By Angela Sun, Director of Multimodal Platforms, Gemini app & Olivia Sturman, Product Manager, Google Labs
Gemini Advanced users can generate and share videos using our state-of-the-art video model, Veo 2. In Gemini, you can now translate text-based prompts into dynamic videos.
Google Labs is also making Veo 2 available through Whisk. This generative AI experiment allows you to create new images using text and image prompts and then animate them into videos.
Create videos in Gemini
Veo 2 represents a leap forward in video generation, designed to produce high-resolution, detailed videos with cinematic realism.
By better understanding real-world physics and human motion, it delivers fluid character movement, lifelike scenes and finer visual details across diverse subjects and styles.
To generate videos, select Veo 2 from the model dropdown in Gemini. This feature creates an eight-second video clip at 720p resolution, delivered as an MP4 file in a 16:9 landscape format.
There is a monthly limit on the number of videos you can create, but we will notify you as you approach it.
Creating videos with Gemini is simple: describe the scene you want to make — whether it’s a short story, a visual concept, or a specific scene — and Gemini will bring your ideas to life.
The more detailed your description, the more control you have over the final video. This opens up a world of fun, creative possibilities. Let your imagination go wild to picture unreal combinations, explore varied visual styles from realism to fantasy, or quickly narrate short visual ideas.
One of the best parts of creating is sharing with others! Sharing your video on mobile is easy: tap the share button to quickly upload engaging short videos to platforms like TikTok and YouTube Shorts.
Video generation is now rolling out to Gemini Advanced subscribers globally on web and mobile, starting today and continuing over the next few weeks.
This feature is available in all languages Gemini supports. With video generation in Gemini, you don’t need complicated software, specialized equipment, or any prior experience to get creative. Try it out today at gemini.google.com.
How Whisk Animate brings your images to life
Introduced this December, Whisk helps you create images using both text and image prompts to explore and visualize new ideas quickly.
Those capabilities are expanding further with Whisk Animate. Launching recently for Google One AI Premium subscribers globally, this new feature will allow you to take the images you generate and instantly turn them into vivid eight-second videos with Veo 2. Subscribers can try Whisk Animate today at labs.google/whisk.
How we approach safety
We’ve taken important steps to make video generation a safe experience. This includes extensive red teaming and evaluation aimed at preventing the generation of content that violates our policies.
All videos generated with Veo 2 are marked with SynthID, a digital watermark embedded in each frame, which indicates the videos are AI-generated.
Gemini’s outputs are primarily determined by user prompts. Like any generative AI tool, there may be instances where it generates content that some individuals find objectionable.
We’ll continue listening to your feedback through the thumbs up/down buttons and make ongoing improvements. For more details, you can read about our approach on our website.
We hope you enjoy making videos using the Gemini app and Whisk as Google One AI Premium subscribers.
Don’t miss important articles during the week. Subscribe to techbuild.africa weekly digest for updates
