Google Veo 3: New Image-to-Video Generation

Google Integrates Image-to-Video Generation into Veo 3

On Thursday, Google announced the addition of an image-to-video capability to its Veo 3 AI video generator. This functionality is being implemented through the Gemini app.

Feature Rollout and Availability

Previously, this feature was introduced within Google’s AI-driven video creation tool, Flow. Flow was initially unveiled during Google’s I/O developer conference in May.

Following the initial launch of Veo 3 video generation in May, Google expanded its availability to over 150 countries as of the previous week. Currently, access is restricted to subscribers of Google AI Ultra and Google AI Pro plans.

These users are limited to generating three videos per day, with no unused creations rolling over to the next day.

How to Utilize the New Feature

Users can initiate video creation by selecting the “Videos” option within the tool’s menu. This is accessible from the prompt box, where a photo can then be uploaded.

Furthermore, audio can be incorporated by providing a descriptive prompt detailing the desired soundscape. Generated videos can then be downloaded or shared.

Usage Statistics and Watermarking

Google reports that over 40 million videos have been created by users utilizing the Gemini app and Flow tool since the release of the feature seven weeks ago.

All videos produced using the Veo 3 model will include a prominent “Veo” watermark. Additionally, an invisible SynthID digital watermark will be embedded.

This SynthID watermark is a standard practice for Google’s AI tools, serving to identify digitally created content generated by artificial intelligence.

SynthID Detection Tool

Earlier in the year, Google also released a dedicated tool designed to detect content containing the SynthID watermark. This aids in identifying AI-generated media.