Google has taken another major step in AI-powered content creation. The company has announced that Gemini Advanced users can now generate cinematic videos using only text prompts. With its latest video generation model, Veo 2, users can create eight-second MP4 videos in 720p resolution simply by writing scene descriptions. This new feature is now available worldwide on both web and mobile platforms.

Gemini Advanced users can now generate AI-powered videos using the new Veo 2 model!

First, it’s worth noting that the Veo 2 model can be selected from the model menu within Gemini. It may not have reached all Advanced users yet, but it will be activated for everyone soon. Users don’t need any software knowledge to produce short videos in 16:9 landscape format. The more detailed the prompt, the higher the quality of the resulting video.

One of the standout features of the new model is its ability to more accurately reflect human movement. With natural character animations, realistic scenes, and fine stylistic control, users can directly visualize the scenes they imagine. The videos can be shared directly on social media platforms or downloaded as MP4 files. You can view the related videos at the bottom of this article.

Google has also expanded the Whisk platform, which it introduced in December, with a new feature. Initially focused on generating static visuals, the experimental platform now allows users to instantly transform images into eight-second videos using a new tool called Whisk Animate. This feature is accessible at labs.google/whisk.

To ensure the safety of AI-generated content, Google adds a digital watermark called SynthID to every video. This technology embeds an invisible marker into every frame to indicate that the content was generated with artificial intelligence.

In addition, Google places strong emphasis on user feedback during the development of its AI systems. The company implements strict content policies and conducts extensive red teaming tests to prevent the creation of harmful or inappropriate material.

Gemini Advanced users can begin using these features starting today. The system works in all languages supported by Gemini and is available under the Google One AI Premium subscription plan.

As stated at the beginning of the article, you can view videos created with Veo 2 below. Examples include short films generated with prompts such as “a dimly lit scene inside a vast glacial cavern,” “sunset over a wavy beach,” or “a tiny mouse with oversized glasses reading under a glowing mushroom.”

Prompt: Aerial shot of a grassy cliff onto a sandy beach where waves crash against the shore, a prominent sea stack rises from the ocean near the beach, bathed in the warm, golden light of either sunrise or sunset, capturing the serene beauty of the Pacific coastline.

Prompt: A wide, slow-panning shot of an enormous glacial cavern, bathed in eerie twilight. Pale cyan light filters from above, illuminating frozen candy figures within the ice walls. Two figures in white exosuits, their helmet lights casting beams, trudge through the center. Capture the cavern’s scale and stillness.

Prompt: An animated shot of a tiny mouse with oversized glasses, reading a book by the light of a glowing mushroom in a cozy forest den.