Google delights again: Google releases Gemini Omni 1.1 Flash for video generation and editing
Now the model can continue a ready scene by analyzing up to 10 seconds of the previous video. The video can be extended in 10-second increments up to a total length of 40 seconds.
Another useful feature allows setting the first and last frame. The model will automatically create smooth camera movement or transition between them without seams.
For quick tests, there is a 360p mode available. Such drafts are generated up to 60% faster and cost about three times less than the 720p version. The final result can then be exported in 1080p or 4K.
Additionally, Gemini Omni 1.1 Flash accepts up to three seconds of video as a reference to transfer motions and better preserve characters.
The model is already available through Google AI Studio, and some of the features have been integrated into Flow and the Gemini app.
