This workflow follows the HTTP Request → OpenAI recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"id": "image-agent",
"name": "Image Agent",
"description": "AI agent that handles image processing, analysis, and generation for LinkedIn posts",
"nodes": [
{
"parameters": {
"functionCode": "const input = $input.first().json;\nconst hasPhoto = input.hasPhoto;\nconst photoId = input.photoId;\nconst content = input.content || '';\n\nreturn {\n hasPhoto: hasPhoto,\n photoId: photoId,\n content: content,\n chatId: input.chatId,\n systemPrompt: `You are an expert visual content strategist for LinkedIn. Your role is to analyze images and suggest visual enhancements for posts.\n\nBased on the content and any provided images, decide:\n1. If images should be included in the final post\n2. What type of image would best complement the content\n3. Image placement and sizing recommendations\n4. Alternative image suggestions if needed\n\nFormat your response as JSON with these fields:\n{\n \"includeInPost\": \"boolean\",\n \"imageUrl\": \"string (if existing image)\",\n \"imageAnalysis\": \"string\",\n \"recommendations\": [\"array\"],\n \"generateNew\": \"boolean\",\n \"imageDescription\": \"string (for generation)\"\n}`\n};"
},
"id": "set-image-prompt",
"name": "Set Image Agent Prompt",
"type": "n8n-nodes-base.function",
"typeVersion": 1,
"position": [
0,
0
]
},
{
"parameters": {
"functionCode": "const input = $input.first().json;\n\nif (input.hasPhoto) {\n // Download and analyze the image\n return {\n action: 'analyze',\n photoId: input.photoId,\n content: input.content,\n systemPrompt: input.systemPrompt\n };\n} else {\n // Generate image suggestions\n return {\n action: 'suggest',\n content: input.content,\n systemPrompt: input.systemPrompt\n };\n}"
},
"id": "decide-image-action",
"name": "Decide Image Action",
"type": "n8n-nodes-base.function",
"typeVersion": 1,
"position": [
250,
0
]
},
{
"parameters": {
"method": "GET",
"url": "https://api.telegram.org/bot{{ $credentials.telegram.botToken }}/getFile?file_id={{ $input.first().json.photoId }}",
"options": {}
},
"id": "get-file-info",
"name": "Get Telegram File Info",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 1,
"position": [
500,
0
]
},
{
"parameters": {
"method": "GET",
"url": "https://api.telegram.org/file/bot{{ $credentials.telegram.botToken }}/{{ $input.first().json.result.file_path }}",
"options": {
"responseFormat": "arraybuffer"
}
},
"id": "download-image",
"name": "Download Image",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 1,
"position": [
750,
0
]
},
{
"parameters": {
"model": "gpt-4-vision",
"messages": "=[{\n 'role': 'user',\n 'content': [\n {\n 'type': 'text',\n 'text': `Analyze this image in the context of this LinkedIn post content: \"${$input.first().json.content}\". Should this image be included in the post? Provide recommendations.`\n },\n {\n 'type': 'image_url',\n 'image_url': {\n 'url': `data:image/jpeg;base64,${$input.first().json.body.toString('base64')}`\n }\n }\n ]\n}]",
"options": {
"temperature": 0.7,
"maxTokens": 500
}
},
"id": "analyze-image",
"name": "Analyze Image with Vision",
"type": "n8n-nodes-base.openai",
"typeVersion": 1,
"position": [
1000,
0
]
},
{
"parameters": {
"model": "gpt-4",
"messages": "=[{\n 'role': 'system',\n 'content': $input.first().json.systemPrompt\n}, {\n 'role': 'user',\n 'content': `Content: ${$input.first().json.content}\\n\\nSuggest image concepts for this LinkedIn post.`\n}]",
"options": {
"temperature": 0.8,
"maxTokens": 400
}
},
"id": "suggest-image",
"name": "Suggest Image Concepts",
"type": "n8n-nodes-base.openai",
"typeVersion": 1,
"position": [
500,
300
]
},
{
"parameters": {
"functionCode": "const input = $input.first().json;\n\nif (input.action === 'analyze') {\n const analysis = input.choices[0].message.content;\n const includeInPost = analysis.toLowerCase().includes('yes') || analysis.toLowerCase().includes('include');\n const imageUrl = includeInPost ? `data:image/jpeg;base64,${input.body.toString('base64')}` : null;\n return {\n includeInPost: includeInPost,\n imageUrl: imageUrl,\n imageAnalysis: analysis,\n recommendations: ['Image analyzed', 'Decision made based on content fit'],\n generateNew: !includeInPost,\n imageDescription: includeInPost ? null : `Create an attention-grabbing LinkedIn visual based on: ${input.content}` ,\n chatId: input.chatId\n };\n} else {\n const suggestions = input.choices[0].message.content;\n return {\n includeInPost: false,\n imageUrl: null,\n imageAnalysis: 'No image provided',\n recommendations: suggestions.split('\n').filter(s => s.trim()),\n generateNew: true,\n imageDescription: suggestions || `Create professional LinkedIn visual for: ${input.content}` ,\n chatId: input.chatId\n };\n}"
},
"id": "process-image-decision",
"name": "Process Image Decision",
"type": "n8n-nodes-base.function",
"typeVersion": 1,
"position": [
1250,
0
]
},
{
"parameters": {
"rules": [
{
"value1": "={{$json.includeInPost}}",
"operation": "equal",
"value2": "true"
}
],
"continueOnFail": true
},
"id": "if-has-image",
"name": "If Has Image",
"type": "n8n-nodes-base.if",
"typeVersion": 1,
"position": [
1500,
0
]
},
{
"parameters": {
"model": "gpt-image-1",
"prompt": "={{ $json.imageDescription || 'Professional LinkedIn post image with modern flat-style, consistent with a business content theme.' }}",
"size": "1024x1024",
"responseFormat": "b64_json"
},
"id": "generate-image",
"name": "Generate Image",
"type": "n8n-nodes-base.openai",
"typeVersion": 1,
"position": [
1750,
0
]
},
{
"parameters": {
"functionCode": "const input = $input.first().json;\nif (input.data && input.data[0] && input.data[0].b64_json) {\n return { includeInPost: true, imageUrl: `data:image/png;base64,${input.data[0].b64_json}`, imageAnalysis: 'Generated image', recommendations: [], generateNew: false, chatId: input.chatId };\n}\nreturn { includeInPost: false, imageUrl: null, imageAnalysis: 'Image generation failed', recommendations: [], generateNew: false, chatId: input.chatId };"
},
"id": "process-generated-image",
"name": "Process Generated Image",
"type": "n8n-nodes-base.function",
"typeVersion": 1,
"position": [
2000,
0
]
},
{
"parameters": {
"functionCode": "const existing = $input.first().json; const generated = $input.second().json; return { includeInPost: true, imageUrl: existing.imageUrl || generated.imageUrl, imageAnalysis: existing.imageAnalysis || generated.imageAnalysis, recommendations: (existing.recommendations||[]).concat(generated.recommendations||[]), chatId: existing.chatId || generated.chatId };"
},
"id": "final-image-output",
"name": "Final Image Output",
"type": "n8n-nodes-base.function",
"typeVersion": 1,
"position": [
2250,
0
]
}
],
"connections": {
"Set Image Agent Prompt": {
"main": [
[
{
"node": "Decide Image Action",
"type": "main",
"index": 0
}
]
]
},
"Decide Image Action": {
"main": [
[
{
"node": "Get File Info",
"type": "main",
"index": 0
}
],
[
{
"node": "Suggest Image Concepts",
"type": "main",
"index": 1
}
]
]
},
"Get File Info": {
"main": [
[
{
"node": "Download Image",
"type": "main",
"index": 0
}
]
]
},
"Download Image": {
"main": [
[
{
"node": "Analyze Image with Vision",
"type": "main",
"index": 0
}
]
]
},
"Analyze Image with Vision": {
"main": [
[
{
"node": "Process Image Decision",
"type": "main",
"index": 0
}
]
]
},
"Suggest Image Concepts": {
"main": [
[
{
"node": "Process Image Decision",
"type": "main",
"index": 1
}
]
]
},
"Process Image Decision": {
"main": [
[
{
"node": "If Has Image",
"type": "main",
"index": 0
}
]
]
},
"If Has Image": {
"main": [
[
{
"node": "Final Image Output",
"type": "main",
"index": 0
}
]
],
"else": [
[
{
"node": "Generate Image",
"type": "main",
"index": 0
}
]
]
},
"Generate Image": {
"main": [
[
{
"node": "Process Generated Image",
"type": "main",
"index": 0
}
]
]
},
"Process Generated Image": {
"main": [
[
{
"node": "Final Image Output",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {},
"staticData": null
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Image Agent. Uses httpRequest, openai. Manual trigger; 11 nodes.
Source: https://github.com/ruvcaltd/n8n/blob/a4620cfa4f1aee541f2b2a96f276c689204f06cc/workflows/image-agent.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Send one WhatsApp message → Get AI-optimized content across 7+ social platforms.
Output Parser Structured, Google Gemini Chat, OpenAI Chat +8
Video runthrough
Google Drive, Output Parser Structured, HTTP Request +3
This template is built for solo attorneys, small law firms, and legal billing coordinators who receive timesheet documents by email and need to produce LEDES-compliant e-billing files for client billi
Email Read Imap, Microsoft Excel, N8N Nodes Word2Text +4
This template is for HR teams, recruitment agencies, and startups that receive job applications via Indeed and want to eliminate manual CV screening. If you're spending hours reading CVs before decidi
Email Read Imap, Chain Llm, Output Parser Structured +5
This workflow automates your entire sales outreach process across LinkedIn, Email, and WhatsApp using AI to create hyper-personalized messages for each prospect. Instead of spending hours crafting ind
Google Sheets, Gmail, Agent +4