Templates / Auto-Translate & Recreate TikTok Carousels with Gemini Vision & Midjourney

Auto-Translate & Recreate TikTok Carousels with Gemini Vision & Midjourney

Needs changes

by Xavier Tai ✓ · 372 views · created 2025-10-06 · Content Creation, Multimodal AI

Needs changes. This template uses 1 thing(s) that n8n 3.0 removes: Convert to/from binary data. 1 breaking item(s) found. Static check, last run 2026-10-19.

What this workflow does

This AI workflow has 15 nodes and runs on a schedule (every day). Along the way it connects Google Gemini, OpenAI Chat Model, Google Sheets and Gmail and 1 more. It also calls tiktok.com and api.midjourney.com over HTTP.

How it runs

Trigger: On a schedule (every day).

  1. Fetch TikTok RSS Feed (HTTP Request): calls tiktok.com
  2. Parse RSS Feed (Convert to/from binary data): uses Convert to/from binary data
  3. Filter: Only 3-Image Posts (If): checks a condition and branches into true / false
  4. Split Images (Split Out): splits a list into separate items
  5. Download Image (HTTP Request): calls an HTTP API
  6. Extract Text & Layout (Gemini Vision) (Google Gemini): analyze (image)
  7. Translate to English (OpenAI): uses OpenAI
  8. Create Midjourney Prompt (AI Agent): runs an AI agent, with model: OpenAI GPT-
  9. Generate New Image (Midjourney) (HTTP Request): calls api.midjourney.com (POST)
  10. Wait: pauses until webhook

…plus 3 more steps. See the full node list below.

Services it uses

Google GeminiOpenAI Chat ModelGoogle SheetsGmailOpenAI

HTTP calls to: tiktok.com, api.midjourney.com

Before you upgrade to n8n 3.0

1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:

  • Convert to/from binary data in Parse RSS Feed: replace with Convert to File or Extract from File.

Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).

Removed in 3.0Replace with
Convert to/from binary data
Parse RSS Feed
Convert to File or Extract from File

Nodes used (13)

From the author

🎨 TikTok Carousel Replicator & Translator An end-to-end automation system that monitors TikTok accounts for new 3-image carousel posts, extracts text overlays and visual layouts using AI vision analysis, translates content into English, and automatically…

Excerpt from Xavier Tai's description on n8n.io.

View the original on n8n.io → Check your own copy

Get the weekly “what broke” email

New templates, newly broken ones, and n8n release changes. One short email a week.

Form not loading? Subscribe here.