Create AI social media carousels from Google Sheet and auto-publish with Blotato

🚀 Create Pro-Level Social Media Carousels & Auto-Publish with Blotato ====================================================================== By @nocodehack Who is this for? ---------------- This workflow is built for e-commerce brands, social media managers, marketing agencies, dropshippers, content creators, and automation builders who need to produce professional carousel posts at scale. Perfect for anyone running product marketing, brand campaigns, multi-platform social media, affiliate content, or any business that publishes carousel posts regularly and wants to eliminate design costs entirely. What problem is this workflow solving? / Use case ------------------------------------------------- Creating professional carousel posts is: Slow — designing even one carousel takes 30-60 minutes manually Expensive — Fiverr/Upwork designers charge $50-100 per carousel Inconsistent — AI-generated slides never visually match each other Unscalable — managing multiple brands multiplies every problem Tedious — exporting, uploading, scheduling, and publishing is repetitive busywork This workflow solves: ❌ Manual carousel design (Canva, Photoshop, Figma) ❌ Paying designers per post ❌ AI images that look obviously AI-generated ❌ Visually inconsistent slides that don't match ❌ Manual copywriting for captions and hashtags ❌ Manual uploading and publishing to each platform ❌ Managing multiple brands with different visual identities It turns one Google Sheet row into a fully designed, published carousel — across Instagram, Facebook, and X — for approximately 5 cents. What this workflow does ----------------------- This automation system acts as a complete AI-powered carousel design studio and publishing pipeline. Step-by-step pipeline: Step 1 — Data Pipeline (Google Sheet) Runs on a schedule (configurable interval) Pulls the next unprocessed row from Google Sheets Each row = one carousel (one brand, one product, one post) Marks the row as "Processing" to prevent duplicate execution Checks if product description and images are provided — if missing, auto-scrapes from the product URL using Jina.ai (free, no account needed) Merges all data into one clean payload for the AI Step 2 — AI Creative Direction (Claude) Sends all product data (description, images as base64, brand logo, creative specifications) to Claude via the Anthropic API Claude acts as an executive creative director — not just generating content, but building a complete visual identity first: Color palette (2-3 hex colors) Typography style and hierarchy Lighting direction and mood Signature design element Background texture concept Then generates for each slide: headline, body copy, layout approach, and a detailed 80+ word image prompt A 2000-word system prompt with banned elements list eliminates the generic AI look (no waves, no scattered leaves, no flat backgrounds, no Canva-style templates) Every image prompt ends with a negative prompt / AVOID block — same concept as Stable Diffusion negative prompts, applied to Gemini Output is structured JSON via a parser — no freeform text that could break the pipeline Also generates the Instagram caption and hashtags Step 3 — Image Generation with Visual Consistency Loop This is the core innovation of the workflow Slides are generated sequentially, NOT in parallel — this is critical For slide 1: Gemini generates the image from the prompt + product reference images For slide 2+: The workflow fetches all previously generated slides, converts them to base64, and attaches them as reference images alongside the current prompt The text prompt explicitly instructs: "Match the exact typography, color palette, and lighting from the attached previous slides" This creates a double enforcement system — visual reference + written instruction Result: every slide in the carousel shares the same visual identity without using templates or presets Images are generated via NanoBanana Pro (Gemini image generation API) Each generated slide is uploaded to Blotato