Google Deepmind updates Veo 3.1 with reference image function for more dynamic videos

Google Deepmind has updated Veo 3.1 with new features for generating video from reference images. The update enables more dynamic and expressive videos, even with simple text prompts, according to Google. Users can now keep characters consistent across multiple scenes and seamlessly combine different elements like textures, objects, and backgrounds.

The update also adds native support for vertical videos in 9:16 format, optimized for YouTube Shorts and the YouTube Create app along with other mobile platforms. Veo 3.1 now offers upscaling to 1080p and 4K resolution for professional productions. This likely means even more AI-generated content flooding YouTube, especially in the Shorts format.

The updates are available now in the Gemini app, YouTube, Flow, Google Vids, and through the Gemini API and Vertex AI. All generated videos include the invisible SynthID watermark to identify AI-generated content. Users can check in the Gemini app whether a video was created with Google AI.