It’s pretty clear that generative AI is the current big thing in the tech space. One popular use case is image creation, and Google has an innovative take with its new experiment: Whisk!
Whisk is a fun and engaging tool that makes AI image generation more accessible, especially if you don’t have any experience with using AI tools. You don’t have to type long and detailed text prompts! Instead, you just drag images to start creating.
Generative AI utilizes deep-learning models to make high-quality content based on existing data. There are times when certain design elements get lost in text prompts. But with Whisk, anyone can easily customize how the image will come out. You can specify image inputs for the main subject, the scene, and preferred art styles.
Behind the scenes, the Gemini model automatically writes a detailed caption of chosen images. It then feeds those descriptions into Google’s latest image generation model, Imagen 3. This process captures the subject’s essence, and doesn’t create an exact replica. This further allows people to remix their subjects, scenes, and styles in novel ways to create something that is uniquely theirs, from character concepts to enamel pin designs.
It’s also important to highlight that Whisk extracts only a few key characters from images, so generated content may differ from one’s expectations. Fortunately, it allows users to view and edit underlying prompts at any time to get the output they want.
You can try out Whisk for yourself here: https://labs.google/fx/tools/whisk.