Last week, Google added Veo 2 video generation to the Gemini app for Advanced subscribers. As a result, more Gemini app users who have upgraded to Advanced now have access to Veo 2 video generation.
“Veo 2: Generate videos from text” will be listed at the bottom of the model dropdown for Android, iOS, and the web when it becomes available.
Simply state your desired outcome; further specifics will help the output. The 8-second film will take one to two minutes to generate once you enter. You receive a 720p landscape (16:9) video.
Also Read: Google DeepMind’s latest Veo 2 AI video creator outperforms OpenAI’s Sora
You can download the MP4 to your device, and Gemini provides its standard link-based sharing.
Gemini notifies users as they get close to the monthly cap on the number of clips they can create. Some examples of prompts are
- “A tiny puppy sprinting through a snow-covered garden in the early morning light”
- “A kitten is brought to the beach, particularly the area by the water, and is startled when a wave crashes close by.”
- “The serene beauty of the Pacific coastline and the dramatic elevation change are captured in this aerial shot of a grassy cliff onto a sandy beach where waves crash against the shore. A prominent sea stack rises from the ocean near the beach, bathed in the warm, golden light of either sunrise or sunset”.Â
Also Read: Gemini 2.5 Pro-powered Deep Research (experimental) is now accessible
Veo 2 access has been extended to more Gemini Advanced users as of right now, although it is still not generally accessible. This is being implemented worldwide. It joins the podcast-style Audio Overviews with Imagen 3 picture production.
In other changes, the model picker’s design has been adjusted by gemini.google.com to align with the mobile app. What you are currently utilizing is now contained in a tablet, which was introduced yesterday.
