Hey everyone, I’ve been working on an ambitious automation system that generates AI-driven UGC product videos with custom durations. For now, I’m focusing on the proof of concept (POC) using two 10-second clips (total ~20s). Here’s how the pipeline works 👇 1️⃣ Prepare Inputs A submission form captures the product image. The image is analyzed by GPT-4o. Results are stored in Google Sheets with three main fields: ICP, Product Features, Video Settings (can also be manually filled) 2️⃣ Generate First Video (Video 1) An AI agent creates the video prompt. The prompt is sent to the Kie.ai API (Sora 2 model) for generation (following Nate’s tutorial). Output → Video1. 3️⃣ Transcription Used Whisper API to extract the transcription from Video1. The text is then added to Google Sheets for further processing. 4️⃣ Quality Check (Optional) A Gemini-powered row checks for abnormalities or hallucinations in the generated content. 5️⃣ Extract Persona & Last Frame Used Shotstack API to capture 10 frames from Video1. Each frame is analyzed and scored. The system extracts the clearest persona image and last frame automatically. 6️⃣ Prepare for Video 2 Generation The workflow gathers all necessary data (images, prompts, metadata) to build the second video. 7️⃣ Generate Second Video (Video 2) Using this body for the sora-2-image-to-video endpoint: { "model": "sora-2-image-to-video", "input": { "prompt": "{{ $json.output.replace(/\r?\n|\r/g, ' ').replace(/\"/g, '').replace(/[“”]/g, '') }}", "image_urls": [ "{{ $('Limit2').item.json['Last frame'] }}", "{{ $('Limit2').item.json['Persona frame'] }}", "{{ $('Limit2').item.json['Product Photo'] }}" ], "aspect_ratio": "portrait", "n_frames": "10", "remove_watermark": true } } 🎥 Results Attached below: First video (Video 1) Second continuation video (Video 2) Workflow visual 💬 Looking for Feedback I’d love feedback or suggestions on: - Optimizing prompt/body/strategy suggestions. - Improving continuity and persona consistency between videos

Hi everyone, is there anyone working with long format UGC type videos (1-2 minutes) ? What is the best strategy to stitch clips together with smooth video and audio transitions ?

got a 9–5? you don’t need to quit. You need 3–4 focused hours a day. → 1 hour before work → 2 hours after → weekends = 15+ bonus hours That’s 25 hours/week you can build a real business in that. But only if you cut the noise. → no scrolling → no fake “research” → no 6-hour logo design sessions Instead: → pick 1 skill (lead gen, automation, landing pages) → offer it to real businesses → learn + sell every day → get your first client → stack momentum $10K/month isn’t magic. it’s just a few hours a day—used well. 👇 what’s stopping you from starting tonight?

n8n just dropped a new Guardrails node, and it’s a game-changer for anyone building AI automations. In this video, I break down exactly what guardrails are, why they matter, and how you can use them to keep your workflows safe and reliable. Guardrails help you automatically detect and handle things like personal data, secret keys, malicious URLs, or unsafe content before it ever reaches your AI model. I’ll walk you through each guardrail type, show real examples, and explain when and why you’d want to use them. The best part is that you can set all of this up in n8n with no code, so whether you’re protecting your data or building safer AI systems, this video will show you how to do it step by step.

In this video, I show you how to build a no-code AI system in n8n that automatically creates UGC (user-generated content) ads, from product photos to full video ads. This workflow utilizes Nano Banana, Veo 3.1, and Sora 2 for image and video generation, so all you have to do is upload a product image, write a short description of the features, and tell the system what type of video you want. From there, it does everything for you, automatically generating realistic, on-brand UGC visuals and short-form videos ready to use in your marketing campaigns. This template is completely free and incredibly easy to customize. As these AI image and video models continue to improve, you’ll be able to refine your prompts to get even better, more human-like results over time. You can generate high-quality 10-second videos for as little as $0.15 each, making it one of the most cost-effective ad creation systems available today. GOOGLE SHEET TEMPLATE