Google released Gemini Omni 1.2 Flash and increased the length of a single video to 15 seconds. Google announced the launch of the Gemini Omni 1.2 Flash AI video generation model, which supports native video generation of up to 15 seconds, and adds multiple rounds of interactive editing capabilities. Compared to the previous generation model, the video time limit was raised from 10 seconds to 15 seconds, which is 50% longer. The user can set the generation time between 3 seconds and 15 seconds in units of 1 second. According to Google, the new model improves the ability to follow reference content, can better maintain the consistency of characters, objects, props, scenes and environments in multiple lenses, and reduce visual drift or morphological changes that occur during movement and lens switching. This capability also applies to interpolating between keyframes at the beginning and end, and continuing to extend the video on top of the original clip.

Google released Gemini Omni 1.2 Flash and increased the length of a single video to 15 seconds. Google announced the launch of the Gemini Omni 1.2 Flash AI video generation model, which supports native video generation of up to 15 seconds, and adds multiple rounds of interactive editing capabilities. Compared to the previous generation model, the video time limit was raised from 10 seconds to 15 seconds, which is 50% longer. The user can set the generation time between 3 seconds and 15 seconds in units of 1 second. According to Google, the new model improves the ability to follow reference content, can better maintain the consistency of characters, objects, props, scenes and environments in multiple lenses, and reduce visual drift or morphological changes that occur during movement and lens switching. This capability also applies to interpolating between keyframes at the beginning and end, and continuing to extend the video on top of the original clip.