AI image creation tools have been delighting us for years now, thanks to OpenAI, Imagen, Adobe Firefly, DALL-E-3, etc. As technology develops, we have more and more options for refining images. Adjust your results. Now, Google Labs has released Whisk, a tool that allows you to upload images as instructions instead of text prompts.

Google Labs’ Whisk creates images from other images

If you live in the US, you’ll now have access to Whisk from Google Labs, an “experiment in Generative AI,” according to Google’s blog. With Whisk, instead of just relying on a descriptive text prompt, you can add images as references. The platform will require 3 main characteristics: Theme, scene and style. The tool will then blend those elements together and create the perfect image for you.

Google has not completely eliminated text prompts with Whisk. You still have the option to write a prompt to create an image for each item in the three categories or add a general note. You can also fine-tune the image after viewing Whisk’s first test. For example, let’s say you create a vintage-style greeting card of a cat lying in the snow. After seeing the results, you might come up with the idea of ​​adding snowflakes for a finishing touch.

Each time you add or create an image in any of Whisk’s three categories, the platform does the work of generating a detailed textual description of that image. So, if you want to add or edit an existing image, you just need to customize the text.

Finally, if you’re out of inspiration, you can randomize your visual elements by choosing a dice symbol. For more complex creations, you can also add more than one theme, scene, or style reference.

When you’re happy with your masterpiece, you can save it on the platform or download it for local access.

Is it worth using Whisk?

With all the advanced AI image creation options available to enhance photos or create “original” works of art, Google’s new tool may seem like just a gimmick. But the way Whisk leverages visual references in its image creation is unique, and you can see how valuable it is in creative and professional situations.

Let’s say you’re working on a pitch deck and need images that look similar to a reference you already have. Instead of trying to reverse engineer that reference verbally, you can simply upload the file, along with a brief text description of how you want your new image to be different.

To differentiate Whisk from other AI imaging software out there, Google has determined that the platform is designed for exploration, not refinement. While other products may be better suited to fine-tuning edits, Whisk is best suited for brainstorming:

“We built it for quick visual exploration, not pixel-perfect editing. Whisk is about exploring ideas in new and creative ways, allowing you to process dozens of options and download your favorite options”.

Honestly, sometimes it’s hard to describe things with words. Whisk offers some new potential when you simply “want an image to look like this”.