Gemini Omni 1.1 Flash adds 4K upscaling, 40-second scene extension, and frame-to-frame video generation
AI video model releases
Gemini Omni 1.1 Flash adds 4K upscaling, 40-second scene extension, and frame-to-frame video generation
Gemini Omni 1.1 Flash extends generated scenes in 10-second increments to a cumulative 40 seconds, using 10 seconds of prior video context rather than the final second used by earlier Omni releases.
Developers can provide a first frame and last frame, and the model generates the continuous motion between them for shots such as camera orbits, dolly zooms, and loops.
The update generates 360p drafts up to 60% faster than 720p output at roughly one-third of the cost, according to the article.
Generated video can be upscaled to 1080p or 4K, and the model accepts video references up to three seconds long.
Google says the model is available through the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform; Adobe Firefly, Figma Weave, and GMI Cloud are already using it in production tools.
cho.sh