Set up Google Sheets API credentials Configure notification preferences (Slack, email, etc.) Set audit schedule (daily, weekly, or custom) Define performance thresholds for alerts Requirements Google PageSpeed Insights API key (free) Google Sheets API access n8n instance (cloud or self-hosted) Optional: Slack/email for notifications Google Sheet Structure Input Sheet ("sites"): URL, Site_Name, Category, Alert_Threshold, Last_Processed_Date and Device. Results Sheet ("audit_results"): Date, URL, Site_Name, Device, Performance_Score, LCP, FID, CLS, Recommendations, Full_Report_URL API Usage (On-Demand) POST to webhook: { "url": "https://example.com", "site_name": "Example Site", "alert_threshold": 75 } How to customize Add custom performance thresholds per site Include additional metrics (accessibility, SEO, best practices) Connect to other dashboards (Data Studio, Grafana) Add competitor benchmarking Integrate with project management tools for issue tracking Set up different notification channels based on severity Sample Google Sheet Included
by Angel Menendez
Workflow Description Who is this for? This workflow is designed for sales and revenue teams using Gong and Salesforce to track and analyze sales calls. It helps automate the extraction, filtering, and preprocessing of Gong call data for further AI analysis. What problem is this solving? Sales teams often generate large amounts of call data, but not all calls are relevant for deeper analysis. This workflow filters calls based on predefined criteria, extracts relevant metadata, and formats the data before passing it to an AI processing pipeline. What this workflow does Triggers on new Gong calls synced to Salesforce** every hour. Filters calls based on opportunity stage** (Discovery or Meeting Booked). Retrieves Gong call details** via API. Formats call data into a structured JSON object** for AI processing. Passes the structured data to a Gong Call Preprocessor workflow** for further insights. Setup Ensure that you have connected Salesforce and Gong APIs with valid credentials. Modify the Salesforce query in Get all custom Salesforce Gong Objects to match your organization’s requirements. Set the schedule trigger interval in the Run Hourly node if needed. Connect this workflow to an AI processing workflow to analyze call transcripts. Workflow Templates: CallForge - 01 - Filter Gong Calls Synced to Salesforce by Opportunity Stage CallForge - 02 - Prep Gong Calls with Sheets & Notion for AI Summarization CallForge - 03 - Gong Transcript Processor and Salesforce Enricher CallForge - 04 - AI Workflow for Gong.io Sales Calls CallForge - 05 - Gong.io Call Analysis with Azure AI & CRM Sync CallForge - 06 - Automate Sales Insights with Gong.io, Notion & AI CallForge - 07 - AI Marketing Data Processing with Gong & Notion CallForge - 08 - AI Product Insights from Sales Calls with Notion How to customize Change filtering logic: Adjust the **opportunity stage filter (Check if Opportunity Stage is Meeting Booked or Discovery) to match your sales process. Modify data formatting**: Add or remove fields in the Format call into correct JSON Object node to customize the output. Adjust trigger frequency**: Change the Run Hourly node to run at a different interval if required.
by Piotr Sobolewski
How it works This advanced workflow transforms your long-form audio content (like podcast episodes or webinar recordings) into digestible, ready-to-use marketing assets. It's designed for podcasters, content creators, and marketers who want to maximize their content's reach. It automatically: Takes a full transcript of your audio/video content as input. Generates a concise, comprehensive summary of the episode using advanced AI. Extracts a list of key topics and keywords from the transcript, perfect for SEO, tagging, and content categorization. Delivers the summary and keywords directly to your inbox or a connected tool for easy access. Streamline your content repurposing pipeline and unlock new value from your audio and video assets with intelligent automation! Set up steps Setting up this powerful workflow typically takes around 20-30 minutes, as it involves multiple AI steps. You'll need to: Obtain API keys for your preferred AI service (e.g., OpenAI, Google AI). Have access to a method for generating transcripts from your audio/video (e.g., manually pasting, or using a separate transcription service like AssemblyAI, Whisper, etc.). Connect your preferred email service (e.g., Gmail) to receive the output. All detailed setup instructions and specific configuration guidance are provided within the workflow itself using sticky notes.
by Danger
How it Works This meta-workflow is designed to intelligently scan all your active workflows in n8n, identify those that contain Webhook nodes, and automatically generate a Swagger (OpenAPI) specification based on them. The output Swagger document reflects all accessible endpoints from your Webhook nodes, making it easier to: Visualize your API structure Share your endpoints Integrate with tools like Postman or Swagger UI Enhanced Parameter Support If you want the Swagger to reflect request parameters (e.g., query or body fields), you can annotate your Webhook nodes using the Note section. When configured properly, these annotations enrich your Swagger documentation with parameter names, types, and descriptions. Setup Steps Add the WebhookDocs to n8n Import the WebhookDocs JSON file into your n8n instance. Activate the WebhookDocs (you can also use the test-endpoint) Annotate Webhook Nodes (Optional but Recommended) To enable parameter documentation, open the Note section of each Webhook node and add annotations in the following format: //@body field_name string description //@query field_name string description Open the page https://n8n.youristance.com/webhook/swagger
by Aadarsh Jain
Who is this for? This workflow is designed for DevOps engineers, platform engineers, and Kubernetes administrators who want to interact with their Kubernetes clusters through natural language queries in n8n. It's perfect for teams who need quick cluster insights without memorizing complex kubectl commands or switching between multiple cluster contexts manually. How it works? The workflow operates in three intelligent stages: Cluster Discovery & Context Switching - Automatically lists available clusters from your kubeconfig and switches to the appropriate cluster based on your natural language query Command Generation - Uses GPT-4o to analyze your request and generate the correct kubectl command with proper flags, selectors, and output formatting Command Execution - Executes the generated kubectl command against your selected cluster and returns the results The workflow supports multi-cluster environments and can handle queries like: "Show me all pods in production cluster" "List failing deployments in production" "Get pod details in kube-system namespace" Setup Clone the MCP Server git clone https://github.com/aadarshjain/kubectl-mcp-server cd kubectl-mcp-server Configure your kubeconfig - Ensure your ~/.kube/config contains all the clusters you want to access Set up MCP STDIO credentials in n8n Command: /full/path/to/python-package Arguments: /full/path/to/kubectl-mcp-server/server.py Import the workflow into your n8n instance Configure OpenAI credentials for the GPT-4o models Test the workflow using the chat interface with queries like "show pods in [cluster-name]"