Google Omni 1.1 Flash: Generate for 10 seconds at a time, continuous write for up to 40 seconds Dynamic Beating AI News: Google has released Gemini Omni 1.1 Flash, a new version of Gemini Omni Flash that was announced in May and will open for API testing at the end of June. The maximum length of a single generated video in the new version is still 10 seconds, but for the first time, video continuation has been added to the Omni API. After a video is generated, you can now let it continue filming. You can continue writing for another 10 seconds each time, and the maximum length of the entire video after continuous continuation is 40 seconds. Each time it follows, the model will refer to the previous up to 10 seconds of footage to ensure that the characters, actions, and plot are as closely connected as possible. Omni 1.1 also added frame control for the beginning and end frames. Users can provide it with a starting image and an ending image, allowing the model to automatically generate a continuous video in the middle. For example, when the designated shot starts with the character standing in the distance and ends with them in front of the camera, the model will complete the entire motion process on its own. This time, a cheaper 360p draft mode has also been added, with the official stating that the system throughput can be increased by up to 60%, and the cost is about one-third of 720p. The API prices are $0.03 per second for 360p, $0.10 per second for 720p, $0.15 per second for 1080p, and $0.30 per second for 4K. 1080p and 4K are both post production amplification, not native high-resolution generation. [Original link]