I cloned myself with Gemini Omni in 15 minutes (and it's terrifyingly good)

2026-06-03 · Source: How I AI · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation · Depth: Novice, long

Summary

Claire Ho successfully created a minute-long AI-generated hype video for her "How I AI" podcast in approximately 15 minutes using Google Flow and the Gemini Omni video generation model. The process involved generating a personal AI avatar by taking photos, then leveraging Flow's creative suite to brainstorm a seven-frame storyboard. She subsequently generated individual video scenes featuring her avatar, noting the tool's ability to incorporate background elements from her initial photos. Despite some "uncanny valley" moments and character inconsistencies, such as altered hair length and changing backgrounds, Ho was impressed by the speed and minimal effort required, achieving a "50% there" result that she deemed tweet-worthy. The entire workflow, from avatar creation to video stitching in the in-browser editor, demonstrated the accessibility of multimodal generative AI for solo content production.

Key takeaway

For content creators or marketing professionals looking to rapidly produce personalized video content, Google Flow with Gemini Omni offers a compelling, low-effort solution. While you may encounter "uncanny valley" effects or minor inconsistencies in your AI avatar, the ability to generate a minute-long video in under 15 minutes, including storyboarding and editing, significantly lowers the barrier to entry for video production. Consider experimenting with this tool to quickly prototype video concepts or create engaging social media assets, understanding that some refinement may be needed for perfect consistency.

Key insights

AI video generation tools like Google Flow with Gemini Omni enable rapid, low-effort avatar-based content creation.

Principles

• Multimodal AI democratizes video production.
• Avatar generation can incorporate real-world context.
• Early video models show character inconsistencies.

Method

Create an avatar by scanning a QR code and taking photos. Use the AI's creative suite to brainstorm a storyboard. Generate individual video scenes with the avatar, then stitch them in an in-browser editor.

In practice

• Experiment with Google Flow for quick video drafts.
• Use avatar generation for personalized content.
• Be aware of "uncanny valley" effects in AI avatars.

Topics

• AI Video Generation
• Google Flow
• Gemini Omni
• AI Avatars
• Content Creation
• Podcast Marketing

Best for: Creative Technologist, Marketing Professional, General Interest

Related on AIssential

• Gemini Omni: Clone yourself with AI in under 15 minutes — Google's Gemini Omni and Flow enable rapid AI avatar creation and video generation with minimal effort.
• Gemini Omni: AI Video Generation Inside Gemini — Video generation is now an integrated capability within multimodal AI assistants, not a separate tool.
• Creating a podcast hype video with Gemini Omni — Generative AI tools like Flow empower non-coders to create sophisticated video content previously out of reach.
• Google Omni made this hype video in less than 15 minutes — AI tools like Google Omni enable rapid, high-quality content creation for marketing and media.
• I Didn’t Know AI Could Do THIS — Gemini Omni can generate complex, path-following video content from combined visual and textual prompts.
• Google’s Gemini Omni Can Generate Videos With Shockingly Accurate Text 😳 — Gemini Omni demonstrates advanced video generation with accurate text, nearing indistinguishable realism despite minor flaws.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by How I AI.