Perhaps Google has recently launched its own app i see generative AI enterprise customersbut the company is wasting no time in getting the new version of the video tool to the first testers. On Monday, Google announced a preview of the Veo 2. According to the company, Veo 2 "understands the language of cinematography". In practice, this means that you can refer to a specific film genre, film effect or lens when suggesting a model.

In addition, Google says the new model better understands real-world physics and human movement. Correctly modeling people in motion is something that all generative models struggle with. So the company's claim that the Veo 2 is better when it comes to both of these points of concern is noteworthy. Of course, the examples provided by the company are not enough to know for sure; The real test of the Veo 2's capabilities will come when someone suggests it Create a video of a gymnast performing. Oh, and speaking of things video models struggle with, Google says the Veo will produce "less" artifacts like extra fingers.

Separately, Google provides improvements Figure 3. The company says the latest version of its text-to-image transition model produces brighter and better-composed images. In addition, it can display a wider variety of art styles with higher fidelity. At the same time, it is better to follow the instructions more faithfully. What I noticed when the company made Imagen 3 available to Google Cloud customers earlier this month was the prompt compliance, so if nothing else, Google is aware of the areas where its AI models need to work.

Veo 2 will roll out gradually Google Labs Users in the United States. For now, Google's testers will limit video creation to eight seconds at 720p. For context, Sora It can create a 1080p video in up to 20 seconds, though it costs $200 a month ChatGPT Pro subscription. As for the latest improvements in Imagen 3, they are available to Google Labs users in more than 100 countries. ImageFX.