Google Launches Veo 2 Video AI for Advanced Gemini Users

As an advanced member, Google is using its Veo 2 model to redefine and generate videos in addition to photographs and music through the Gemini app.

Thanks to a grasp of real-world physics and human motion, Veo 2, which was announced at the end of last year, promises “cinematic realism,” “fluid character movement, lifelike scenes, and finer visual details across diverse subjects and styles.” 

On Tuesday, Google said that the Veo 2 AI model will be included in the Gemini chatbot. The AI model will currently only be available to Gemini’s paying members. Eligible users can utilize this AI model to create eight-second movies using natural language text cues. In December 2024, the tech giant located in Mountain View unveiled Veo 2, the Veo AI model’s replacement. It also drives YouTube’s Dream Screen feature and is accessible through the company’s Vertex AI platform.

The tech giant announced the launch of the video generating AI model in Gemini in a blog post. Google is making it available to Gemini Advanced subscribers worldwide in every language that Gemini supports. The model will not be available to users on the free tier.

Simply said, “The more comprehensive your description, the more influence you have over the final video.” Describe the situation you wish to create. The clip takes one to two minutes to create.

The model selector option in Gemini’s mobile applications and online client allows users to choose Veo 2. When given written inputs, the model can produce an eight-second video clip. The resulting video is available for download in MP4 format and is produced at 720p quality with a 16:9 aspect ratio. Google claims that a user may only create a certain number of videos each month, and it will alert the user when they get close to that limit.

Veo 2 can produce 720p, eight-second video snippets in Gemini. In particular, you will receive a 16:9 landscape MP4 file. Additionally, a g.co/gemini/share/ link may be used to share. On the online and mobile applications, choose Veo 2 from the model option to input your prompt.

Simply said, “The more comprehensive your description, the more influence you have over the final video.” Describe the situation you wish to create. The clip takes one to two minutes to create.

Additionally, Google is enabling users to share the produced videos with other people. Tap the share icon on the Gemini app to rapidly post videos to YouTube and TikTok, among other social networking sites. Interestingly, even though the functionality has started to go out, it can take a few weeks until qualified people worldwide can use it.

The tech giant said at the time of release that Veo 2 had better details and realism for all of its components. Additionally, the AI model is able to comprehend the technical jargon used in cinematography, allowing users to describe camera motions, lens, effects, and other details in text prompts.

This creates a world of exciting creative possibilities where you may rapidly describe brief visual ideas, explore a variety of visual styles from realism to fantasy, and imagine unbelievable combinations.

Google also stated that the video creation algorithm has been trained to hallucinate less. As a consequence, consumers should notice undesired features such as additional fingers, morphing limbs, or unplanned items less frequently.

There is a “monthly limit” on the number of movies you may create, and Google alerts users when they are about to expire. This feature is exclusive to Gemini Advanced customers ($19.99 per month). It will be completely accessible in the upcoming weeks after beginning its global rollout today in all of the languages that Gemini supports.

Veo 2 generation is now available in Whisk for Google One AI Premium users. This Google Labs project, which was announced in December, allows you to “prompt with images” rather than words. The option to “Whisk Animate,” which transforms your photographs “into vivid eight-second videos with Veo 2,” is what’s new today.