Gemini Omni 1.1 Flash lets you build with more control
Source
blog.google
Date
Context
Gemini Omni 1.1 Flash gives video creators a longer stretch of existing footage to guide a continuation. Google DeepMind says the model can examine up to ten seconds of prior video, compared with the final second in previous models, then extend the scene in ten-second increments to a cumulative forty seconds. More preceding footage supplies context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → for maintaining the scene's appearance and narrative. Announcement
The same release lets creators specify both a shot's opening and closing images, with the model generating the transition between them. These controls make scene continuation and shot endpoints explicit inputs to a creative workflow.
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
