Google is preparing to roll out “Whisk,” an innovative generative AI tool specifically designed for artists and creative professionals. Unlike traditional AI tools that rely heavily on lengthy and detailed text prompts, Whisk allows users to generate and modify images simply through visual prompts. With this new approach, users can drag and drop images to kickstart their creative process and produce unique visuals effortlessly.
“Today, we’re launching our newest gen AI experiment in @labsdotgoogle: Whisk,” Google said in a statement posted on X (formerly Instagram). Whisk allows you to prompt with graphics rather of lengthy, in-depth text prompts. Simply drag in images, and start creating.” A supporting blog post elaborated on Whisk’s functionality, highlighting how users can input separate images to define the subject, scene, and style of their project. The tool then combines and remixes these elements to generate fresh, distinctive visuals—whether that’s creating a digital plushie, a pin design, or a custom sticker.
To give insight into its underlying process, Google explained that Whisk uses its advanced Gemini model to automatically generate descriptive captions for the input images. These captions are then processed by Google’s latest image-generation model, Imagen 3. Instead of replicating the original images exactly, the AI focuses on capturing their essence and blending elements creatively.
However, Google acknowledges that Whisk may sometimes deliver unexpected results because it selectively extracts key visual features from the images. This could mean variations in details like height, weight, hairstyle, or skin tone. Understanding that such specifics may be significant for certain creative projects, Google has included an option for users to view and tweak the auto-generated prompts whenever needed.
During its testing phase, artists and creators described Whisk as a revolutionary creative tool rather than a conventional image editor. Designed for rapid visual experimentation rather than meticulous pixel-level adjustments, Whisk encourages users to explore ideas dynamically. The tool enables creatives to try out multiple variations, fostering innovation and allowing them to download their favorite results. Google’s vision with Whisk is to empower artists with an intuitive and fast-paced tool for creative exploration.
