Aside from Gemini, Google further expands its suite of Generative AI tools with Whisk, which is its latest experiment exploring the potential of AI imager generation. The main selling point of Whisk is that Google claims even those without prior AI knowledge will be able to make good use of the platform. Beyond text prompts, Whisk also allows users to use image prompts—just drag images into the platform, and Whisk will take care of creating images for you.

Whisk’s image generation process is made possible with Google’s Imagen 3 model, which captures the subject’s essence and allows people to remix subjects, scene, and styles in any way they like–from character concepts to enamel pin designs. What you just need to do is to input images for the main subject, scene, and preffered art style, and Whisk will try to generate an image that fits those prompts.

A few disclaimers to take note: Whisk extracts only a few key characters from images, so generated content may differ from one’s expectations. However, the way Whisk works is that users can view and edit prompts anytime to further refine the image it generates. Aside from that, do note that the images you upload as prompts should be 10MB or smaller.

You can try out Google Whisk here.