Google Gemini Update: Enhanced AI Videos with Multiple Images

Key Takeaways

1. OpenAI’s Sora 2 is not available in Europe, while Google is improving its Veo model.
2. Veo 3.1 has been added to the Gemini app for mobile and desktop platforms.
3. Users can now upload multiple reference images with text prompts for better precision in AI-generated videos.
4. This feature allows users to combine different elements, like characters, backgrounds, and visual styles, in their prompts.
5. The “Ingredients to Video” functionality has expanded from Google’s specialized tools to the standard Gemini app.

While OpenAI’s Sora 2 isn’t yet accessible in Europe, Google is enhancing its rival model, Veo. Following the release of Veo 3.1 in the middle of October, this model has now been incorporated into the Gemini app for both mobile and desktop platforms. With the recent update, Google aims to tackle one of the main obstacles and offers users greater precision in their control. As per Google’s announcement on their X account for the Gemini app, users now have the ability to upload several reference images alongside their text prompts.

Enhanced User Experience

For instance, one image might serve as a reference for a character, another could depict the background, and a third might illustrate the overall visual style. The accompanying text prompt can then provide clearer directions on how these components should merge in the AI-generated video.

New Features Available

This functionality isn’t entirely fresh, considering the “Ingredients to Video” feature was integrated into Google’s AI filmmaking tool, Flow, back in October. With the recent update, this feature has expanded beyond Google’s specialized developer tools like Flow or Vertex AI, and is now directly integrated into the standard Gemini app.

According to Google, the introduction of this new feature has already begun to roll out.

Source:
Link