Video generation just got more fun with Google’s new Gemini feature that allows users to quickly create short videos by simply describing their ideas, which can be used for fun, sharing with friends, or visualizing concepts.
This new feature, which can convert photos into eight-second video clips with sound, is powered by the Veo 3 model. Users can select ‘Videos’ from the tool menu and upload their photo. They can then enter a prompt describing the video and any audio instructions, including dialogue or ambient sounds.
The videos generated are 8 seconds long, which may take 1-2 minutes to generate. During video generation, users cannot interact with the same chat, but can start a new one and revisit it later. Additionally, users can request audio generation from Gemini. Once the video is created, users can share it and download it.
The feature allows users to create animated videos, bring their drawings and paintings to life, or add movement to nature scenes. The generated videos will have a visible watermark and an invisible SynthID digital watermark to indicate their AI generation.
Google AI Pro and Google AI Ultra users have limits on video creation, with notifications sent when users reach the limit. Pro users can upgrade to Google AI Ultra or wait for their limit to refresh. Ultra users have higher limits and can generate more videos.
However, Gemini Apps may remove videos if they detect a violation of Google’s Terms of Service, including the Prohibited Use Policy.
