Google has updated its Gemini Omni Flash video model to version 1.1, offering developers greater flexibility and cost efficiency in AI video generation. The new version supports scene extension up to 40 seconds, with the ability to analyze up to ten seconds of existing video for more visually consistent results. Developers can also upload up to three seconds of external footage as a style reference to maintain characters or motion patterns. Additionally, they can set start and end frames to create camera movements between keyframes. These enhancements aim to streamline the video generation process while reducing computational demands.
The 360p draft mode in Gemini Omni 1.1 Flash runs up to 60% faster at a third of the cost compared to the 720p version. Videos can be upscaled to 1080p or 4K, with per-second pricing at $0.03 for 360p, $0.10 for 720p, $0.15 for 1080p, and $0.30 for 4K. The model is now available through Google AI Studio and the developer documentation, providing access to a range of tools and resources for creators. The pricing structure reflects Google's efforts to make AI video generation more accessible and scalable for different use cases.
According to the source, the update to Gemini Omni 1.1 Flash is part of Google's ongoing efforts to refine its AI video capabilities. The model's improvements are designed to address specific challenges in video generation, such as maintaining consistency and reducing costs. The pricing details and feature enhancements are intended to support developers in creating more efficient and high-quality video content.
Source: thedecoder
