Recently, Google updated the Gemini app, offering users a new AI video generation control method. Users can now upload multiple reference images in a single video prompt. The system will generate videos and audio based on these images and text, allowing users to have more direct control over the final video's appearance and sound.

image.png

Google had previously tested this feature in its extended video AI platform Flow. Flow not only supports expanding existing video clips and splicing multiple scenes but also offers higher video quotas than the Gemini app. According to Google, the Veo3.1 version released in mid-October shows significant improvements in texture realism, input fidelity, and audio quality compared to the Veo3.0 version.

With this update, users can more flexibly use AI tools to create content that better meets their needs. The ability to upload multiple reference images means creators can incorporate more personalized elements into video production, providing audiences with richer visual and auditory experiences.

In this era of rapid development in AI technology, Google's move demonstrates its continuous innovation in the field of video generation. As user demands become more diverse, the flexibility and customizability of AI tools are becoming increasingly important. Gemini's new features are undoubtedly attracting more creators' attention and usage.

Key Points:

🌟 Users can upload multiple reference images to guide AI in generating videos and audio.  

🎥 This new feature enhances users' control over the final video effect.  

🔊 The Veo3.1 version has noticeable improvements in video quality and audio experience compared to the previous version.