This AI Video Went Viral - Here's How To Make It

This AI Video Went Viral - Here's How To Make It

🎙 Matt Wolfe 👥 1.0M 📅 June 12, 2023 ⏱ 15 min 👁 174K 📄 tutorial 🧭 2026-08-28
Available in: English (current) Français

Keywords

Runway Gen-1ElevenLabsDaVinci ResolveAI video editingviral video

Summary

Matt Wolfe demonstrates how to recreate a viral AI-generated video originally posted by Martin Haerlin. The process involves filming a simple selfie video with snapping fingers, then using Runway ML’s Gen-1 tool to transform each segment into different styles (samurai, superhero, pop star, astronaut, Thanos). He splits the video into two parts due to Gen-1’s 15-second limit, generates styled clips using reference images, and then assembles them in DaVinci Resolve, aligning each clip with the snap. He adds voiceovers using ElevenLabs and background music from Motion Array, plus sound effects. He discusses the costs involved, noting that the process consumed his Runway credits and required additional purchases. The final result is a fun demonstration of AI video editing, though he notes the original creator likely generated many more iterations for higher quality. He encourages viewers to try the process and share their results.

143 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides a high practical value for anyone interested in AI video generation, offering a clear, step-by-step tutorial that is easy to follow. The creator demonstrates the entire workflow, from filming to final edit, and openly discusses the limitations and costs, which adds credibility. The argumentation is solid, as he bases his claims on direct experimentation and provides realistic expectations about the quality and effort required. He also compares his result to the original, acknowledging the gap and explaining why, which strengthens the tutorial’s honesty.

95 words

Title / Content Match

The title accurately reflects the content: the video explains how to recreate a viral AI-generated video, providing a step-by-step tutorial.

Quality & Reliability

8/10

The tutorial is practical, transparent about costs and limitations, and based on direct experimentation with the tools. The creator clearly demonstrates each step, acknowledges imperfections, and provides a realistic cost breakdown. The information is reliable for replicating the process, though it relies on the creator's personal experience rather than formal documentation.

Key Moments

Cited Sources

  • Runway Gen-1 — The main tool used for video-to-video style transfer.
  • ElevenLabs — Used for generating voiceovers.
  • Motion Array — Source for background music and sound effects.
  • DaVinci Resolve — Free video editing software used for assembling the final video.
  • Future Tools — Creator's website for discovering AI tools.
  • Future Tools Newsletter — Weekly newsletter for AI news.
  • Future Tools Discord — Community for discussing AI tools.
  • Matt Wolfe's Blog — Personal blog of the creator.
  • Mubert — Used for generating outro music.

Concurring Sources

  • Runway Gen-1 — The tool's official page confirms its video-to-video capabilities.
  • ElevenLabs — The platform's official page confirms its voice generation features.

Contribution & Novelties

The video provides a practical, step-by-step tutorial for recreating a viral AI video, demystifying the process and making it accessible to a general audience. It offers a realistic cost breakdown and highlights the limitations of current tools, which is valuable for anyone considering similar projects.

Pour aller plus loin :

  • Runway Gen-1 — Official page for the tool used, with details on capabilities and pricing.
  • ElevenLabs — Voice generation platform used for the voiceovers.
  • DaVinci Resolve — Free video editing software used in the tutorial.
  • Motion Array — Subscription service for stock music and video assets.
  • AI video generation — Wikipedia article on AI art, which includes video generation context.

110 words

Radar Profile

The radar profile shows high scores in information quantity, quality, and reliability, with a slightly lower technical level. This indicates a well-balanced tutorial that is both informative and trustworthy, though it may not delve into advanced technical details.

Reliability 8/10

💬 Très positif. Sur les 30 commentaires analysés, les spectateurs expriment une forte appréciation pour la clarté du tutoriel, l'approche pédagogique et la transparence sur les coûts, avec des encouragements et des remerciements répétés.