n8n
Workflow
Easy Image Captioning With Gemini 1 5 Pro
This n8n workflow automates tasks and integrates with various services. Easy Image Captioning With Gemini 1 5 Pro - ready to import and run in your n8n instance.
n8n
workflow.json
About This Script
This n8n workflow automates tasks and integrates with various services. Easy Image Captioning With Gemini 1 5 Pro - ready to import and run in your n8n instance.
Features:
- Makes HTTP requests to external APIs
Source Code
{
"nodes": [
{
"id": "0b64edf1-57e0-4704-b78c-c8ab2b91f74d",
"name": "When clicking \u2018Test workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
480,
300
],
"parameters": [],
"typeVersion": 1
},
{
"id": "a875d1c5-ccfe-4bbf-b429-56a42b0ca778",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
1280,
720
],
"parameters": {
"options": [],
"modelName": "models/gemini-1.5-flash"
},
"credentials": {
"googlePalmApi": {
"id": "dSxo6ns5wn658r8N",
"name": "Google Gemini(PaLM) Api account"
}
},
"typeVersion": 1
},
{
"id": "a5e00543-dbaa-4e62-afb0-825ebefae3f3",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1480,
720
],
"parameters": {
"jsonSchemaExample": "{\n\t\"caption_title\": \"\",\n\t\"caption_text\": \"\"\n}"
},
"typeVersion": 1.2
},
{
"id": "bb9af9c6-6c81-4e92-a29f-18ab3afbe327",
"name": "Get Info",
"type": "n8n-nodes-base.editImage",
"position": [
1100,
400
],
"parameters": {
"operation": "information"
},
"typeVersion": 1
},
{
"id": "8a0dbd5d-5886-484a-80a0-486f349a9856",
"name": "Resize For AI",
"type": "n8n-nodes-base.editImage",
"position": [
1100,
560
],
"parameters": {
"width": 512,
"height": 512,
"options": [],
"operation": "resize"
},
"typeVersion": 1
},
{
"id": "d29f254a-5fa3-46fa-b153-19dfd8e8c6a7",
"name": "Calculate Positioning",
"type": "n8n-nodes-base.code",
"position": [
2020,
720
],
"parameters": {
"mode": "runOnceForEachItem",
"jsCode": "const { size, output } = $input.item.json;\n\nconst lineHeight = 35;\nconst fontSize = Math.round(size.height / lineHeight);\nconst maxLineLength = Math.round(size.width/fontSize) * 2;\nconst text = `\"${output.caption_title}\". ${output.caption_text}`;\nconst numLinesOccupied = Math.round(text.length / maxLineLength);\n\nconst verticalPadding = size.height * 0.02;\nconst horizontalPadding = size.width * 0.02;\nconst rectPosX = 0;\nconst rectPosY = size.height - (verticalPadding * 2.5) - (numLinesOccupied * fontSize);\nconst textPosX = horizontalPadding;\nconst textPosY = size.height - (numLinesOccupied * fontSize) - (verticalPadding/2);\n\nreturn {\n caption: {\n fontSize,\n maxLineLength,\n numLinesOccupied,\n rectPosX,\n rectPosY,\n textPosX,\n textPosY,\n verticalPadding,\n horizontalPadding,\n }\n}\n"
},
"typeVersion": 2
},
{
"id": "12a7f2d6-8684-48a5-aa41-40a8a4f98c79",
"name": "Apply Caption to Image",
"type": "n8n-nodes-base.editImage",
"position": [
2380,
560
],
"parameters": {
"options": [],
"operation": "multiStep",
"operations": {
"operations": [
{
"color": "=#0000008c",
"operation": "draw",
"endPositionX": "={{ $json.size.width }}",
"endPositionY": "={{ $json.size.height }}",
"startPositionX": "={{ $json.caption.rectPosX }}",
"startPositionY": "={{ $json.caption.rectPosY }}"
},
{
"font": "/usr/share/fonts/truetype/msttcorefonts/Arial.ttf",
"text": "=\"{{ $json.output.caption_title }}\". {{ $json.output.caption_text }}",
"fontSize": "={{ $json.caption.fontSize }}",
"fontColor": "#FFFFFF",
"operation": "text",
"positionX": "={{ $json.caption.textPosX }}",
"positionY": "={{ $json.caption.textPosY }}",
"lineLength": "={{ $json.caption.maxLineLength }}"
}
]
}
},
"typeVersion": 1
},
{
"id": "4d569ec8-04c2-4d21-96e1-86543b26892d",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-120,
80
],
"parameters": {
"width": 423.75,
"height": 431.76353488372104,
"content": "Configuration note: update with your credentials or endpoint.",
"color": "#FFF59D"
},
"typeVersion": 1
},
{
"id": "45d37945-5a7a-42eb-8c8c-5940ea276072",
"name": "Merge Image & Caption",
"type": "n8n-nodes-base.merge",
"position": [
1620,
400
],
"parameters": {
"mode": "combine",
"options": [],
"combineBy": "combineByPosition"
},
"typeVersion": 3
},
{
"id": "53a26842-ad56-4c8d-a59d-4f6d3f9e2407",
"name": "Merge Caption & Positions",
"type": "n8n-nodes-base.merge",
"position": [
2200,
560
],
"parameters": {
"mode": "combine",
"options": [],
"combineBy": "combineByPosition"
},
"typeVersion": 3
},
{
"id": "b6c28913-b16a-4c59-aa49-47e9bb97f86d",
"name": "Get Image",
"type": "n8n-nodes-base.httpRequest",
"position": [
680,
300
],
"parameters": {
"url": "https://images.pexels.com/photos/1267338/pexels-photo-1267338.jpeg?auto=compress&cs=tinysrgb&w=600",
"options": []
},
"typeVersion": 4.2
},
{
"id": "6c25054d-8103-4be9-bea7-6c3dd47f49a3",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
340,
80
],
"parameters": {
"color": "#FFF59D",
"width": 586.25,
"height": 486.25,
"content": "Configuration note: update with your credentials or endpoint."
},
"typeVersion": 1
},
{
"id": "d1b708e2-31c3-4cd1-a353-678bc33d4022",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
960,
140
],
"parameters": {
"color": "#FFF59D",
"width": 888.75,
"height": 783.75,
"content": "Configuration note: update with your credentials or endpoint."
},
"typeVersion": 1
},
{
"id": "36a39871-340f-4c44-90e6-74393b9be324",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1880,
280
],
"parameters": {
"color": "#FFF59D",
"width": 753.75,
"height": 635,
"content": "Configuration note: update with your credentials or endpoint."
},
"typeVersion": 1
},
{
"id": "d175fe97-064e-41da-95fd-b15668c330c4",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
2660,
280
],
"parameters": {
"width": 563.75,
"height": 411.25,
"content": "Configuration note: update with your credentials or endpoint.",
"color": "#FFF59D"
},
"typeVersion": 1
},
{
"id": "23db0c90-45b6-4b85-b017-a52ad5a9ad5b",
"name": "Image Captioning Agent",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1280,
560
],
"parameters": {
"text": "Generate a caption for this image.",
"messages": {
"messageValues": [
{
"message": "=You role is to provide an appropriate image caption for user provided images.\n\nThe individual components of a caption are as follows: who, when, where, context and miscellaneous. For a really good caption, follow this template: who + when + where + context + miscellaneous\n\nGive the caption a punny title."
},
{
"type": "HumanMessagePromptTemplate",
"messageType": "imageBinary"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.4
}
],
"connections": {
"Get Info": {
"main": [
[
{
"node": "Merge Image & Caption",
"type": "main",
"index": 0
}
]
]
},
"Get Image": {
"main": [
[
{
"node": "Resize For AI",
"type": "main",
"index": 0
},
{
"node": "Get Info",
"type": "main",
"index": 0
}
]
]
},
"Resize For AI": {
"main": [
[
{
"node": "Image Captioning Agent",
"type": "main",
"index": 0
}
]
]
},
"Calculate Positioning": {
"main": [
[
{
"node": "Merge Caption & Positions",
"type": "main",
"index": 1
}
]
]
},
"Merge Image & Caption": {
"main": [
[
{
"node": "Calculate Positioning",
"type": "main",
"index": 0
},
{
"node": "Merge Caption & Positions",
"type": "main",
"index": 0
}
]
]
},
"Image Captioning Agent": {
"main": [
[
{
"node": "Merge Image & Caption",
"type": "main",
"index": 1
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Image Captioning Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Image Captioning Agent",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Merge Caption & Positions": {
"main": [
[
{
"node": "Apply Caption to Image",
"type": "main",
"index": 0
}
]
]
},
"When clicking \u2018Test workflow\u2019": {
"main": [
[
{
"node": "Get Image",
"type": "main",
"index": 0
}
]
]
}
},
"n8n_version": "1.5.0"
}Requirements
n8n instance, API credentials for connected services
Tags
#n8n
#automation
#workflow