Google set the AI Video world on fire with the introduction of their VEO 3 model, which took your text prompt and converted it into an 8 second video with built-in audio, and this was an absolute game changer as you could now generate videos based on your idea without the need to put in the extra effort of creating the audio for the same separately. Obviously, the next thing on the mind of Gemini users was – “well, I have an image that I want to animate, when can I do that?”.
If you are one of these users, then there is good news for you as Gemini now allows you to upload the image of your choice and create the video based on the same. Obviously, you cannot upload content that violates Google policy, which is to be expected, but otherwise, image to video is now a real thing on Google’s Gemini platform. One more thing, you need to be a Gemini Pro subscriber to use the new feature as it is bundled with Veo 3, which is only accessible to Pro users.
If you want to try Gemini’s new image-to-video feature, just hit the “tools” button in the prompt bar and pick “video.” Right now, Google’s keeping things pretty limited — Veo 3 can only generate eight-second clips at 720p resolution. The videos come out in landscape (16:9), which means they’re not exactly made for Instagram or TikTok. So if you’re thinking of social sharing, TikTok’s AI Alive still has the upper hand.
That said, Veo 3 has something most other models don’t: it can sync audio with the video it creates — a rare ability at the moment.
You can also access the same image-to-video tool in Flow, Google’s AI filmmaking app, which just expanded to 75 more countries. On desktop, it’s already rolling out via the Gemini app, and mobile users should see it by the end of the week. To use it, you’ll need either a $20/month Google AI Pro plan or the $250/month AI Ultra plan.
