by Yaron Been
Seraphina Design Tracy AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the seraphina-design/tracy 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: seraphina-design/tracy API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
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.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 Firecrawl
Turn any prompt into structured web data. Send a POST request with a natural language prompt and an optional JSON schema, and get back clean, structured results scraped from the web by an AI agent powered by Firecrawl. Use Cases Data Enrichment**: Feed company names or URLs from your CRM and get back structured firmographic data (industry, funding, team size, tech stack). Lead Generation**: Ask the agent to find pricing, contact pages, or product details for a list of competitors. Market Research**: Extract structured pricing plans, feature comparisons, or product catalogs from any website. Content Aggregation**: Pull structured news, events, or job postings from across the web on a schedule. Sales Intelligence**: Enrich prospect lists with company info, recent news, or tech stack details before outreach. How It Works POST /webhook/scrape-agent Receive Scrape Request receives a POST request with prompt and an optional output_schema. Validate Output Schema checks the schema. If none is provided, it falls back to a permissive default. If the schema is malformed, it returns a clear error via Return Schema Error. Research & Extract Web Data takes the prompt and uses the full Firecrawl toolkit to research the web: Search (/search): Finds relevant pages and sources across the web. Scrape (/scrape): Extracts clean, structured content from any URL. Interact (interactContext, interact, interactStop): Lets the agent interact with scraped pages in a live session. After scraping a page, the agent can click buttons, fill forms, navigate dynamic content, and extract data that static scraping cannot reach, all without managing sessions manually. This combination gives the AI agent complete web navigation capabilities. It can discover sources, read pages, and interact with dynamic content autonomously. Format Response to Schema (Structured Output Parser) formats the agent's response to match the provided (or default) schema. Return Structured Results sends the structured JSON back to the caller. Setup Requirements Firecrawl API Key**: Sign up at firecrawl.dev and grab your API key. Connect it in the Firecrawl credential nodes. LLM Provider**: Configure your Primary Chat Model and Fallback Chat Model nodes (e.g., OpenRouter, OpenAI, Anthropic). The template uses two model nodes for reliability, plus a separate Parser Chat Model for the output parser. n8n Instance**: Self-hosted or cloud. Make sure the webhook node is set to accept POST requests. API Reference Endpoint POST https://your-n8n-instance/webhook/scrape-agent Request Body | Field | Type | Required | Description | |-------|------|----------|-------------| | prompt | string | Yes | Natural language instruction for the agent | | output_schema | object | No | JSON Schema defining the desired output structure | Response Returns a JSON object matching the provided schema, or a flexible object if no schema was given. Testing Examples 1. Basic Request (No Schema) The agent decides the output structure on its own. curl -X POST "https://your-n8n-instance/webhook/scrape-agent" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Find the latest pricing for Firecrawl" }' | jq Expected output: A JSON object with whatever structure the agent finds most appropriate for the data. Since no schema was provided, the internal default ({ "type": "object", "additionalProperties": true }) is used. 2. Request With a Custom Schema You define exactly the shape of data you want back. curl -X POST "https://your-n8n-instance/webhook/scrape-agent" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Find the latest pricing for Firecrawl", "output_schema": { "type": "object", "properties": { "source": { "type": "string" }, "plans": { "type": "array", "items": { "type": "object", "properties": { "name": { "type": "string" }, "price": { "type": "string" }, "credits": { "type": "string" }, "highlights": { "type": "array", "items": { "type": "string" } } } } } } } }' | jq Expected output: { "output": { "source": "https://www.firecrawl.dev/pricing", "plans": [ { "name": "Free", "price": "$0 (one-time)", "credits": "500 credits (one-time)", "highlights": [ "Scrape up to 500 pages", "2 concurrent requests", "Low rate limits", "No credit card required" ] }, { "name": "Hobby", "price": "$16/month (billed yearly, save $38)", "credits": "3,000 credits / month", "highlights": [ "Scrape up to 3,000 pages", "5 concurrent requests", "Basic support", "$9 per extra 1k credits" ] } ] } } 3. Invalid Schema (String Instead of Object) curl -X POST "https://your-n8n-instance/webhook/scrape-agent" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Find the latest pricing for Firecrawl", "output_schema": "not a valid schema" }' | jq Expected output: { "error": true, "message": "Invalid output_schema: must be a JSON object with a valid 'type' property (object, array, string, number, boolean)", "example_schema": { "type": "object", "properties": { "name": { "type": "string" }, "price": { "type": "number" } } } } 4. Invalid Schema (Array Instead of Object) curl -X POST "https://your-n8n-instance/webhook/scrape-agent" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Find the latest pricing for Firecrawl", "output_schema": [1, 2, 3] }' | jq Expected output: Same error response as above. 5. Invalid Schema (Missing type Property) curl -X POST "https://your-n8n-instance/webhook/scrape-agent" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Find the latest pricing for Firecrawl", "output_schema": { "properties": { "name": { "type": "string" } } } }' | jq Expected output: Same error response as above. 6. Invalid Schema (Invalid type Value) curl -X POST "https://your-n8n-instance/webhook/scrape-agent" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Find the latest pricing for Firecrawl", "output_schema": { "type": "banana" } }' | jq Expected output: Same error response as above. Workflow Architecture Receive Scrape Request (POST) | v Validate Output Schema |--- Error --> Return Schema Error (error JSON) |--- Success --> Research & Extract Web Data (AI Agent) | |--- Primary Chat Model |--- Fallback Chat Model |--- Search & Scrape: | - /search with Firecrawl | - /scrape with Firecrawl |--- Interact Tool: | - Interact context with Firecrawl | - Execute interaction with Firecrawl | - Stop interaction with Firecrawl | v Return Structured Results | |--- Format Response to Schema (Output Parser) | |--- Parser Chat Model Schema Validation Logic The Validate Output Schema node runs this validation before passing data to the agent: If output_schema is missing or null, the default permissive schema is used: { "type": "object", "additionalProperties": true }. If output_schema is present, it must be a JSON object (not a string, array, or primitive). It must have a type property with a valid value: object, array, string, number, or boolean. If validation fails, the workflow returns an error response with a helpful message and example schema. Notes The Format Response to Schema node (Structured Output Parser) requires the schema to be passed as a JSON string. The expression {{ JSON.stringify($('Validate Output Schema').item.json.output_schema) }} handles this conversion. The agent has access to Firecrawl's full toolkit: search, scrape, and interact. With all three connected, the agent has complete web navigation powers. It can discover sources via search, extract content via scrape, and interact with dynamic JavaScript-heavy pages via interact. The interact tools let the agent scrape a page first and then continue working with it in a live session, clicking buttons, filling forms, and navigating deeper, all without manual session management. The agent autonomously decides which tools to use based on the prompt. Response times vary depending on the complexity of the prompt and how many pages the agent needs to visit. Simple lookups take a few seconds; deep research can take longer.
by Max Tkacz
Who is this template for? This workflow template is designed for Sales and Customer Success professionals seeking alerts when potential high-value users, prospects, or existing customers register for a Discourse community. Leveraging Clearbit, it retrieves enriched data for the new member to assess their value. Example result in Slack How it works Each time a new member is created in Discourse, the workflow runs (powered by Discourse's native Webhooks feature). After filtering out popular private email accounts, we run the member's email through Clearbit to fetch available information on the member as well as their organization. If the enriched data meets certain criteria, we send a Slack message to a channel. This message has a few quick actions: Open LinkedIn profile and Email member Setup instructions Overview is below. Watch this 🎥 quick set up video for detailed instructions on how to get the template running, as well as how to customize it. Complete the Set up credentials step when you first open the workflow. You'll need a Discourse (admin user), Clearbit, and Slack account. Set up the Webhook in Discourse, linking the On new Discourse user Trigger with your Discourse community. Set the correct channel to send to in the Post message in channel step After testing your workflow, swap the Test URL to Production URL in Discourse and activate your workflow Template was created in n8n v1.29.1
by Jonathan
How it works This workflow watches a selected Google Drive folder for any images added to it. It then takes that image, sends it the the tinypng.com service which optimises and reduces its size (where possible) Tinypng then returns the updated image which is then automatically saved in your chose Google Drive folder Setting things up It's pretty simple to configure and should only take around 5-10mins. You only need to set up credentials for Google Drive and Tinypng.com For Tinypng.com you can sign up for their free tier API access which gives you 500 optimisations per month Once you have those two things, you just need choose your 'input' folder to watch for images and your 'output' folder for where these images should be stored There are a few more optional things you can do such as the naming of your final image and also lots more you could do with the Tinypng API for more advanced image optimisation
by Milorad Filipovic
This workflow will translate all your PDF documents from specified Google Drive folder to the desired language. Translated files will be automatically uploaded to the original folder. Required accounts 1️⃣ Google Drive account 2️⃣ DeepL developer account and API key How to setup? 1️⃣ Setup your google drive folder url, target and source language in the configuration node 2️⃣ Connect your Google Drive account with all Google Drive nodes 3️⃣ Setup HTTP header credentials that should be used for HTTP nodes in the template (replace yourAuthKey with your DeepL API key) 4️⃣ Set your DeepL header credentials in all HTTP nodes