Gemini Omni 1.1 Flash: Google's multimodal AI video model
Gemini Omni 1.1 Flash is Google's multimodal AI video model: generate video from a text prompt, images, or existing footage, pin the start and end frame and let it interpolate the motion between, guide results with up to 5 reference images and 3 reference videos, extend any clip, and output up to 4K. Available now in Picsart's AI Playground.
- Guide video with reference footage
- Connect your start and end frames
- Extend an existing clip
Turn text, images, and video into one Gemini AI video
Gemini Omni 1.1 Flash is genuinely multimodal: start from a text prompt, a single image, or existing footage, and combine them in one generation. Feed up to 5 reference images to lock characters, products, or style, and up to 3 reference videos to carry motion and look across shots - so every clip stays on-brand from the first frame to the last.
Set the first and last frame, interpolate everything between
Pin a start frame and an end frame and Gemini Omni 1.1 Flash fills in the motion between them, so a transition lands exactly where you want it. It's frame-level control most text-to-video models don't give you - ideal for logo reveals, product turns, and seamless loops - with output from 360p all the way up to 4K, in 16:9 or 9:16.
Google video generation, sharp enough for up to 4K
Every Gemini Omni 1.1 Flash clip renders up to native 4K, in 16:9 for landscape or 9:16 for Shorts, Reels, and TikTok - no upscaling or reformatting. Generate up to 10 seconds per clip, then extend the result when a scene needs more room to breathe.
Find the right Google video model in Picsart
Gemini Omni 1.1 Flash lives in Picsart's AI Playground, where a single prompt runs against 150+ other models so you can compare before committing. Pick Gemini Omni 1.1 Flash for reference-guided, frame-controlled video; choose Veo 3.1 or Veo 3.1 Fast when you need synchronized audio in the same render. And you can reach it whichever way you work - on the web, in the Picsart desktop app, or built into your own projects via CLI, MCP, REST API, and SDK, with no third-party API keys or separate subscriptions to manage.
What you can create with Gemini Omni 1.1 Flash
Reference-guided video
Bring up to 5 reference images and 3 reference videos to keep characters, products, and style consistent across every generated clip.
Understand video model choices
Learn how to compare video models and choose an output.
Explore more models like Gemini Omni 1.1 Flash
Compare Gemini Omni 1.1 Flash with other video models for motion, ads, and social clips.
Gemini Omni 1.1 Flash FAQ
Gemini Omni 1.1 Flash is Google's multimodal AI video model. It generates video from text, images, or video, supports start- and end-frame interpolation, up to 5 reference images and 3 reference videos, clip extension, and output up to 4K.
Generate AI video with Gemini Omni 1.1 Flash
Pro
Most popularAI tools for everyday creative work.
Ultra
Most powerfulHeavy AI usage for creators & teams.