Last May, Google announced Veo 3, its long-developed AI model for creating videos from images and text. Having garnered considerable attention with its high-quality videos and widely used by many, Veo 3 has now been integrated into Gemini. Veo 3 support will now be available through Gemini. Here are the details.
Veo 3 Support for Google Gemini
Veo 3, introduced in May and accessible to Google AI Pro subscribers in over 150 countries last week, has now been integrated into Gemini. With this new feature, you can create 8-second audio videos on Gemini by simply uploading an image and entering a prompt.
According to Google, over 40 million videos have been created on Veo 3 in the last seven weeks. These videos include interpreting fairy tales through the eyes of a modern influencer, cutting a piece of cooling lava, ASMR videos, and more.
The photo-to-video conversion feature is currently only available to Google AI Pro and Ultra subscribers in select countries. While the same features are available in Flow, to use them on Gemini, simply select Videos from the toolbar menu in the command box, upload an image, describe the scene, and add any voice instructions.
When you use this feature, the image will turn into a video, and you can download or share it. AI-generated videos feature AI and an invisible SynthID digital watermark.
So, what are your thoughts on this? Share your thoughts in the comments.
{{user}} {{datetime}}
{{text}}