Google is preparing to usher in a new era in visual content creation with its artificial intelligence tool.The tech giant introduced Whisk, a new image creation tool that takes commands with images instead of text. Users will be able to upload multiple images and show the AI what they imagine instead of telling it.

What is Google Whisk and how to use it?

Visual commands uploaded to Whisk will determine the subject, setting and overall style of the output created. While textual detail can be added for more detail, Whisk’s core functionality will be based on the power of the visual.

Powered by Imagen 3, Whisk promises realistic imagery, enabling real-world elements and cinematic elements to be understood. Google describes Whisk as a “rapid visual brainstorming” tool and acknowledges that the results may require further refinement.

Of course, it should be noted that users can change the image output. In addition, Google also introduced Veo 2, the next generation video creation model. The company emphasizes that Veo 2’s capabilities are not limited to content production, but are combined with real-time analysis and recommendation systems.

For example, the model can analyze a long video in a few seconds and highlight the most engaging scenes for the viewer. It also makes content easily accessible globally with multilingual subtitling and voice-over capabilities.

With Whisk pioneering image creation and Veo 2 pushing the boundaries of video creation, we can say that Google has opened a new chapter in AI-powered image creation.