On Tuesday, Google announced the launch of the Veo 2 artificial intelligence (AI) model integrated into its Gemini chatbot. Currently, this feature is exclusively available to paid subscribers of the Gemini service, allowing eligible users to create eight-second videos through natural language text prompts.
Veo 2 in Gemini Can Generate 720p Videos
In a recent blog post, Google revealed details about the global rollout of this video generation AI model across all languages supported by Gemini, specifically for Gemini Advanced subscribers. Users on the free tier will not have access to this feature.
The Veo 2 model can be selected from the model picker menu in both the web client and mobile applications of Gemini. It generates video clips of eight seconds in length based on user-provided text prompts. The videos are produced in 720p resolution with a 16:9 aspect ratio and can be downloaded in MP4 format. Google has indicated that there will be a limit on the number of videos a user can create each month, and users will receive notifications as they approach that limit.
Additionally, Google is enabling users to share their created videos with others. Within the Gemini app, users can click the share button to easily upload their videos to social media platforms like TikTok and YouTube. Although the feature is being rolled out now, it may take several weeks for all eligible users worldwide to gain access.
Upon its introduction, Google noted that Veo 2 offers enhanced realism and detail in the generated content. The model’s ability to comprehend cinematographic terminology allows users to specify elements such as camera lenses, movements, and cinematic effects, which the AI can incorporate into the resulting video.
Furthermore, Google stated that the video generation model has been optimized to reduce instances of hallucinations. Users can expect fewer unwanted details such as extra fingers, distorted limbs, or random objects appearing in their videos.
