Google Labs has been hard at work creating a new tool to help us play more. That's led to Whisk, an AI-powered image generation tool that allows users to create and remix visuals using their own images as prompts.
Announced yesterday (December 16), Whisk marks a significant shift from traditional text-based prompts, instead offering a more intuitive and creative approach to AI-generated imagery. As someone who plays with a lot of AI tools, I have to say, this one is so fun and addictive — in just five minutes, I made plushies, pins, and stickers.
Meet Whisk! 🎉 Our new experiment that lets you use images as prompts to visualize your ideas and tell your story. Try it now: https://t.co/BR1z7gmDs6 pic.twitter.com/2zrPLQZlgaDecember 16, 2024
A new approach to image generation
Whisk is not like other AI image generators. Rather than using typical text prompts, users simply upload an image and then determine the subject, scene and style of their creations. This method allows for a more nuanced and tailored process, as users can provide multiple images for each category to guide the AI's output. Additionally, Whisk offers the flexibility to refine results with text prompts, enhancing the accuracy of the generated images.
Users can use Whisk from their browser or on mobile using uploaded images. For users without readily available images, Whisk offers sample images to serve as prompts, streamlining the creative process and making it accessible to anyone hoping to try out the AI tool.
Powered by Google's Imagen 3 model
Whisk leverages Google's latest Imagen 3 model to produce images quickly. While the tool is optimized for speed and creativity rather than quality, Google acknowledges that it may not always produce perfect results, emphasizing its role in the early stages of the creative process rather than final image editing.
For me, the speed at which users can create images is part of Whisk’s charm. From my experience testing Whisk within hours of its release, I noticed a few flaws, but was able to fix them with the editing feature. AndWhisk's design encourages experimentation, allowing users to explore various concepts and styles efficiently.
Despite occasional imperfections in the image generation process, the overall experience is fun, making Whisk an entertaining and valuable resource for creative brainstorming.
Availability and access
Whisk is currently available through Google Labs, allowing users to experiment with the tool and provide feedback for further refinement. As part of Google's ongoing commitment to advancing AI technology, Whisk represents a step toward more interactive and user-friendly AI applications in the creative industry.
Alongside Whisk, Google has introduced Veo 2, an advanced video generation model aimed at enhancing video creation tools such as VideoFX. Veo 2 is expected to integrate with platforms like YouTube Shorts in the future, expanding the capabilities of content creators by providing AI-driven video generation features.
The introduction of Whisk reflects a growing trend toward AI-assisted creativity, making AI a collaborative partner in the artistic process by giving users the opportunity to upload and remix images on their terms.
