Generate & publish social media content with Gemini, Kie.ai, and Late API

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

This workflow automates end to end social media publishing powered by Late API . It generates text content with Google Gemini , creates branded visuals with Kie.ai , uploads media to Late , and pub...

Best for

Social Media automation workflows
Multimodal AI automation workflows
advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.if, n8n-nodes-base.httprequest, n8n-nodes-base.code, n8n-nodes-base.respondtowebhook, n8n-nodes-base.manualtrigger, n8n-nodes-base.wait, n8n-nodes-base.set, n8n-nodes-base.merge

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Adrian.

Original n8n.io source

1.1 Workflow description

Title: Generate & publish social media content with Gemini, Kie.ai, and Late API
Workflow name: Generate & publish social media content with Gemini, Kie.ai, and Late API

📘 Overview

This workflow automates end-to-end social media publishing powered by Late API.
It generates text content with Google Gemini, creates branded visuals with Kie.ai, uploads media to Late, and publishes across multiple platforms (Facebook, Instagram, LinkedIn, TikTok).

It’s a production-ready automation for marketing teams who want to save hours of work by letting AI handle both copywriting and design — all inside n8n.

⚙️ How it works

Generate text content → Google Gemini produces platform-optimized copy (tone & length adapted to each network).
Generate visuals → Kie.ai Seedream v4 creates branded 1080x1080 images.
Upload to Late → media is stored using Late’s upload API (small & large file handling).
Publish → posts are created via Late API on enabled platforms with correct { platform, accountId } mapping.
Notify → success logs are sent via Slack, Discord, Email, and Webhook.

🛠 Setup Steps

Time to setup: ~10–15 minutes
Steps:
1. Add your API keys in n8n Credentials:
  - Google Gemini API (PaLM)
  - Kie.ai (Seedream)
  - Late API
2. Insert your Account IDs (Facebook, Instagram, LinkedIn, TikTok) into the Default Settings node.
3. Choose which platforms to enable (ENABLE_FACEBOOK, ENABLE_INSTAGRAM, etc.).
4. Set your Business Type and Content Topic (e.g., “a tech company” / “new product launch”).
5. Execute the workflow.

📝 Notes

Sticky Notes are included in the workflow to guide each section: Overview, Prerequisites, Default Settings, Content Generation, Image Generation, Media Upload, Publishing Logic, Notifications, Error Handling.
All API keys are handled via Credentials (no hardcoding).
Fallback content is included in case Gemini fails to parse.
Large image files (>4MB) are handled with Late’s multipart upload flow.

💸 Cost per Flow (Estimated)

Late API: $0.00 within Free/Unlimited plans, or ≈ $0.11/post on Build plan ($13/120 posts).
Google Gemini: ~$0.0001–$0.0004 per post (≈200 tokens in/out).
Kie.ai (Seedream): ≈ $0.01–$0.02 per generated image.

➡️ Total: ~$0.01 – $0.12 per post, depending mainly on your Late plan & Kie.ai credits.

🎯 Use cases

Marketing teams automating cross-platform campaigns.
Solo founders posting content daily without design/copy effort.
Agencies scaling social media management with AI + automation.

📢 Credits

Built by Adrian (RoboMarketing) for the n8n Arena Challenge – September 2025.
Powered by:

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - Check Enabled Platforms

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.1

Block 2 - Gemini - Generate Content

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 3 - Parse & Filter Platforms

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 4 - Kie.ai - Generate Image

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 5 - Kie.ai - Obtain Image

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 6 - Prepare data

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 7 - HTTP Request for content-length

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 8 - IF – „Is Large?”

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 9 - HTTP Request for files ≤ ~4 MB

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 10 - LATE – Init Upload files > 4MB

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 11 - Late - Upload Media files <=4MB

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 12 - Download Large (GET)

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 13 - Upload to Storage (PUT)

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 14 - Success Notification & Logging

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 15 - Respond to Webhook

Type / Role: n8n-nodes-base.respondToWebhook - respondToWebhook
Config choices: Version 1.4

Block 16 - When clicking ‘Execute workflow’

Type / Role: n8n-nodes-base.manualTrigger - manualTrigger
Config choices: Version 1

Block 17 - Wait 30s

Type / Role: n8n-nodes-base.wait - wait
Config choices: Version 1.1

Block 18 - Default Settings

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 19 - Late Create Post Facebook

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 20 - IF Facebook

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 21 - IF Instagram

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 22 - IF LinkedIn

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 23 - IF TikTok

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 24 - Late Create Post Instagram

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Showing the first 24 of 43 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow	Generate & publish social media content with Gemini, Kie.ai, and Late API
Complexity	advanced
Nodes	43
Categories	Social Media, Multimodal AI
Author	Adrian
Published	26 Sept 2025

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/8965/8965.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source Social Media workflows Multimodal AI workflows

Frequently asked questions

What does Generate & publish social media content with Gemini, Kie.ai, and Late API do?

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Social Media, Multimodal AI use case.

Adrian

2 workflows

Nodes

n8n-nodes-base.if n8n-nodes-base.httprequest n8n-nodes-base.code n8n-nodes-base.respondtowebhook n8n-nodes-base.manualtrigger n8n-nodes-base.wait n8n-nodes-base.set n8n-nodes-base.merge

Complexity

advanced

Published 26 Sept 2025

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/8965/8965.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Promote YouTube uploads to social channels with DeepSeek and Posta

## Quick overview This workflow fetches the latest video from a YouTube channel feed, generates platform-specific promo captions with DeepSeek, and creates draft promotion posts in Posta for active social media accounts. You can automatically promote your videos to all your social media. Add a "publish" at the end for auto-post. ## How it works 1. Runs manually when you click “Execute workflow”. 2. Fetches your YouTube channel RSS feed over HTTP, parses the XML, and extracts the latest video’s title, description, thumbnail URL, and link. 3. Downloads the video thumbnail and uploads it to Posta to create a reusable media asset. 4. Retrieves your social accounts from Posta, keeps only active accounts, and de-duplicates them to one account per platform. 5. Combines the latest video data with each target platform and asks DeepSeek (via an n8n LangChain LLM chain) to write a tailored promotional caption per platform. 6. Tags each generated caption with its platform and merges it back to the matching Posta social account. 7. Creates a draft Posta post per selected account, attaching the uploaded thumbnail and the platform-specific caption and video link. 8. (Optional) Add a "publish a post" at the end to automatically post to the social media channels (If you are feeling brave and trust the LLM), ## Setup 1. Add a Posta API credential and select it in the Posta nodes that list accounts, upload media, and create posts. 2. Add a DeepSeek API credential and select it in the DeepSeek Chat Model node. 3. Update the YouTube channel feed URL (channel_id) in the HTTP request that downloads the YouTube feed. 4. Review your Posta social accounts to ensure the intended accounts are marked active and have the correct platform values for de-duplication. ## Additional info Video explanation: https://youtu.be/tTWaYb71YyA

View

Post scheduled Threads updates from Google Sheets with error tracking

## Quick overview This workflow runs hourly to read the next pending post from Google Sheets, publishes it to Threads via the Threads Graph API, and then updates the sheet with published or failed status plus timestamps and error details. ## How it works 1. Runs every hour on a schedule. 2. Reads the first row in Google Sheets where the status column equals pending. 3. Retrieves the authenticated Threads account’s user ID from the Threads Graph API. 4. Creates a Threads text post container using the content from the pending Google Sheets row. 5. Publishes the post to Threads and updates the same Google Sheets row as published with posted_at and updated_at timestamps. 6. If any Threads API call fails, records the error message and marks the corresponding Google Sheets row as failed with an updated_at timestamp. ## Setup 1. Create a Meta app and generate a Threads access token, then add it to an HTTP Header Auth credential used for the Threads Graph API requests. 2. Set up a Google Sheets Service Account credential in n8n and share your target spreadsheet with the service account email. 3. Replace the placeholder Google Sheet ID in all Google Sheets nodes and confirm the sheet name is Sheet1 (or update it to match your sheet). 4. Ensure your sheet has the required columns (row_number, content, status, posted_at, updated_at, error_message) and set status to pending for posts you want published.

View

Send a daily product newsletter with Google Sheets and Gmail

## Quick Overview This workflow runs daily at 08:00, pulls products scheduled for today from Google Sheets, generates an HTML newsletter email, and sends it to each subscriber via Gmail. ## How it works 1. Runs every day at 08:00 on a schedule. 2. Reads all rows from the `newsletter_products` sheet in Google Sheets. 3. Keeps only products whose `send_date` matches today’s date and stops if none are found. 4. Builds an HTML email and subject line containing a card for each product (image, description, and optional referral link). 5. Reads the subscriber list from the `newsletter_recipients` sheet in Google Sheets. 6. Sends the generated newsletter to each recipient individually using Gmail. ## Setup 1. Create or copy a Google Sheets document with `newsletter_products` (including a `send_date` column) and `newsletter_recipients` (including an `email` column). 2. Add a Google Sheets OAuth2 credential in n8n and paste your Google Sheet ID into the Config step. 3. Add a Gmail OAuth2 credential and confirm the sender mailbox to use for sending the newsletter. 4. Add products and recipients to the sheet, run a test execution, and adjust the schedule/timezone if needed before activating.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

Generate & publish social media content with Gemini, Kie.ai, and Late API

Workflow preview

Important notice

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

📘 Overview

⚙️ How it works

🛠 Setup Steps

📝 Notes

💸 Cost per Flow (Estimated)

🎯 Use cases

📢 Credits

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - Check Enabled Platforms

Block 2 - Gemini - Generate Content

Block 3 - Parse & Filter Platforms

Block 4 - Kie.ai - Generate Image

Block 5 - Kie.ai - Obtain Image

Block 6 - Prepare data

Block 7 - HTTP Request for content-length

Block 8 - IF – „Is Large?”

Block 9 - HTTP Request for files ≤ ~4 MB

Block 10 - LATE – Init Upload files > 4MB

Block 11 - Late - Upload Media files <=4MB

Block 12 - Download Large (GET)

Block 13 - Upload to Storage (PUT)

Block 14 - Success Notification & Logging

Block 15 - Respond to Webhook

Block 16 - When clicking ‘Execute workflow’

Block 17 - Wait 30s

Block 18 - Default Settings

Block 19 - Late Create Post Facebook

Block 20 - IF Facebook

Block 21 - IF Instagram

Block 22 - IF LinkedIn

Block 23 - IF TikTok

Block 24 - Late Create Post Instagram

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions