Google He announced the launch of Veo 2 Artificial Intelligence model (Ai) for Gemini Chatbot on Tuesday. Currently, the AI model will be accessible only to subscribers paid from twins. With this AI model, eligible users can generate eight -second videos with natural language text warnings. Mountain View -based technology giant first introduced Veo 2 in December 2024 as successor of the Veo Ai model. It is also available through the AI platform of the company’s company and feeds the YouTube dream screen feature.
Veo 2 in Gemini can generate videos 720p
In one Blog postThe technology giant announced the launch of the twin video generation model. Google is launching globally in all languages that Gemini supports the Advanced Gemini subscribers. Those in the free layer will not have access to the model.
I see 2 It can be selected from the Picker Model menu in Web Web apps and Gemini’s mobile applications. The model can generate an eight second music video based on text warnings. The output video is generated in 720p resolution with a ratio of 16: 9 and can be downloaded in MP4 format. Google says there is a monthly limit on how many videos a user can generate and will notify the user as they approach the limit.
Google is also allowing users to share the videos generated with others. Node Twins Application, users can play the Share button to upload videos quickly to social media platforms like Tiktok and YouTube. Notably, although the feature has started to be released, it can take a few weeks for eligible users worldwide to have access to it.
At the time of launch, the technology giant said Veo 2 comes with improvements in realism and details of the various elements. It can also understand the technical terms of cinematography, which means that users can specify a camera lens, camera movements, cinematic effects and more in text warnings, and the AI model can adhere to them.
Google also said the video generation model was trained to hallucinate less. As a result, users should see unwanted details, such as extra fingers, transformed limbs or unexpected objects with less frequently.