Workflow Templates

Prunaai Flux Schnell Image Generator Description This is a 3x faster FLUX.1 [schnell] model from Black Forest Labs, optimised with pruna with minimal quality loss. Contact us for more at pruna.ai Overview This n8n workflow integrates with the Replicate API to use the prunaai/flux-schnell model. This powerful AI model can generate high-quality image 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 Optional Parameters seed** (integer, default: None): Random seed. Set for reproducible generation megapixels** (string, default: 1): Approximate number of megapixels for generated image speed_mode** (string, default: Juiced 🔥 (default)): Run faster predictions with model optimized for speed num_outputs** (integer, default: 1): Number of outputs to generate aspect_ratio** (string, default: 1:1): Aspect ratio of the output image output_format** (string, default: jpg): Format of the output images output_quality** (integer, default: 80): Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs num_inference_steps** (integer, default: 4): Number of denoising steps. 4 is recommended, and lower number of steps produce lower quality outputs, faster. 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 image content Access the generated output from the final node API Reference Model: prunaai/flux-schnell API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of image generation parameters

This workflow automatically monitors the functionality of a factory. The workflow logs machine data coming from factory sensors in a CrateDB database, generates an incident report in PagerDuty, and notifies the responsible staff members when the temperature of a machine crosses the threshold value. This workflow builds on a workflow that generates factory data. Read more about this use case and how to build both workflows with step-by-step instructions in the blog post How to automate your factory's incident reporting. Prerequisites A PagerDuty account and credentials AMQP, an ActiveMQ  connection, and credentials A CrateDB instance running locally or on a server, and credentials. Nodes AMQP Trigger node starts the workflow. IF node filters sensor values higher than 50°C. PagerDuty node creates an incident in the account. Set nodes set the required incident information and sensor data, respectively. CrateDB nodes ingest the information data and machine sensor data, respectively. Function node converts degrees from Celsius to Fahrenheit.

This fun workflow automates the generation and delivery of personalized jokes by email based on the names or objects entered in the form. The process works as follows: On form submission The workflow starts when someone submits a form with the required names or objects to create the joke. You can modify the form fields to make the jokes more creative. Set the output language Manually define the language in which you want to receive the joke. OpenAI Message Model Uses the OpenAI model to generate the joke based on the prompt and in the chosen language. (The response is limited to around 200 tokens.) Gmail: send message The generated joke is automatically sent to the specified email address via Gmail.

This n8n workflow automates the process of researching companies by gathering relevant data such as traffic volume, foundation details, funding information, founders, and more. The workflow leverages the ProspectLens API, which is particularly useful for researching companies commonly found on Crunchbase and LinkedIn. ProspectLens is an API that provides very detailed company data. All you need to do is supply the company's domain name. You can obtain your ProspectLens API key here: https://apiroad.net/marketplace/apis/prospectlens In n8n, create a new "HTTP Header" credential. Set x-apiroad-key as the "Name" and enter your APIRoad API key as the "Value". Use this credential in the HTTP Request node of the workflow.

Store a key with a value in a local json file. Multiple keys could be saved in a single file. Related workflow: GetKey Create a subfolder in your n8n homedir: /home/node/.n8n/local-files. In docker look at the data path and create a subfolder local-files. Set the correct access rights chmod 1000.1000 local-files. Put the workflow code in a new workflow named WriteKey. Create another workflow with a function item: return { file: '/4711.json', // 4711 should be your workflow id key: 'MyKey', value: 'MyValue' } Pipe the function item to an Execution Workflow that calls the WriteKey workflow. It would be nice if we could get someday a shiny built-in n8n node that does the job. :)

How to scrap emails from websites This workflow shows how to quickly build an Email scraping API using n8n. Email marketing is at the core of most marketing strategies, be it content marketing, sales, etc. As such, being able to find contacts in bulk for your business on a large scale is key. There are available tools available in the market that can do this, but most are premium; why not build a custom one with n8n? Usage The workflow gets the data from a website and performs an extraction based on the date around on the website Copy the webhook URL to your browser Add a query parameter eg ?Website=https://mailsafi.com . This should give you a URL like this {{$n8nhostingurl/webhook/ea568868-5770-4b2a-8893-700b344c995e?Website=https://mailsafi.com Click on the URL and wait for the extracted email to be displayed. This will return the email address on the website, or if there is no email, the response will be "workflow successfully executed." Make sure to use HTTP:// for your domains Otherwise, you may get an error.

🎉 Do you want to master AI automation, so you can save time and build cool stuff? I’ve created a welcoming Skool community for non-technical yet resourceful learners. 👉🏻 Join the AI Atelier 👈🏻 Accepting payments via credit card online is a crucial component for the majority of businesses. Stripe provides a robust suite of tools for processing payments, yet many people still find it challenging to create a simple payment page and distribute it to their customers. 📋 Blog post 📺 Youtube Video This n8n workflow aims to offer the simplest and most direct method for generating a Stripe payment link. Features Quick Stripe Payment Link Creation:** Simply enter a title and select a price to create a Stripe payment link in seconds. Set Up Steps Connect your Stripe credentials. Fill the config node (currency). This n8n workflow template is crafted to significantly reduce the creation time of a Stripe Payment link. Created by the n8ninja.

AI-Powered Workflow for Auto-Responding to Positive Cold Email Replies This workflow is designed for agencies, freelancers, and sales teams who want to turn positive cold email replies into booked meetings automatically—without hiring VAs or spending hours on manual responses. ❓ The Problem Most teams waste time replying manually or pay for virtual assistants, leading to delays and missed opportunities. This template eliminates that bottleneck. ✅ What the Workflow Does Detects positive replies from Instantly.ai campaigns Uses AI to analyze intent and craft natural, human-like responses Adds personalization to keep replies authentic Includes Calendly links, product docs, or FAQs based on the lead’s intent Sends responses instantly—so you never miss a hot lead again No robotic AI text. Just smooth, human-style emails that get booked calls faster. 👥 Who is This For? Agencies** running Instantly.ai or similar outbound tools Founders** handling their own cold email outreach Sales teams** looking to automate follow-up and booking Anyone who gets 5–20 positive replies a week and wants to 2x–4x conversions ✅ Requirements n8n** (Cloud or self-hosted) Instantly.ai account** with API access OpenAI API key** (stored securely in n8n credentials) (Optional) Calendly or booking link, Notion or Google Docs for resources ⚙️ How to Set Up Import the workflow into n8n Add your Instantly.ai API credentials and OpenAI key using n8n’s credential manager Customize the AI prompt for your tone, CTA, and offer Insert your Calendly or booking link in the response template Test with one positive reply to confirm filtering and response quality Activate the workflow to auto-reply in real time 🔧 How to Customize Adjust the filtering logic for different keywords or intent signals Add branching for multiple booking links (e.g., based on region or service type) Push responses to a CRM for tracking Include extra resources like case studies or pricing docs

This workflow automatically connects to a Cloudflare R2 bucket (via S3-compatible API), filters out files older than 14 days, deletes them, and then sends a Telegram notification for each deletion. It runs on a daily schedule. 🕘 Schedule Trigger Executes the workflow once a day at a specified hour (e.g., 9 AM). 📦 S3 Node – List Files Retrieves all objects from a specific folder (prefix) in a Cloudflare R2 bucket using the S3 API. 🔎 Code Node – Filter Files Older Than 2 Weeks Filters the retrieved files by comparing their LastModified timestamps to the current date. Files older than 14 days (2 weeks) are selected for deletion. 🗑️ S3 Node – Delete File Deletes each filtered file from the R2 bucket. 📨 Telegram Node – Notify Deletion Sends a Telegram message with the name of the deleted file to a specified chat ID. The message includes:

This sub-workflow uses two custom Hugging Face regression models from Open Paws to evaluate and predict the real-world performance and advocacy alignment of text content. It’s designed to support animal advocacy organizations in optimizing their messaging across platforms like social media, email campaigns, and more. 🛠️ What It Does Sends input text to two deployed Hugging Face endpoints: Predicted Performance Model – Estimates real-world content success (e.g., engagement, shares, opens) based on patterns from real online data. Advocate Preference Model – Predicts how well the content will resonate with animal advocates (emotional impact, relevance, rationality, etc.) Outputs structured scores for both models Can be integrated into larger workflows for automated content review, filtering, or revision 📊 About the Models Text Performance Prediction Model** Trained on real-world data from 30+ animal advocacy organizations, this model predicts actual online performance of content—including social media, email marketing, and other outreach channels. Advocate Preference Prediction Model** Trained on ratings from animal advocates to evaluate how well a piece of text aligns with advocacy goals and values. Model Repositories: open-paws/text_performance_prediction_longform open-paws/animal_advocate_preference_prediction_longform > 📌 You must deploy each model as an inference endpoint on Hugging Face. Click "Deploy" on each model’s repo, then add the endpoint URL and your Hugging Face access token using n8n credentials. 📦 Use Cases Advocacy content review before publishing Automated scoring of outreach messages Filtering or flagging content with low predicted impact A/B testing support for message optimization

This workflow builds a valid RSS feed (which is an XML feed under the hood) for ARD Audiothek podcasts. This allows you to subscribe to such podcasts using your favourite podcatcher without using the ARD Audiothek app. The example builds a feed for Kalk & Welk, but the workflow can be easily adjusted by providing another podcast URL on the Get overview page HTTP Request node. To subscribe to the feed, active your n8n workflow and then use the Production URL from the intitial Feed Webhook node in your podcatcher. I've tested the resulting feed using Pocket Casts... ...and Miniflux: When using Miniflux, you can add your feed via this page to your account. Make sure you select Private when doing so to avoid sharing your n8n instance with the world. The resulting feed passes the W3C Feed Validation Service: The workflow can also be used as a foundation to free other podcasts from propriertary big media platforms, though not all of them will be as simple to deal with as the ARD Audiothek.

n8n does not currently offer a way to retrieve emails from arbritrary providers via a regular node. Unless you're using Gmail or Outlook, you can only use the email trigger to start a workflow when a new email arrives. This currently limits the possible use cases you can cover in your n8n workflows, as you cannot (for example) get an idea of how many unread messages there are in an inbox, or search for specific messages when an event occurs. But fear not, there's a new sheriff in town! The JMAP standard allows you to interact with your mailboxes, calendars and contacts through single HTTP requests whenever needed. This n8n workflow demonstrates how to retrieve the total number of unread messages from a JMAP server and also retrieve details for the first 3 messages. It can easily be adapted to search for messages other than unread, or to return details for more than the first 3 messages. Screenshots FAQ Which n8n version do I need? The workflow was built using n8n 1.20 and should work here out of the box. HTTP requests are also supported on older n8n versions, so the workflow can be backported as an alternative. Which credentials do I need? The JMAP standard does not limit the available authentication options. Fastmail (the sponsor of the standard) supports Bearer authentication as well as OAuth2. In n8n you can implement the Fastmail Bearer authentication by creating Header Auth credentials with a name of Authorization and a value of Bearer $apiToken (replacing $apiToken with your actual API token from Fastmail). For other services you'd need to check the respective API documentation for more details on the support authentication methods. What even is JMAP? It's an official Internet Engineering Task Force (IETF) standard, sponsored by Fastmail, that will hopefully replace the legacy standards CalDAV, CardDAV, and IMAP soon. The full specs are available here. How can I use JMAP? If you're a Fastmail customer or if you're hosting your own Stalwart mail server you can use JMAP today. If your email provider doesn't yet support JMAP, you might want to contact them and let them know you're interested in this functionality.