Google DeepMind launches the video generation model Gemini Omni 1.2 Flash
Google has released an updated video generation model from Google DeepMind called Gemini Omni 1.2 Flash. Drafts can be generated in 360p or 720p ($0.07/s) and upscaled to 1080p or 4K, reducing costs by 30%. It supports generating and editing videos up to 15 seconds long, with customizable durations between 3s and 15s. The model also allows replacing backgrounds, subjects, or lighting in a conversational turn-by-turn manner, improving lip-sync for multiple speakers and reducing jump cuts through smoother camera movements.
Continue looking at this topic
Related contentWhat is Veo? How to distinguish native audio-video generation from discontinued preview models ↗News and AnalysisGoogle releases Gemini Omni 1.2 Flash: 15-second video generation, price cut of 30% to $0.07/second ↗OpportunitiesTikTok AI product promotion with cumulative ten million views: how to find benchmarks, break down viral hits, and judge content direction ↗Open-source projectAfter breaking down the video shot by shot, how can you convert the rea-video replication plan into a script you can edit yourself? ↗Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original