Claire Vo · 2 min read · Gen AI Tools
Gemini Omni: Clone yourself with AI in under 15 minutes
Read the original on lennysnewsletter.com →
An experimental walkthrough of building an AI avatar using Google Flow and Gemini Omni, showing how to go from a face scan to a complete one-minute hype video in roughly 15 minutes. The episode covers storyboard generation, avatar consistency across scenes, in-browser editing, and common pitfalls like uncanny valley moments.
Key Takeaways
- Quick AI avatar workflow: face scan with Google Flow, then generate a multi-scene video using Gemini Omni.
- AI video tools democratize production for creators with zero video skills.
- AI-assisted storyboard and consistent avatar across multiple scenes.
- Common issues: uncanny valley and emotion or physics misalignment; troubleshooting guidance.
- End-to-end process: stitch scenes in a browser-based editor to publish the finished video.
Excerpt
In this experimental episode, I document my real-time attempt to create an AI avatar of myself using Google Flow and the new Gemini Omni video generation model. I walk through the entire process—from scanning my face with my phone to generating a complete one-minute hype video for the podcast, all in about 15 minutes. Listen or watch on YouTube , Spotify , or Apple Podcasts What you’ll learn: How to create an AI avatar using Google Flow in under five minutes Why video AI tools unlock creative possibilities for people with zero video production skills The step-by-step process of generating…