OpenAI upped the ante in the video generation space earlier this month, making Sora — its state-of-the-art text-to-video generator model — available to ChatGPT Plus users with Sora Turbo. Now, Google is gearing up to compete with the launch of its most advanced video generator.
On Monday, Google launched Veo 2, a text-to-video generator that boasts improvements from the company’s previous model, including a better understanding of real-world physics, which helps the AI produce better generations with more detail and realism, according to Google.
Also: This new Google AI tool lets you easily generate images from other photos – no prompt required
The videos generated can reach up to 4K resolution and, Google said, can tackle common video generator challenges — including hallucinations such as extra fingers. When evaluated by human raters against other leading video models, including Sora Turbo, Kiling v1.5, and Meta Movie Gen, Veo 2 was voted best on overall performance …