Google adds image-to-video generation capability to Veo 3 | TechCrunch

Google said on Thursday it’s adding an image-to-video generation feature to its Veo 3 AI video generator through its Gemini app.

The company had already rolled out this feature in its AI-powered video tool called Flow, which was launched in May at Google’s I/O developer conference.

After launching Veo 3-powered video generation in May, Google made the feature available in over 150 countries as of last week. At the moment, only Google AI Ultra and Google AI Pro plan users can generate videos with a three-creations-per-day limit with no carry-over.

Google said that users can generate a clip by selecting the “Videos” option from the tool menu in the prompt box and uploading a photo. You can also add sound by describing the audio in the prompt. Once the video is generated, you can download it or share it with others.

The company noted that since its release seven weeks ago, users have created more than 40 million videos across the Gemini app and Flow tool. All videos generated using the Veo 3 model will have a visible watermark that says “Veo” along with an invisible SynthID digital watermark, which is adopted by Google’s AI tool to identify AI-powered digital artifacts.

Earlier this year, the company also released a tool that helps you detect content containing SynthID.