Google Introduces Image-to-Video Generation for Veo 3 via Gemini App
AI-Powered Video Creation Now Accessible to More Users
Google has expanded the creative capabilities of its Veo 3 AI video generator by adding image-to-video generation directly through the Gemini app.
- Users can now upload a photo and instantly generate a video clip by selecting the “Videos” option from the tool menu and adding audio descriptions in the prompt.
- This feature was previously available only in Google’s Flow tool, which debuted at the I/O developer conference in May, and has now been rolled out to Veo 3 users across more than 150 countries.
How It Works and Who Can Use It
- Currently, Google AI Ultra and Google AI Pro subscribers can access image-to-video generation, with a daily limit of three video creations (no carry-over).
- Users simply upload an image, describe the desired audio, and the app produces a downloadable, shareable video.
AI Watermarking and Responsible Content Creation
- Every video made with Veo 3 is visibly watermarked (“Veo”) and includes an invisible SynthID digital watermark—Google’s proprietary method for identifying AI-generated content.
- Earlier this year, Google also released a tool that helps users detect SynthID watermarks, supporting transparency and digital authenticity.
Strong Adoption and Continued Rollout
- Since launching Veo 3-powered video generation in May, Google reports that users have created over 40 million videos across the Gemini app and Flow.
- This update positions Google at the forefront of AI-driven multimedia tools, offering creators new ways to blend photos and text prompts into dynamic video content.
