Google has announced that another AI model is coming to Gemini, but this time it is more than a chatbot. The company's VEO 2 videoerator was rolled out to the Gemini app and website, giving paying customers the chance to make short video clips with the alleged state-of-the-art video model from Google.
VEO 2 works like other video drivers, including the Sora from OpenAi – You enter text that describes the desired video, and a Google Data Center turns through tokens until it has an animation. Google claims that VEO 2 is designed to have a solid understanding of physics in practice, in particular the way people move. The examples of Google look good, but it is probably why they were chosen.
Prompt: aerial photo of a grassy cliff on a sandy beach where waves crash against the coast, a prominent sea pile from the ocean near the beach, bathed in the warm, golden light of sunrise or sunset, conquered the serene beauty of the coastline of the Pacific.
VEO 2 will be available in the drop -down list model, but Google does notice that it is still considering ways to integrate this function and that the location can therefore change. However, it is probably not there yet. Google starts with the rollout today, but it can take a few weeks before all Gemini Advanced subscribers get access to VEO 2. Gemini functions can take surprisingly long to arrive for most of the users -for example, it took about a month for Google Live video available to everyone to make everyone available to everyone.
When VEO 2 pops up in your Gemini app, you can give them as many details as you want, which Google says you have a good control over the final video. VEO 2 is currently limited to 8 seconds of 720p video, which you can download as a standard MP4 file. Video -generation uses even more processing than your average generative AI function, so Google has implemented a monthly limit. However, it has not confirmed what that limit is and only saying that users will be informed if they approach it.
