Fact Checked by 
Google has released a new artificial intelligence (AI) image generation tool called Whisk, which lets you submit prompts as images and refine them with text.
According to a blog post, users can submit an image to act as the subject, the scene, and the style, and Whisk will use those inputs to remix (AI generates) something new based on the prompts, “from a digital plushie to an enamel pin or sticker”, or presumably, pictures of those things.
How does Whisk work?
Behind the scenes, Whisk is using Google’s Gemini AI to create detailed text prompts from the images you input. It then feeds those text prompts into its newly updated Imagen 3 AI image generator. According to Google, this process extracts the “essence” of the images you submit, allowing it to generate unique remixes.
Google does state that: “Since Whisk extracts only a few key characteristics from your image, it might generate images that differ from your expectations. For example, the generated subject might have a different height, weight, hairstyle or skin tone.”
As such, users can edit or supplement the Gemini-generated prompts in order to tweak and finesse the Whisk output and get it to create something closer to what they want.
Google states in its blog post that Whisk is not quite like a traditional image-generation tool. “In our early testing with artists and creatives, people have been describing Whisk as a new type of creative tool — not a traditional image editor. We built it for rapid visual exploration, not pixel-perfect edits. It’s about exploring ideas in new and creative ways, allowing you to work through dozens of options and download the ones you love.”
How to try out Whisk
Currently, Whisk is only available in the US. If you’re based in America you can try it out for free on Google Labs’ website. Google has not given any indication as to when it will be available in other countries.
Featured image credit: Google
