Google has revealed a major update to its Gemini AI platform that adds a new feature that lets users turn their photographs into sound-assisted, dynamic eight-second video snippets. Now accessible to Google AI Pro and Ultra members in more than 150 countries, the tool is driven by Google’s most recent video creation model, Veo 3. Since the model’s initial release, the company has noted a strong acceptance and innovative experimentation.
“We introduced our cutting-edge video generation model Veo 3 in May, and we extended access to Google AI Pro subscribers in more than 150 countries last week,” stated David Sharon, Multimodal Generation Lead for Gemini Apps. Now that Gemini has a new photo-to-video feature, you can turn your favorite pictures into lively, sound-added eight-second video snippets.
Sharon went on to explain the procedure: “To create videos from your images, upload a picture and choose ‘Videos’ from the tool menu in the prompt box. After describing the scene and providing any voice instructions, you may observe how your still image becomes a dynamic video. Adding movement to nature sceneries, animating commonplace things, or bringing your paintings and sketches to life are all ways to express your creativity. To share your finished film with friends and family, either download it or hit the share button.
Google reports that user response has been prompt and positive. “Over 40 million Veo 3 videos have been created over the past seven weeks using the Gemini app and Flow, demonstrating the absolutely amazing surge in user creativity. When you use Gemini to make films, you can do anything you want, from retelling fairy tales through the eyes of a contemporary influencer to ASMR recordings that explore what it might sound like to cut through a piece of cooling lava,” Sharon added.
Google’s latest text-to-video artificial intelligence technology, Veo 3, is being made more widely available along with the new photo-to-video function. Veo 3 is already well-known for its capacity to create realistic motion and synchronized sound in high-definition video clips that are created only by human input. The concept integrates audio and pictures in eight-second chunks, eliminating the need for post-production editing.
Through the Google Cloud Vertex AI platform, companies can access Veo 3, which Google is touting as a creative and enterprise solution. Veo 3 has been used by app developers and creative professionals to speed up workflows, produce marketing materials, and prototype video content in a fraction of the time that was previously needed.
The business also highlights its dedication to safe and responsible AI development. “We want you to be satisfied with the outcomes when you utilize our video creation tools. To ensure that video generation is a suitable experience, we take important procedures behind the scenes,” Sharon said. This involves what Google calls “extensive ‘red teaming,’ in which we proactively test our systems and aim to fix potential issues before they arise,” in addition to “thorough evaluations to understand how our tools might be used and how to prevent any misuse.”
As Sharon explained, “All generated videos include a visible watermark to show they are AI-generated and an invisible SynthID digital watermark.” Safety precautions also include content labeling. Sharon says, “Use the thumbs up and down buttons on your generated videos to give us feedback, which we’ll use to make ongoing improvements to our safety measures and overall experience.” Users are also urged to leave comments on generated content.
Today, Google AI Pro and Ultra subscribers in a few countries will be able to access the new photo-to-video feature. Google’s AI filmmaking tool, Flow, has the same features, and the corporation is working to make it available in other areas.
“Your imagination is the limit when you create videos with Gemini,” Sharon remarked.
