The Automated ChatGPT Slideshow System Behind 11M Followers
Mastering character consistency and multi-image automated pipelines gives creators a lightweight approach to fast audience growth and rapid concept validation.
What this lesson covers
Adrian outlines a strategy for using ChatGPT and Claude to automate viral multi-slide social media posts on Instagram and Facebook. He highlights visual pitfalls to avoid, such as recognizable default AI typography and image degradation from over-iteration.
Key takeaways from the creator
AI-extracted notes, not independently verified product claims. Timestamp links let you check each point in the original video.
- 01:24 ↗
GPT Image 2 enables creators to generate realistic human figures and clean infographic slides for social feeds.
- 03:13 ↗
Recursively re-prompting generated images degrades visual sharpness and leads to blurry, low-quality slide outputs.
- 05:43 ↗
Re-creating proven viral slideshow concepts with a custom recurring AI character yields higher engagement than unproven ideas.
- 06:33 ↗
Prompting Claude to generate structured image prompts allows creators to execute entire slide decks directly within ChatGPT.
Workflow outlined in the video
- Research high-performing multi-slide posts in target social niches to analyze structure and pacing.
- Use Claude to re-concept winning posts and draft individual slide prompts incorporating a consistent custom character.
- Generate images inside ChatGPT while requesting clean typography to avoid default AI font artifacts.
- Assemble and inspect slide aspect ratios before publishing across target channels.
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.
Explore the tools
How to interpret the numbers
1,451 views captured 27 September 2026. ReelStack recommendation score: 31/100. Formula: radar-v5. This is ReelStack’s calculation, not a YouTube rating or a measure of factual accuracy.
Show the calculation
- 45% performance: 0.73× views vs 4 other channel videos observed at a similar age. View-evidence factor 59% (views / (views + 1,000))
- 25% freshness: 20/100 with a 14-day half-life
- 20% momentum: 6 views/day vs 3 channel baseline (3 comparable uploads), with the same view-evidence factor
- 10% engagement: 63/100; likes + 4× comments, smoothed with a 500-view neutral prior