January 22, 2026

Google Gemini to LinkedIn, posts with images ready

Lisa Granqvist Partner Workflow Automation Expert

Get a free AI assessment → ⬇️ Use template

You sit down to “just post on LinkedIn,” and suddenly it’s 45 minutes later. The idea was there, but the writing, formatting, image creation, and upload steps turned into a mini project.

This hits marketing managers hard, because consistency is part of the job. founders feel it when the week gets busy. And if you run a small agency, it’s one more thing that slips when client work piles up. With Gemini LinkedIn automation, one topic becomes a publish-ready post plus a matching image.

Below, you’ll see how the workflow runs in n8n, what you need to connect, and what kind of time you get back once the boring parts are automated.

How This Automation Works

The full n8n workflow, from trigger to final output:

n8n Workflow Template: Google Gemini to LinkedIn, posts with images ready

Click to explore

flowchart LR

    subgraph sg0["On form submission Flow"]
        direction LR
        n0["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/form.svg' width='40' height='40' /></div><br/>On form submission"]
        n1@{ icon: "mdi:swap-vertical", form: "rounded", label: "Mapper", pos: "b", h: 48 }
        n2@{ icon: "mdi:robot", form: "rounded", label: "AI Agent", pos: "b", h: 48 }
        n3@{ icon: "mdi:brain", form: "rounded", label: "Google Gemini Chat Model", pos: "b", h: 48 }
        n4["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/code.svg' width='40' height='40' /></div><br/>Normalizer"]
        n5["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>HTTP Request"]
        n6["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Register Image Upload"]
        n7["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Text to image1"]
        n8["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Upload Image to LinkedIn1"]
        n9["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/code.svg' width='40' height='40' /></div><br/>Convert to binary buffer"]
        n10["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/code.svg' width='40' height='40' /></div><br/>Code"]
        n11@{ icon: "mdi:cog", form: "rounded", label: "Wait", pos: "b", h: 48 }
        n10 --> n11
        n11 --> n5
        n1 --> n2
        n2 --> n4
        n4 --> n7
        n7 --> n6
        n0 --> n1
        n6 --> n9
        n9 --> n8
        n3 -.-> n2
        n8 --> n10
    end

    %% Styling
    classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
    classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
    classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
    classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
    classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
    classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
    classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
    classDef disabled stroke-dasharray: 5 5,opacity: 0.5
    class n0 trigger
    class n2 ai
    class n3 aiModel
    class n5,n6,n7,n8 api
    class n4,n9,n10 code
    classDef customIcon fill:none,stroke:none
    class n0,n4,n5,n6,n7,n8,n9,n10 customIcon

The Problem: LinkedIn Posting Becomes a Multi-Step Chore

Writing a decent LinkedIn post is only part of the work. You also have to turn rough notes into something structured, clean up formatting that looks fine in a doc but weird on LinkedIn, come up with an image that doesn’t feel like stock-photo filler, and then go through the upload process without breaking line spacing or losing hashtags. On a busy week, the “I’ll post later” delay is what kills consistency. And when you do rush it, mistakes show up in public.

The friction compounds. Not because any one step is impossible, but because there are too many of them.

Drafting from scratch for every post makes you second-guess tone, length, and structure.
Manual formatting often turns bullet points and spacing into a messy wall of text.
Finding or designing a relevant image can take about 30 minutes on its own.
Uploading the image, waiting for processing, and publishing becomes a repetitive checklist you repeat every time.

The Solution: Generate the Post and Image, Then Publish Automatically

This workflow turns a single topic submission into a finished LinkedIn post with a custom AI-generated image, then publishes it for you. It starts with a simple form where you drop the topic you want to write about. From there, Google Gemini generates two things in one go: the LinkedIn post copy (with a coherent structure and hashtags) and a separate image prompt that matches the theme. The workflow then calls Google Imagen 4 to create a square, LinkedIn-friendly image, registers an upload session with LinkedIn, converts the image data into the right format, and uploads it. Finally, it adapts the text into LinkedIn-safe formatting, waits briefly so the asset is ready, and publishes the post with the image attached.

The workflow kicks off from your form submission. Gemini produces post text plus an image description, then Imagen 4 creates the visual. LinkedIn’s API handles upload registration, the image is attached, and the post goes live after a short wait.

What You Get: Automation vs. Results

What This Workflow Automates

Results You’ll Get

You submit one topic via a web form and the workflow takes over.
Google Gemini generates LinkedIn-ready copy plus a matching image prompt.
Google Imagen 4 creates a 1:1 professional image automatically.
The workflow uploads the image to LinkedIn and publishes the final post after a short wait.

What used to take about 60 minutes often becomes 5 minutes of input time.
Fewer public formatting mistakes because the text is normalized before posting.
Stronger consistency because you are not blocked by design work.
A repeatable format that keeps your posts on-brand with small prompt tweaks.
Less mental load, which means you post more regularly.

Example: What This Looks Like

Say you publish three LinkedIn posts per week. Manually, a reasonable routine is about 30 minutes to write, 20 minutes to clean up formatting and hashtags, and another 20 minutes to create or find an image, so roughly 70 minutes per post (about 3.5 hours a week). With this workflow, you submit a topic in about 2 minutes, then wait while Gemini and Imagen run (image generation is usually 10–30 seconds, plus upload time). You still may review the output, but the “blank page + design task” part is gone.

What You’ll Need

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
LinkedIn Developer App for OAuth and posting permissions.
Google Gemini API to generate the post and image prompt.
Google Cloud access token (get it from Google Cloud SDK via gcloud auth print-access-token)

Skill level: Intermediate. You’ll be connecting OAuth credentials and pasting API tokens, plus minor prompt edits if you want a specific brand voice.

Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).

How It Works

A topic submission triggers everything. You fill out a form with one topic (for example, “3 mistakes teams make with onboarding emails”). n8n captures it and maps the input into the format the AI agent expects.

Gemini writes the post and plans the image. The content agent asks Google Gemini for structured output, which includes LinkedIn post text plus an image prompt description. A formatting step cleans the response, so you are not stuck fixing JSON quirks or odd line breaks.

Imagen creates the visual and LinkedIn accepts the upload. n8n sends the prompt to Google Imagen 4 (square aspect ratio), then registers an upload with LinkedIn. The workflow converts the returned base64 image into a binary payload and uploads it as an asset.

The post is curated and published. Another formatting step adapts the text into LinkedIn-friendly formatting (so markdown doesn’t show up like raw symbols). After a short wait to ensure the asset is processed, the workflow publishes the post with the image attached.

You can easily modify the tone and formatting rules to match your brand, then publish as a draft-review flow instead of auto-posting based on your needs. See the full implementation guide below for customization options.

Step-by-Step Implementation Guide

Step 1: Configure the Form Trigger

This workflow starts with a form that captures a LinkedIn post topic and maps it into the AI prompt pipeline.

Add and open Form Submission Trigger.
Set Form Title to LinkedIn Post Generator .
In Form Fields, keep the Topic field as required with placeholder Enter prompt here.....
Connect Form Submission Trigger to Map Input Fields to pass the form data downstream.

Tip: The Flowpast Branding sticky note is informational and does not affect execution.

Step 2: Connect Primary Services (AI + LinkedIn)

Set credentials for the AI model and LinkedIn API requests used in the workflow.

Open Gemini Chat Engine and set Model Name to models/gemini-2.5-pro.
Credential Required: Connect your googlePalmApi credentials in Gemini Chat Engine.
Open Generate Image Prompt and verify URL is https://us-central1-aiplatform.googleapis.com/v1/projects/[YOUR_ID]/locations/us-central1/publishers/google/models/imagen-4.0-generate-preview-06-06:predict.
Credential Required: Connect your httpBearerAuth credentials in Generate Image Prompt.
Open Initiate Image Upload and Publish LinkedIn Post.
Credential Required: Connect your httpBearerAuth and linkedInOAuth2Api credentials in both Initiate Image Upload and Publish LinkedIn Post.

⚠️ Common Pitfall: Replace every [YOUR_ID] placeholder in LinkedIn and Vertex AI URLs with your actual project/person IDs, or the API calls will fail.

Step 3: Set Up the AI Content Strategy Chain

The workflow maps the form topic into a structured prompt, then uses the AI agent to generate post content and an image prompt.

In Map Input Fields, add an assignment with Name chatInput and Value ={{ $json.Topic }}.
Open Content Strategy Agent and keep the System Message expression that starts with =I need help creating a professional LinkedIn post for the topic: "{{ $json.chatInput }}".
Ensure Gemini Chat Engine is connected as the language model for Content Strategy Agent (credentials are set on Gemini Chat Engine, not the agent).
Connect Content Strategy Agent to Format Output Data to parse the JSON response into post_content and image_prompt.

Tip: If the AI response includes code fences, Format Output Data strips ```json and ``` before parsing.

Step 4: Configure Image Generation and LinkedIn Asset Upload

This stage generates the image, registers a LinkedIn upload, builds a binary payload, and uploads the asset.

In Generate Image Prompt, set Method to POST and Content Type to raw.
Set Body to the JSON expression that includes "prompt": "{{ $json.image_prompt }}" and "aspectRatio": "1:1".
In Initiate Image Upload, keep URL as https://api.linkedin.com/v2/assets?action=registerUpload and ensure the header X-Restli-Protocol-Version is set to 2.0.0.
Open Build Binary Payload and keep the code that reads from Generate Image Prompt and Format Output Data (no changes required).
In Upload Image Asset, set URL to ={{ $('Initiate Image Upload').item.json.value.uploadMechanism['com.linkedin.digitalmedia.uploading.MediaUploadHttpRequest'].uploadUrl }} and Content Type to binaryData.
In Upload Image Asset, set headers Authorization to Bearer [CONFIGURE_YOUR_TOKEN] and Content-Type to image/png.

⚠️ Common Pitfall: Upload Image Asset does not use credentials—ensure the Authorization header contains a valid LinkedIn token.

Step 5: Adapt Post Text and Publish to LinkedIn

The post text is converted to LinkedIn-friendly formatting, then a short pause allows the asset upload to finalize before publishing.

In Adapt LinkedIn Text, keep the code that converts markdown to LinkedIn-compatible text and outputs linkedin_content.
In Pause for Upload, set Amount to 60 seconds to allow asset processing time.
In Publish LinkedIn Post, keep URL as https://api.linkedin.com/v2/ugcPosts.
Set the Body field to the existing JSON expression, including "text": {{ $json.linkedin_content ? JSON.stringify($json.linkedin_content) : "\"\"" }} and "media": "{{ $('Initiate Image Upload').item.json.value.asset }}".
Confirm the execution flow is linear: Upload Image Asset → Adapt LinkedIn Text → Pause for Upload → Publish LinkedIn Post.

Step 6: Test and Activate Your Workflow

Run a manual test to confirm the form input produces a LinkedIn post with an image.

Click Execute Workflow and submit the Form Submission Trigger with a test Topic.
Verify Format Output Data returns post_content and image_prompt without JSON parsing errors.
Confirm Upload Image Asset succeeds and Adapt LinkedIn Text outputs linkedin_content.
Check LinkedIn for a new published post with the generated image after Pause for Upload completes.
Toggle the workflow Active to enable it for production form submissions.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Common Gotchas

LinkedIn credentials can expire or need specific permissions. If things break, check your LinkedIn Developer App token and the w_member_social scope first.
If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever.

Frequently Asked Questions

How long does it take to set up this Gemini LinkedIn automation?

About an hour if you already have your LinkedIn and Google credentials ready.

Do I need coding skills to automate Gemini LinkedIn automation?

No. You will mostly connect accounts and paste tokens into n8n. The only “code” parts are already in the workflow and usually don’t need changes.

Is n8n free to use for this Gemini LinkedIn automation workflow?

Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in Google Gemini and Google Imagen 4 usage from your Google accounts.

Where can I host n8n to run this automation?

Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.

Can I customize this Gemini LinkedIn automation workflow for draft approval instead of auto-posting?

Yes, but you’ll change one key behavior. Keep the Gemini generation steps the same, then replace the “Publish LinkedIn Post” HTTP request with a draft-saving step (for example, write the final text and asset URL to Google Sheets) and add an approval workflow before publishing. Common tweaks include adjusting the agent prompt for your brand voice, changing the hashtags style, and increasing the Wait duration if LinkedIn assets aren’t ready in time.

Why is my LinkedIn connection failing in this workflow?

Usually it’s expired credentials or missing scopes on your LinkedIn app. Regenerate the token, confirm you included w_member_social, then update the credentials used by the HTTP Request nodes that register the upload and publish the post. If it works sometimes and fails in batches, you may also be hitting LinkedIn rate limits, so spacing out executions helps.

How many posts can this Gemini LinkedIn automation handle?

A lot.

Is this Gemini LinkedIn automation better than using Zapier or Make?

For this use case, n8n is typically a better fit because you’re doing multi-step API work (image generation, upload registration, binary conversion, then publishing). Zapier and Make can do it, but you often end up paying more as the steps and volume grow, and handling binary file uploads can get finicky. n8n also gives you a self-hosting route, which matters if you want unlimited runs without counting every task. If you just want “topic in, draft out” with minimal logic, Zapier or Make can be simpler. If you’re unsure, Talk to an automation expert and we’ll point you to the cleanest option.

Once this is running, LinkedIn stops being a weekly scramble. The workflow handles the repeatable parts, so you can focus on ideas and results.

Need Help Setting This Up?

Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.

Lisa Granqvist

Workflow Automation Expert

Expert in workflow automation and no-code tools.

{
"id": "",
"meta": {
"instanceId": "67a204bce2bdc05e5e4a1ca78ca0646bd5357949209744d88ed5a2768dcd6dc7"
},
"name": "Automated LinkedIn Post Creator",
"tags": [],
"nodes": [
{
"id": "flowpast-topbar-6772",
"name": "Flowpast Branding",
"type": "n8n-nodes-base.stickyNote",
"position": [
10,
30
],
"parameters": {
"color": 7,
"width": 790,
"height": 80,
"content": "## Flowpast.com | Automation Workflow Library\n**\ud83d\udcd6 Full tutorial & setup guide:** flowpast.com"
},
"typeVersion": 1
},
{
"id": "c857bae2-9915-4c76-8171-3847dc610092",
"name": "Form Submission Trigger",
"type": "n8n-nodes-base.formTrigger",
"position": [
700,
150
],
"webhookId": "60f5ee52-0a91-4e25-8e16-14c3a58a5f49",
"parameters": {
"options": [],
"formTitle": "LinkedIn Post Generator ",
"formFields": {
"values": [
{
"fieldLabel": "Topic",
"placeholder": "Enter prompt here....",
"requiredField": true
}
]
}
},
"typeVersion": 2.2
},
{
"id": "b545a052-851c-4bfb-9a4c-6c343d45821d",
"name": "Map Input Fields",
"type": "n8n-nodes-base.set",
"position": [
465,
190
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "694a158d-53fd-425c-9a42-be4288c17ac9",
"name": "chatInput",
"type": "string",
"value": "={{ $json.Topic }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "ddafb2fd-1326-4131-9ef3-7fe19ad00666",
"name": "Content Strategy Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
250,
130
],
"parameters": {
"options": {
"systemMessage": "=I need help creating a professional LinkedIn post for the topic: \"{{ $json.chatInput }}\". The output should include:\n\n1. **LinkedIn Post Content**:\n   - Write an engaging and informative LinkedIn post on the topic \" {{ $json.chatInput }}\".\n   - Start with an attention-grabbing hook that entices readers to read further.\n   - Provide valuable insights or actionable tips related to the topic.\n   - The tone should be professional, clear, and concise, using language that's easy to understand.\n   - End with a call to action (CTA) encouraging the audience to engage, reflect, or share their thoughts.\n   - Include relevant hashtags to increase engagement and visibility on LinkedIn. Make sure these hashtags are specific to the topic and aligned with trending keywords for LinkedIn posts.\n\n2. Image Generation Prompt:\n\nVisual Aesthetic:\nThe image should align with LinkedIn's professional and corporate atmosphere. Make sure it conveys sophistication, modernity, and relevance to the topic. Avoid overly busy designs.\n\nColor Palette:\nStick to corporate tones such as blues, whites, and grays to maintain a professional and clean look. Consider using gradients for depth or subtle contrasts to highlight key elements.\n\nImagery:\n\nFocus on visualizing the topic of the post. For AI in Business, this could involve:\n\nA futuristic office or workspace setting, highlighting cutting-edge technologies.\n\nIcons or symbols that represent data analysis, AI, or automation.\n\nVisuals of humans interacting with AI systems (e.g., robots working alongside humans or using AI tools).\n\nAbstract representations of neural networks or digital data flows.\n\nNo Text Overlay:\n\nDo not include any text in the image, ensuring it remains clean and focuses solely on the visuals.\n\nText overlays or titles are not necessary in this case to keep the professional look intact.\n\nStyle and Tone:\n\nThe design should be minimalist, modern, and sleek. Use a balanced layout with a focus on professional imagery that resonates with business-minded audiences.\n\nAvoid overly complex or distracting backgrounds\u2014keep it clean and visually appealing.\n\nFont Style (if applicable):\n\nIf any text were used in future visuals or branding (though none should appear in this image), use clean, modern fonts like Helvetica, Arial, or Roboto\u2014sans-serif fonts that are readable and professional.\n\nimage prompt can be like this short and simple\nA modern co-working space where AI assistants and human employees brainstorm around a digital whiteboard. The scene shows innovation and teamwork, with a multicultural group, smart gadgets, and subtle futuristic elements. Warm natural lighting and a balanced, professional layout ideal for a LinkedIn audience.\n the JSON output would look like this:\n{\n  \"post_content\": {\n    \"text\": \"The Future of AI in Business: How It is Transforming Industries \ud83d\ude80\\n\\nAI in Business is no longer just a buzzword; it's revolutionizing the way businesses operate today. From improving efficiency to driving innovation, AI is an essential tool for modern companies.\\n\\nHere are some key insights on how AI in Business is shaping the future of industries:\\n1. Enhanced Data Analytics: AI helps businesses make data-driven decisions with greater accuracy.\\n2. Automation of Tasks: AI is automating repetitive tasks, improving operational efficiency.\\n3. Personalized Experiences: AI is enabling personalized customer experiences in real-time.\\n\\nIs your business ready to embrace AI in Business? Let's discuss how it can help drive growth and innovation.\\n\\n#AIinBusiness #Innovation #FutureOfWork #BusinessGrowth #TechnologyTrends #DigitalTransformation\"\n  },\n  \"image_prompt\": {\n    \"description\": \"Create an image for a LinkedIn post on the topic of AI in Business. The image should:\\n- Feature modern, sleek visuals that align with the corporate tone of LinkedIn.\\n- Visualize AI in Business through elements like a futuristic office, AI-powered systems, or human-robot collaboration.\\n- Use a professional color palette like blues, whites, and grays.\\n- The optional text overlay (if relevant) could be something like 'The Future of AI in Business' or 'Driving Innovation with AI'.\\n- The design should use clean, modern fonts that are easily readable and match the professional style of LinkedIn posts.\"\n  }\n}\n"
}
},
"typeVersion": 2
},
{
"id": "6dd0d0ed-abe7-4508-b7cc-ff98a7d2000f",
"name": "Gemini Chat Engine",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
270,
320
],
"parameters": {
"options": [],
"modelName": "models/gemini-2.5-pro"
},
"credentials": {
"googlePalmApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "33a57e05-34f6-46ab-bb86-47f09a2e3a80",
"name": "Format Output Data",
"type": "n8n-nodes-base.code",
"position": [
10,
155
],
"parameters": {
"jsCode": "const input = $input.first().json.output\n\nconst cleanedInput = input.replace(/```json|```/g, '').trim();\n\n// Parse the cleaned JSON\nconst parsedOutput = JSON.parse(cleanedInput);\n\n// Extract the `post_content.text` and `image_prompt.description` details\nconst postContent = parsedOutput.post_content.text;\nconst imagePrompt = parsedOutput.image_prompt.description;\n\n// Prepare the final output in the desired JSON structure\nreturn {\n  post_content: postContent,\n  image_prompt: imagePrompt\n};"
},
"typeVersion": 2
},
{
"id": "ec7cc327-dd4d-45bd-b05e-92cff72b2452",
"name": "Generate Image Prompt",
"type": "n8n-nodes-base.httpRequest",
"position": [
35,
435
],
"parameters": {
"url": "https://us-central1-aiplatform.googleapis.com/v1/projects/[YOUR_ID]/locations/us-central1/publishers/google/models/imagen-4.0-generate-preview-06-06:predict",
"body": "={\n \"endpoint\": \"projects/[YOUR_ID]/locations/us-central1/publishers/google/models/imagen-4.0-generate-preview-06-06\",\n \"instances\": [\n {\n \"prompt\": \"{{ $json.image_prompt }}\"\n }\n ],\n \"parameters\": {\n \"aspectRatio\": \"1:1\",\n \"sampleCount\": 1,\n \"negativePrompt\": \"\",\n \"enhancePrompt\": false,\n \"personGeneration\": \"allow_all\",\n \"safetySetting\": \"block_few\",\n \"addWatermark\": true,\n \"includeRaiReason\": true,\n \"language\": \"auto\"\n }\n}",
"method": "POST",
"options": [],
"sendBody": true,
"contentType": "raw",
"authentication": "genericCredentialType",
"rawContentType": "application/json",
"genericAuthType": "httpBearerAuth"
},
"credentials": {
"httpBearerAuth": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "bf60b9f5-fe3a-465c-81ea-c1a393924362",
"name": "Initiate Image Upload",
"type": "n8n-nodes-base.httpRequest",
"position": [
200,
460
],
"parameters": {
"url": "https://api.linkedin.com/v2/assets?action=registerUpload",
"body": "={\n  \"registerUploadRequest\": {\n    \"recipes\": [\n      \"urn:li:digitalmediaRecipe:feedshare-image\"\n    ],\n    \"owner\": \"urn:li:person:[YOUR_ID]\",\n    \"serviceRelationships\": [\n      {\n        \"relationshipType\": \"OWNER\",\n        \"identifier\": \"urn:li:userGeneratedContent\"\n      }\n    ],\n    \"supportedUploadMechanism\": [\n      \"SYNCHRONOUS_UPLOAD\"\n    ]\n  }\n}",
"method": "POST",
"options": [],
"sendBody": true,
"contentType": "raw",
"sendHeaders": true,
"authentication": "genericCredentialType",
"rawContentType": "application/json",
"genericAuthType": "httpBearerAuth",
"headerParameters": {
"parameters": [
{
"name": "X-Restli-Protocol-Version",
"value": "2.0.0"
}
]
}
},
"credentials": {
"httpBearerAuth": {
"id": "credential-id",
"name": ""
},
"linkedInOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4
},
{
"id": "da0925bc-93f5-41bb-ba33-a0c988736b3a",
"name": "Build Binary Payload",
"type": "n8n-nodes-base.code",
"position": [
405,
425
],
"parameters": {
"jsCode": "const base64 = $('Generate Image Prompt').first().json.predictions[0].bytesBase64Encoded;\nconst uploadUrl = $input.first().json.value.uploadMechanism['com.linkedin.digitalmedia.uploading.MediaUploadHttpRequest'].uploadUrl;\nconst asset = $input.first().json.value.asset;\nconst post_content = $('Format Output Data').first().json.post_content || '';\n\n// Validate input fields\nif (!base64 || !uploadUrl || !asset) {\n  throw new Error(\"Missing one of: decoded_image_buffer, uploadUrl, or asset.\");\n}\n\n// Convert base64 string to binary buffer\nconst buffer = Buffer.from(base64, 'base64');\n\nreturn [{\n  binary: {\n    data: {\n      data: buffer,\n      mimeType: 'image/png', // or 'image/jpeg' if needed\n      fileName: 'image.png'\n    }\n  },\n  json: {\n    uploadUrl,\n    asset,\n    post_content\n  }\n}];\n"
},
"typeVersion": 2
},
{
"id": "a5980d83-bd72-4db4-b902-a9876781eea1",
"name": "Upload Image Asset",
"type": "n8n-nodes-base.httpRequest",
"position": [
690,
410
],
"parameters": {
"url": "={{ $('Initiate Image Upload').item.json.value.uploadMechanism['com.linkedin.digitalmedia.uploading.MediaUploadHttpRequest'].uploadUrl }}",
"method": "PUT",
"options": [],
"sendBody": true,
"contentType": "binaryData",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "Bearer [CONFIGURE_YOUR_TOKEN]"
},
{
"name": "Content-Type",
"value": "image/png"
}
]
},
"inputDataFieldName": "data"
},
"typeVersion": 4
},
{
"id": "2f0be0b9-50a2-4835-bcfc-c844d85d3cae",
"name": "Adapt LinkedIn Text",
"type": "n8n-nodes-base.code",
"position": [
645,
680
],
"parameters": {
"jsCode": "// n8n Code Node: Convert Markdown to LinkedIn Format\n// This code processes markdown content from a specific field and converts it to LinkedIn-compatible format\n\n// Get the markdown content from the specific field\nlet markdownContent = $('Build Binary Payload').first().json.post_content || '';\n  \n  // Function to convert markdown to LinkedIn format\n  function convertMarkdownToLinkedIn(content) {\n    let linkedinContent = content;\n    \n    // 1. Handle bold text: **text** or __text__ -> text (LinkedIn doesn't support markdown bold)\n    // But we can use Unicode bold characters or just keep it as regular text\n    linkedinContent = linkedinContent.replace(/\\*\\*(.*?)\\*\\*/g, '$1');\n    linkedinContent = linkedinContent.replace(/__(.*?)__/g, '$1');\n    \n    // 2. Handle italic text: *text* or _text_ -> text\n    linkedinContent = linkedinContent.replace(/\\*(.*?)\\*/g, '$1');\n    linkedinContent = linkedinContent.replace(/_(.*?)_/g, '$1');\n    \n    // 3. Handle numbered lists: convert 1\ufe0f\u20e3, 2\ufe0f\u20e3, 3\ufe0f\u20e3 format or regular numbered lists\n    // Keep emoji numbers as they are, but handle regular numbered lists\n    linkedinContent = linkedinContent.replace(/^\\d+\\.\\s/gm, '\u2022 ');\n    \n    // 4. Handle bullet points: convert - or * to \u2022\n    linkedinContent = linkedinContent.replace(/^[\\-\\*]\\s/gm, '\u2022 ');\n    \n    // 5. Handle line breaks: convert \\n to actual line breaks\n    linkedinContent = linkedinContent.replace(/\\\\n/g, '\\n');\n    \n    // 6. Handle headers: remove # symbols but keep the text prominent\n    linkedinContent = linkedinContent.replace(/^#{1,6}\\s/gm, '');\n    \n    // 7. Handle links: [text](url) -> text (url) or just text\n    linkedinContent = linkedinContent.replace(/\\[([^\\]]+)\\]\\(([^\\)]+)\\)/g, '$1 ($2)');\n    \n    // 8. Handle code blocks: remove ``` or ` formatting\n    linkedinContent = linkedinContent.replace(/```[\\s\\S]*?```/g, (match) => {\n      return match.replace(/```/g, '');\n    });\n    linkedinContent = linkedinContent.replace(/`([^`]+)`/g, '$1');\n    \n    // 9. Clean up excessive line breaks (more than 2 consecutive)\n    linkedinContent = linkedinContent.replace(/\\n{3,}/g, '\\n\\n');\n    \n    // 10. Trim whitespace from start and end\n    linkedinContent = linkedinContent.trim();\n    \n    // 11. Handle special LinkedIn formatting\n    // LinkedIn supports emojis, so keep them as they are\n    // LinkedIn supports line breaks, so maintain paragraph structure\n    \n    return linkedinContent;\n  }\n  \n  // Function to add LinkedIn-specific enhancements\n  function enhanceForLinkedIn(content) {\n    let enhanced = content;\n    \n    // Add extra line break before emoji bullets for better readability\n    enhanced = enhanced.replace(/([.!?])\\s*([1-9]\ufe0f\u20e3)/g, '$1\\n\\n$2');\n    \n    // Ensure proper spacing around key sections\n    enhanced = enhanced.replace(/(:)\\n\\n([1-9]\ufe0f\u20e3)/g, '$1\\n\\n$2');\n    \n    // Handle hashtag formatting - ensure they're on a new line\n    const hashtagPattern = /#\\w+/g;\n    const hashtags = enhanced.match(hashtagPattern);\n    \n    if (hashtags) {\n      // Remove hashtags from content\n      enhanced = enhanced.replace(hashtagPattern, '').trim();\n      \n      // Add hashtags at the end with proper spacing\n      enhanced += '\\n\\n' + hashtags.join(' ');\n    }\n    \n    return enhanced;\n  }\n  \n// Process the content\nlet processedContent = convertMarkdownToLinkedIn(markdownContent);\nprocessedContent = enhanceForLinkedIn(processedContent);\n\n// Return the single processed item\nreturn {\n  json: {\n    original_content: markdownContent,\n    linkedin_content: processedContent,\n    processed_at: new Date().toISOString(),\n    character_count: processedContent.length\n  }\n};\n\n/* \nUSAGE INSTRUCTIONS:\n1. Add this code to an n8n Code Node\n2. Make sure you have a previous node named \"Build Binary Payload\" \n3. The code will read from the \"post_content\" field of that node\n4. The output will include:\n   - original_content: The original markdown content\n   - linkedin_content: The processed LinkedIn-ready content\n   - processed_at: Timestamp of processing\n   - character_count: Length of the processed content\n\nEXAMPLE INPUT from \"Build Binary Payload\" node:\n{\n  \"post_content\": \"Forget just asking AI questions. The next evolution is here: AI agents that *take action*. \ud83e\udd16\\\\n\\\\nWe're moving beyond conversational AI...\"\n}\n\nEXAMPLE OUTPUT:\n{\n  \"original_content\": \"Forget just asking AI questions...\",\n  \"linkedin_content\": \"Forget just asking AI questions. The next evolution is here: AI agents that take action. \ud83e\udd16\\n\\nWe're moving beyond conversational AI...\",\n  \"processed_at\": \"2024-01-15T10:30:00.000Z\",\n  \"character_count\": 1250\n}\n*/"
},
"typeVersion": 2
},
{
"id": "47e5f253-8096-4afd-ba9e-e5db91199aa9",
"name": "Pause for Upload",
"type": "n8n-nodes-base.wait",
"position": [
460,
655
],
"webhookId": "931a20ed-0390-41e9-8a7e-ac68588c4a29",
"parameters": {
"amount": 60
},
"typeVersion": 1.1
},
{
"id": "2f088968-5974-4d5a-ba92-c5246f7300d0",
"name": "Publish LinkedIn Post",
"type": "n8n-nodes-base.httpRequest",
"position": [
245,
665
],
"parameters": {
"url": "https://api.linkedin.com/v2/ugcPosts",
"body": "={\n  \"author\": \"urn:li:person:[YOUR_ID]\",\n  \"lifecycleState\": \"PUBLISHED\",\n  \"specificContent\": {\n    \"com.linkedin.ugc.ShareContent\": {\n      \"shareCommentary\": {\n        \"text\": {{ $json.linkedin_content ? JSON.stringify($json.linkedin_content) : \"\\\"\\\"\"}}\n      },\n      \"shareMediaCategory\": \"IMAGE\",\n      \"media\": [\n        {\n          \"media\": \"{{ $('Initiate Image Upload').item.json.value.asset }}\",\n          \"status\": \"READY\",\n          \"thumbnails\": []\n        }\n      ]\n    }\n  },\n  \"visibility\": {\n    \"com.linkedin.ugc.MemberNetworkVisibility\": \"PUBLIC\"\n  }\n}",
"method": "POST",
"options": [],
"sendBody": true,
"contentType": "raw",
"sendHeaders": true,
"authentication": "genericCredentialType",
"rawContentType": "=application/json",
"genericAuthType": "httpBearerAuth",
"headerParameters": {
"parameters": [
{
"name": "X-Restli-Protocol-Version",
"value": "2.0.0"
},
{
"name": "Content-Type",
"value": "application/json"
}
]
}
},
"credentials": {
"httpBearerAuth": {
"id": "credential-id",
"name": ""
},
"linkedInOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2
}
],
"active": false,
"pinData": [],
"settings": {
"executionOrder": "v1"
},
"versionId": "",
"connections": {
"Adapt LinkedIn Text": {
"main": [
[
{
"node": "Pause for Upload",
"type": "main",
"index": 0
}
]
]
},
"Pause for Upload": {
"main": [
[
{
"node": "Publish LinkedIn Post",
"type": "main",
"index": 0
}
]
]
},
"Map Input Fields": {
"main": [
[
{
"node": "Content Strategy Agent",
"type": "main",
"index": 0
}
]
]
},
"Content Strategy Agent": {
"main": [
[
{
"node": "Format Output Data",
"type": "main",
"index": 0
}
]
]
},
"Format Output Data": {
"main": [
[
{
"node": "Generate Image Prompt",
"type": "main",
"index": 0
}
]
]
},
"Generate Image Prompt": {
"main": [
[
{
"node": "Initiate Image Upload",
"type": "main",
"index": 0
}
]
]
},
"Form Submission Trigger": {
"main": [
[
{
"node": "Map Input Fields",
"type": "main",
"index": 0
}
]
]
},
"Initiate Image Upload": {
"main": [
[
{
"node": "Build Binary Payload",
"type": "main",
"index": 0
}
]
]
},
"Build Binary Payload": {
"main": [
[
{
"node": "Upload Image Asset",
"type": "main",
"index": 0
}
]
]
},
"Gemini Chat Engine": {
"ai_languageModel": [
[
{
"node": "Content Strategy Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Upload Image Asset": {
"main": [
[
{
"node": "Adapt LinkedIn Text",
"type": "main",
"index": 0
}
]
]
}
}
}