Notes by ReelStack · AI-assistedUpdated 25 October 2026

How To Make Facebook Ads With AI - Step by Step

Automating UGC ad creation through specialized platforms highlights the shift toward scalable, template-driven marketing pipelines for physical products.

Video thumbnail: How To Make Facebook Ads With AI - Step by Step
Original YouTube video

Youri van Hofwegen

Published

Watch the original video ↗

What this lesson covers

Youri van Hofwegen demonstrates how to turn a single product image into multiple high-converting UGC-style Facebook ads using Arcads. The workflow automatically handles scripting, audience pain point research, influencer generation, and video stitching using generative models.

Key takeaways from the creator

AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.

  1. 0:42 ↗

    Use a dedicated platform like Arcads to automate market research, scriptwriting, and multi-angle ad generation from a single product image.

  2. 2:55 ↗

    Generate a reference image of your AI influencer first, as downstream video generation nodes rely on it to preserve character consistency.

  3. 4:31 ↗

    Prompting for multiple ad angles allows the system to generate distinct variations such as pain relief, product demos, and daily routines in one batch.

Workflow outlined in the video

  1. Open Arcads and start a new workflow on a blank canvas.
  2. Upload your product image into the prompt box and enter a natural language description of your desired ad concept.
  3. Run the workflow to automatically generate the reference actor image, script prompts, and UGC video clips.
  4. Review the generated clips and use the stitch node to combine them into final captioned ad variations.

Before you use this workflow

These notes describe the source video at its publication date. Model access, pricing, connectors and interfaces may have changed. Check the original source and the provider’s current documentation before installing an add-on, connecting an account or spending credits.

ReelStack has not independently tested this workflow. Preview one representative shot and check motion, continuity and output quality before applying it to a full production. No result, cost saving or model capability is guaranteed.

How to interpret the numbers

24,921 views captured 25 October 2026. ReelStack recommendation score: 29/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.

Show the calculation
  • 45% performance: 0.96× views vs 12 other channel videos observed at a similar age. View-evidence factor 96% (views / (views + 1,000))
  • 25% freshness: 0/100 with a 14-day half-life
  • 20% momentum: 81 views/day vs 127 channel baseline (6 comparable uploads), with the same view-evidence factor
  • 10% engagement: 3/100; likes + 4× comments, smoothed with a 500-view neutral prior

Read our methodology and limitations →

Powered by ReelStack

Help keep this running

Your tip funds servers, models, and the time it takes to ship new tools faster. Set any amount below — every bit helps.