# Leonardo adds Gemini Omni Flash for text-to-video

By Steven Van · 2026-06-30

Generates 720p clips up to 10 seconds from a text prompt or reference image, with more accurate lighting, physics and motion.

Leonardo.Ai has added Google's Gemini Omni Flash model, generating 720p video clips up to 10 seconds long from a text prompt or a reference image. The vendor says the model handles lighting, physics and motion more accurately, producing scenes grounded in narrative logic rather than pattern-matched motion.

See the [announcement](<https://x.com/i/status/2072077875746918688>) for details.

[View media](<https://video.twimg.com/amplify_video/2072077764346236928/vid/avc1/1280x720/XaivFD4mVj-LMRLd.mp4?tag=14>)

![Leonardo.Ai](<https://www.google.com/s2/favicons?domain=leonardo.ai&sz=128>)

Leonardo.Ai

AI image and video generation platform — create production-quality visuals with fine-tuned models and a generous free tier.

[View Leonardo.Ai →](<https://creatorstoolbox.com/tools/leonardo-ai>)

[Read Leonardo adds Gemini Omni Flash for text-to-video on Creators Toolbox](<https://creatorstoolbox.com/blog/leonardo-ai-gemini-omni-flash-on-leonardo>)

---
Canonical source: https://creatorstoolbox.com/blog/leonardo-ai-gemini-omni-flash-on-leonardo