Gemini Omni 1.1 Flash adds 4K upscaling and 10-second scene extension
- Source
- x.com
- Date
Meet Gemini Omni 1.1 Flash ⚡️ Our newest multimodal model for video generation and editing. It now features your favorite creative controls from Veo, plus brand new capabilities. Enjoy features like 4K upscaling, first / last frame control, and fast 360p drafting. But, the biggest upgrade? Next-level scene extension. With Omni 1.1 you can extend scenes based on 10 seconds of context from your original video, a big jump from Veo's 1 second! That means tighter consistency, deeper control, and longer, more cohesive storytelling. See it in action ↓
— Upgrades coming to @FlowbyGoogle — Extend scenes in the @GeminiApp (globally rolling out for all Google AI Plus, Pro and Ultra subscribers) — Build directly in @GoogleAIStudio — Deploy on the Gemini Enterprise Agent Platform https://t.co/AgQG8VKOhz
Context
Gemini Omni 1.1 Flash can use up to ten seconds of an existing clip when generating its continuation. Google DeepMind's release explanation contrasts that with earlier models that referenced only the final second. The longer input gives the model more of the preceding action to draw on, which the company says improves visual consistency and adherence to the story.
The same release permits extensions in ten-second increments, up to a cumulative 40 seconds. The input- and the added footage are separate limits: one describes how much preceding video the model examines, and the other describes how the resulting clip grows.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
- postGoogle's week: EmbeddingGemma 2, Nano Banana 2.1, Gemini business agent
postGoogle opens SynthID watermark checks to everyone, with partner coverage
postGemma 4 orchestrates a plant DNA model to find crop mutations in minutes
articleGoogle's Project CC gives a family agent its own identity and sandbox
Checking sign-in…
Loading comments…