Google’s Gemini AI can now modify photographs into eight-second videos using Veo 3. The Photo-to-Video tool, accessible through the prompt box, allows users to submit a photo, describe the scenario, and choose audio cues. This cinematic spin on still photographs enables users to create moving scenes, add sound, and bring static memories to life with a single prompt.
Google recently introduced the Veo 3 video-making model, which expanded access to Google AI Pro members in over 150 countries. Gemini now has a photo-to-video feature, which allows users to convert photographs into dynamic eight-second clips with sound. As per the company, over 40 million Veo 3 videos have been created over the previous seven weeks using the Gemini app and Flow, allowing users to produce an array of creative content.
Photo-to-video is a tool that allows users to convert images into dynamic videos by uploading a photo, describing the scenario, and providing vocal directions. After completing the video, viewers may share it with friends and family by hitting the share icon or downloading it. Video generation limits are enforced, with notifications sent when you’re nearing the limit, indicating the number of videos you’ve created and the remaining ones.
Also Read: Vivo X Fold 5 with 120Hz refresh rate 8T LTPO display launched in India
Google AI Pro and Ultra subscribers worldwide are now able to use photo-to-video capabilities, which are also available in Google’s AI filmmaking tool, Flow, via gemini.google.com.
How to generate a video
The option to create a video from a photo is presently unavailable in the European Economic Area, Switzerland, and the United Kingdom. To create a video, go to gemini.google.com, click Video, enter a video prompt, click Add image, pick the file, and then click Submit. Videos are 8 seconds long and may take 1-2 minutes to create. You cannot communicate in the same chat while the video is being created. Instead, start a new chat and return to watch the video later.
Also Read: Samsung Galaxy Watch 8 Series now available for pre-orders in India
According to the company, Google’s video generation tools aim to provide a confident experience for users. The video generation tools prioritise user confidence through extensive “red teaming,” proactively testing systems to fix potential issues, conducting thorough evaluations to prevent misuse, and constantly developing and enforcing policies against unsafe content. All generated videos are said to include a visible watermark and an invisible SynthID digital watermark, and users can provide feedback by using the thumbs up and down buttons to improve safety measures and overall experience.
