Google Releases Gemini Omni 1.2 Flash Video Model
Google DeepMind has released its video generation model, Gemini Omni 1.2 Flash. The company claims it generates videos faster and reduces costs by 30%. It supports upscaling drafts from 360p/720p (at $0.07 per second) to 1080p/4K, with videos up to 15 seconds long. The model also enables conversational, iterative revisions and more natural speech-to-lip-sync alignment.
Google Releases Gemini Omni 1.2 Flash Video Model
Google has released Gemini Omni 1.2 Flash, a video generation model from Google DeepMind. According to official claims, it generates videos faster and reduces costs by 30%: users can create 360p or 720p drafts ($0.07/second) and then upscale them to 1080p or 4K.
Videos can be up to 15 seconds long, with selectable durations from 3 to 15 seconds. The model supports conversational, turn-by-turn modifications to backgrounds, subjects, or lighting. It also delivers more natural multi-speaker audio with synchronized lip movements, more controllable camera movements, and fewer abrupt cuts.
Google(@Google)