Three new generative AI models for media creation introduced at Google I/O

Google unveiled its latest generative AI models for media creation – Imagen3, Music AI Sandbox, and Veo – at Google I/O 2024. According to the tech giant, these three new AI tools are its most advanced yet, offering higher quality results compared to previous models.

Imagen3, the new image creation tool, has been upgraded to better understand the prompts provided by users, resulting in images that capture even the smallest details. Google claims that Imagen3 can generate text more reliably than its predecessor, Imagen2, which was integrated into Google’s chatbot known as Bard.

On the audio front, Google collaborated with industry professionals like Marc Rebillet to develop Music AI Sandbox, a system tailored for musicians and producers. This suite of AI tools aims to revolutionize music creation by providing artists with the necessary resources to succeed.

But Google’s focus on generative AI doesn’t stop there. The company also introduced Veo, a new video generation model that excels at capturing intricate details, making it a valuable tool for video artists. Veo allows users to create and edit high-quality videos in various visual styles simply by inputting a text, image, or video prompt.

The capabilities of Veo were showcased by Google, demonstrating how the model can produce cinematic shots with just a few keywords. The video quality produced by Veo is exceptional, showcasing its potential to revolutionize the creative process for content creators.