Google introduced an image-to-video generation feature for its Veo 3 AI video generator via the Gemini app on Thursday, extending a capability previously available in its Flow tool.
This image-to-video feature was initially launched in May through Google’s AI-powered video tool, Flow, at the I/O developer conference. Following the May launch of Veo 3-powered video generation, Google expanded its availability to over 150 countries as of last week. Currently, only Google AI Ultra and Google AI Pro plan subscribers can generate videos, limited to three creations per day, with no carry-over of unused creations.
Users can generate a video clip by selecting the “Videos” option within the tool menu in the prompt box and uploading an image. Additionally, users can incorporate sound by describing the desired audio in the prompt. Upon generation, the video can be downloaded or shared. Google reported that since its release seven weeks ago, users have created more than 40 million videos across both the Gemini app and the Flow tool.
All videos produced using the Veo 3 model will feature a visible “Veo” watermark and an invisible SynthID digital watermark, which Google’s AI tools utilize to identify AI-generated digital artifacts. Earlier this year, Google also released a tool designed to detect content containing SynthID.
