AI product Images
Workflow JSON
{"name": "AI product Images", "nodes": [{"parameters": {}, "type": "n8n-nodes-base.manualTrigger", "typeVersion": 1, "position": [0, 0], "id": "1ddfbdfd-f3c0-4ef5-8b48-a3ae77a92955", "name": "When clicking \u2018Test workflow\u2019"}, {"parameters": {"resource": "fileFolder", "filter": {"folderId": {"__rl": true, "value": "1NQ_9HXkMrjm_DPZENAmwRo0JJkvQm8BU", "mode": "id"}}, "options": {}}, "type": "n8n-nodes-base.googleDrive", "typeVersion": 3, "position": [220, 0], "id": "6feb317d-1d43-4174-a5a3-b9e4a2bf46e6", "name": "Google Drive", "credentials": {"googleDriveOAuth2Api": {"id": "", "name": "[Your googleDriveOAuth2Api]"}}}, {"parameters": {"operation": "download", "fileId": {"__rl": true, "value": "={{$json[\"id\"]}}", "mode": "id"}, "options": {}}, "type": "n8n-nodes-base.googleDrive", "typeVersion": 3, "position": [460, 0], "id": "b5232274-25a6-43b7-a424-dcfff47057ba", "name": "Google Drive1", "credentials": {"googleDriveOAuth2Api": {"id": "", "name": "[Your googleDriveOAuth2Api]"}}}, {"parameters": {"resource": "image", "operation": "analyze", "modelId": {"__rl": true, "value": "gpt-4o", "mode": "list", "cachedResultName": "GPT-4O"}, "text": "Describe the visual style of this image, what stands out. if you had to have a holistic overview, as a professional facebook ads designer. How would you explain this image / or images to be able to reproduce the elements that make it work for other ads.\n\nThe core goal of the output here should be to create a template of the style for inspirations. As later we will take ideas from these to generate our own high converting facebook ads.\n\nensure you do not make this product specific, rather focusing on creating outlines for static ad styles. so keep ti vague in terms of what exactly is in the ad, but rather the principles of the ad", "inputType": "base64", "options": {}}, "type": "@n8n/n8n-nodes-langchain.openAi", "typeVersion": 1.8, "position": [720, -20], "id": "ff9ab47d-5980-4d2d-ab5e-1e76d0df87ab", "name": "OpenAI", "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}}, {"parameters": {"resource": "fileFolder", "searchMethod": "query", "filter": {"folderId": {"__rl": true, "value": "11t72SNGpHJvGk-UurfuLwGpdMz37-cwW", "mode": "id"}}, "options": {}}, "type": "n8n-nodes-base.googleDrive", "typeVersion": 3, "position": [220, 240], "id": "b5e0b994-cde8-4069-bdac-3173ecf8ccfb", "name": "Google Drive2", "credentials": {"googleDriveOAuth2Api": {"id": "", "name": "[Your googleDriveOAuth2Api]"}}}, {"parameters": {"operation": "download", "fileId": {"__rl": true, "value": "={{$json[\"id\"]}}", "mode": "id"}, "options": {}}, "type": "n8n-nodes-base.googleDrive", "typeVersion": 3, "position": [460, 240], "id": "41b44442-46d1-40b7-9a26-57f410d0426b", "name": "Google Drive3", "credentials": {"googleDriveOAuth2Api": {"id": "", "name": "[Your googleDriveOAuth2Api]"}}}, {"parameters": {"resource": "image", "operation": "analyze", "modelId": {"__rl": true, "value": "gpt-4o", "mode": "list", "cachedResultName": "GPT-4O"}, "text": "Analyse our product image. Identify the core emotions behind it and the main product. we will use this later to connect the product image with some ad styles and generate our own ads", "inputType": "base64", "options": {}}, "type": "@n8n/n8n-nodes-langchain.openAi", "typeVersion": 1.8, "position": [700, 240], "id": "1eea9b08-38d1-48dc-b578-88d0818de342", "name": "OpenAI1", "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}}, {"parameters": {"model": {"__rl": true, "value": "gpt-4", "mode": "list", "cachedResultName": "gpt-4"}, "options": {}}, "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "typeVersion": 1.2, "position": [1040, 420], "id": "6a97f2fe-fc62-4591-bb03-37d4ae24343c", "name": "OpenAI Chat Model", "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}}, {"parameters": {"promptType": "define", "text": "=You\u2019ve been given an outline that includes: \n\n(use all the data from here when creating the prompts {{ $json.choices[0].message.content }} - it is also critical our product image is displayed in here: {{ $('OpenAI1').item.json.content }} )\n\nWhat the product is and who it\u2019s for\n\nWhat\u2019s visible in the product image (e.g. background, angle, lighting)\n\nPatterns and emotional triggers from top-performing ad examples\n\nYour task:\nUsing this outline, generate 10 image ad prompts that follow this format exactly:\n\nprompt: [Detailed visual description of the ad concept]\n\nEach prompt should include:\n\nA bold, testimonial-style headline (in quotation marks at the top)\n\nA clear description of the emotional transformation the image should convey\n\nWhat is shown in the image (body parts, facial expressions, environment, etc.)\n\nWhere and how the product is placed\n\nThe color palette and visual tone (e.g., icy blue for calm, red for pain)\n\nWhere the headline should appear on the image\n\nRendering style (e.g., cinematic, hyperrealistic, dramatic shadows)\n\nFinal format for Facebook or Instagram (1:1 format always)\n\nRepeat this 10 times. Each one must be unique, emotionally powerful, and visually clear.", "hasOutputParser": true, "options": {}}, "type": "@n8n/n8n-nodes-langchain.agent", "typeVersion": 1.9, "position": [1120, 240], "id": "16138c72-2b3d-4c4b-9d11-ad91d15c2e4c", "name": "AI prompt agent"}, {"parameters": {"jsonSchemaExample": "[\n {\n \"Prompt\": \"Sun-drenched poolside shot of the product on a marble ledge at golden hour, with soft shadows and warm tones. Aspect ratio 1:1.\"\n },\n {\n \"Prompt\": \"Cool lavender-tinted sunset beach backdrop behind the product, highlighting reflective metallic accents. Aspect ratio 4:5.\"\n },\n {\n \"Prompt\": \"...\"\n }\n]\n"}, "type": "@n8n/n8n-nodes-langchain.outputParserStructured", "typeVersion": 1.2, "position": [1380, 420], "id": "8fbfad99-d724-45a9-9b3e-e45e486dcfc5", "name": "Structured Output Parser"}, {"parameters": {"fieldToSplitOut": "output", "options": {}}, "type": "n8n-nodes-base.splitOut", "typeVersion": 1, "position": [1560, 160], "id": "508946cd-0aed-4858-bf5a-c25e64371ea4", "name": "Split Out"}, {"parameters": {"method": "POST", "url": "https://api.openai.com/v1/images/generations", "sendHeaders": true, "headerParameters": {"parameters": [{"name": "Authorization", "value": "Bearer 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"}, {"name": "Content-type", "value": "application/json"}]}, "sendBody": true, "bodyParameters": {"parameters": [{"name": "model", "value": "gpt-image-1"}, {"name": "prompt", "value": "={{ $json.Prompt }}"}, {"name": "size", "value": "1024x1024"}]}, "options": {}}, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [2320, 160], "id": "ab08c200-9ff9-4dd9-86be-09b8f1e219a9", "name": "HTTP Request1"}, {"parameters": {"options": {}}, "type": "n8n-nodes-base.splitInBatches", "typeVersion": 3, "position": [1840, 160], "id": "dc69258e-7c57-4158-92af-7257ba85102e", "name": "Loop Over Items1"}, {"parameters": {"amount": 15}, "type": "n8n-nodes-base.wait", "typeVersion": 1.1, "position": [2100, 160], "id": "1af8885e-00a3-49f1-b159-1a02eba84a84", "name": "Wait", "webhookId": "9f2950cd-2ab2-405f-83d7-4f44e15e16f2"}, {"parameters": {"operation": "toBinary", "sourceProperty": "data[0].b64_json", "options": {"fileName": "image.png", "mimeType": "image/png"}}, "type": "n8n-nodes-base.convertToFile", "typeVersion": 1.1, "position": [2540, 160], "id": "535a5a20-11ab-476a-be3b-07e23073d5f5", "name": "Convert to File"}, {"parameters": {"modelId": {"__rl": true, "value": "gpt-4", "mode": "list", "cachedResultName": "GPT-4"}, "messages": {"values": [{"content": "=Analyse this prompt which is a template of a high converting facebook ad we have built {{ $json.content }}\n\nNow we will take this template, and add our product in as the hero for our ads{{ $json.content}}\n\nensure the template is applied to make our product the hereo, with all copy, colours and vibe being focused on making the product stand out, in a facebook ad, deisgn to convert.\n\nMake a relevant prompt & outline as our next step in the flow is to break down this prompt (combining the facebook ad visual style, with our product image) and spit it into 10 prompts, all to create individual statics.\n\nDo what you think is best to pass this information forward.", "role": "system"}, {"content": "Put both pieces of data together and only generate 1 output prompt\n"}]}, "simplify": false, "options": {}}, "type": "@n8n/n8n-nodes-langchain.openAi", "typeVersion": 1.8, "position": [1020, -20], "id": "a01ff233-7e6f-456e-b691-f54a5c73aee0", "name": "OpenAI2", "executeOnce": false, "alwaysOutputData": false, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}}, {"parameters": {"driveId": {"__rl": true, "mode": "list", "value": "My Drive"}, "folderId": {"__rl": true, "value": "1V_USzVT-v-6LIjk3HPd0nlr2vnv4nJAr", "mode": "list", "cachedResultName": "n8n testing", "cachedResultUrl": "https://drive.google.com/drive/folders/1V_USzVT-v-6LIjk3HPd0nlr2vnv4nJAr"}, "options": {}}, "type": "n8n-nodes-base.googleDrive", "typeVersion": 3, "position": [2780, 160], "id": "3deb2f20-abc3-439e-b181-24c1956a4657", "name": "Google Drive4", "credentials": {"googleDriveOAuth2Api": {"id": "", "name": "[Your googleDriveOAuth2Api]"}}}], "pinData": {}, "connections": {"When clicking \u2018Test workflow\u2019": {"main": [[{"node": "Google Drive", "type": "main", "index": 0}]]}, "Google Drive": {"main": [[{"node": "Google Drive1", "type": "main", "index": 0}]]}, "Google Drive1": {"main": [[{"node": "OpenAI", "type": "main", "index": 0}]]}, "Google Drive2": {"main": [[{"node": "Google Drive3", "type": "main", "index": 0}]]}, "Google Drive3": {"main": [[{"node": "OpenAI1", "type": "main", "index": 0}]]}, "OpenAI": {"main": [[{"node": "Google Drive2", "type": "main", "index": 0}]]}, "OpenAI1": {"main": [[{"node": "OpenAI2", "type": "main", "index": 0}]]}, "OpenAI Chat Model": {"ai_languageModel": [[{"node": "AI prompt agent", "type": "ai_languageModel", "index": 0}]]}, "AI prompt agent": {"main": [[{"node": "Split Out", "type": "main", "index": 0}]]}, "Structured Output Parser": {"ai_outputParser": [[{"node": "AI prompt agent", "type": "ai_outputParser", "index": 0}]]}, "Split Out": {"main": [[{"node": "Loop Over Items1", "type": "main", "index": 0}]]}, "HTTP Request1": {"main": [[{"node": "Convert to File", "type": "main", "index": 0}]]}, "Loop Over Items1": {"main": [[], [{"node": "Wait", "type": "main", "index": 0}]]}, "Wait": {"main": [[{"node": "HTTP Request1", "type": "main", "index": 0}]]}, "Convert to File": {"main": [[{"node": "Google Drive4", "type": "main", "index": 0}]]}, "OpenAI2": {"main": [[{"node": "AI prompt agent", "type": "main", "index": 0}]]}, "Google Drive4": {"main": [[{"node": "Loop Over Items1", "type": "main", "index": 0}]]}}, "active": false, "settings": {"executionOrder": "v1"}, "versionId": "85462564-6f39-41df-b09c-9507c177c96a", "meta": {"templateCredsSetupCompleted": true, "instanceId": "aa305389a9f146cc99db373653903c47ecf7fe4bb66df261da9bedf94add0f72"}, "id": "XZrlhnSYaHKcAdp4", "tags": []}How to Import This Workflow
- 1Copy the workflow JSON above using the Copy Workflow JSON button.
- 2Open your n8n instance and go to Workflows.
- 3Click Import from JSON and paste the copied workflow.
Don't have an n8n instance? Start your free trial at n8nautomation.cloud
Related Templates
KB Tool - Confluence Knowledge Base
Quickly retrieve information from your Confluence knowledge base with this n8n workflow. It connects to your Confluence instance via an HTTP Request node, allowing you to query for specific content directly from n8n. This workflow is ideal for support teams needing to rapidly access articles, developers looking up documentation, or anyone who frequently references Confluence pages and wants to integrate that data into other automated processes. By centralizing Confluence queries within n8n, you save significant time and effort previously spent manually navigating and searching, streamlining information retrieval and improving operational efficiency.
Analyze the sentiment of feedback and send a message on Mattermost
Automatically analyze customer feedback sentiment and notify your team on Mattermost with this n8n workflow. This automation connects Typeform submissions directly to Google Cloud Natural Language for sentiment analysis, then routes the results to your Mattermost channel. When a user submits a form through Typeform, the workflow extracts the feedback, sends it to Google Cloud Natural Language for sentiment scoring, and based on that score, sends a message to a designated Mattermost channel, allowing for immediate team awareness of positive, negative, or neutral feedback. This workflow is ideal for product managers, customer support teams, or marketing departments who need to quickly gauge public opinion or customer satisfaction from surveys, support tickets, or product reviews, enabling faster response times to critical feedback and reducing the manual effort of monitoring and reporting. It saves significant time and ensures that important customer insights are never missed, fostering a more responsive and customer-centric operation.
Hacker News Throwback Machine - See What Was Hot on This Day, Every Year!
Discover what was trending on Hacker News on this exact day, every year, with the Hacker News Throwback Machine. This n8n workflow automates the process of fetching historical Hacker News front pages and summarizing the top stories, delivering a daily dose of tech nostalgia directly to your Telegram chat. A Schedule Trigger initiates the workflow, which then dynamically generates a list of past years. For each year, it uses an HTTP Request node to retrieve the Hacker News front page for today's date, then an HTML Extract Details node parses the headlines and links. These headlines are then compiled and fed into a Google Gemini Chat Model via a Basic LLM Chain, which summarizes the most interesting stories. Finally, the summarized insights are sent to your designated Telegram chat, providing a unique historical perspective without any manual effort. This workflow is perfect for tech enthusiasts, developers, or anyone curious about the evolution of tech news, saving significant time and effort compared to manually searching through archives.