You can now give Google’s AI video model camera directions
1 min read
Summary
Google Cloud has made a series of updates to its AI generation and editing tools, including its video AI model, Veo 2.
Veo 2 can now automatically remove objects and apply cinematic styles, along with interpolation features for video transitions between still images.
Text to image editing model, Imagen 3, has also been improved with enhanced automatic object removal, while text to music model, Lyria, is available for audio creation.
Additionally, Google’s synthetic speech model, Chirp 3, has a customisable voice feature and transcribes individual speakers in multi-person conversations.
The updates form part of Google’s strategy to make AI tools more efficient for enterprise users.