Google Labs, Google’s experimental arm, is testing a brand new picture generator referred to as Whisk. This instrument permits individuals to immediate with photos as an alternative of textual content, permitting them to remix a photograph by altering the topic, scene, and magnificence.
Whisk makes use of Google’s image-generation mannequin, Imagen 3, to mix three photos: one for the topic, one other for the scene, and one for the fashion. For example, you may choose a photograph of your self as the topic, a futuristic panorama because the scene, and an anime fashion for the ultimate look.
The mannequin robotically generates an in depth caption of your photos, which is then used to information Imagen 3 in making a remix of the picture. It’s also possible to enter textual content prompts to additional outline the specified final result, together with detailed descriptions like “Topic is driving a flying bike.”
As a result of Whisk solely focuses on a number of key traits from every picture, the corporate explains that the outcomes might not all the time meet your expectations. For instance, the generated topic may differ in peak, weight, coiffure, or pores and skin tone. Google says you may view and edit the underlying prompts at any time.
The experiment is at the moment solely obtainable to customers primarily based within the U.S. at labs.google/whisk.
