Google Launches Whisk, An AI Tool For Multiple Image Generation

Reading Time: 2 minutes

Google’s Whisk: A groundbreaking shift in AI-driven visual design, redefining creativity and reimagination.

Key takeaways

• No more text-only prompts — Whisk’s image-first approach is a game-changer.
• Say goodbye to perfect copies; Whisk prioritizes creative essence over replication.
• Artists and designers call it a “creative playground” for visual brainstorming.
• Available exclusively in the U.S., leaving global users on the sidelines (for now).

Google launches Whisk

An Image-First AI Generator Google Labs has released Whisk, its latest generative AI experiment, in the United States. Unlike traditional image generators, which mostly rely on text prompts, Whisk focuses on using images as the primary input method. 

Users can upload images directly into Whisk or generate them within the tool, specifying elements for the subject, scene, and style. This fresh approach aims to give artists, designers, and creators a more intuitive way to generate visuals.

How Google Whisk works?

A Fusion of Images, AI, and Human Input Rather than mimicking images pixel-by-pixel, Whisk’s system focuses on capturing the essence of the subject. 

Google’s language model—likely the recently released Gemini 2.0 Flash—creates detailed descriptions of the input images automatically. 

These descriptions are then processed by Google’s latest image generation model, Imagen 3, which captures the essential features of the subject rather than creating exact copies. 

Users can refine their creations by editing text prompts, allowing for more tailored results.

Not your typical AI tool!

Whisk’s Creative Edge Unlike “exact copy” generators, Whisk produces designs that may differ in height, weight, hairstyle, or skin tone. 

Google aims not to “clone” but to “create,” making it ideal for creative ideation. Since Whisk only extracts a few key elements from each source image, Google warns that the results might not match users’ expectations. 

The generated images could have different heights, weights, hairstyles, or skin tones than the originals. Early testers, including artists and creative professionals, have described it as a “visual playground” for rapid brainstorming. 

It’s less about perfection and more about possibility, giving users multiple design options to sort and save.

Whisk lets you input images for the subject, one for the scene and another image for the style. Then, you can remix them to create something uniquely your own, from a digital plushie to an enamel pin or sticker.

Learn more 🔽 https://t.co/ldp0eO3CdA

— Google (@Google) December 16, 2024

Is the hype real, or is it just another US-only gimmick? 

For now, only US-based users can experience Whisk’s potential. Available through Google Labs at labs.google/whisk access is free — but the exclusivity has sparked some frustration among global users. 

While demand surges, early reviews report slight delays in image generation, likely due to traffic overload. But as always with Google’s experiments, there’s hope for a broader rollout. 

Although users outside the US won’t be able to access the tool yet, many eagerly await its worldwide availability.

Whisk’s debut signals a shift in AI image generation from text-based instructions to image-first creativity. 

Artists and designers are already praising it as a tool for visual brainstorming, but with limited access, many are left watching from the sidelines. 

While Whisk offers innovation and creative freedom, its exclusive access to US users has disappointed international creators. 

Will Google’s image-first model become the industry standard, or is this another US-exclusive hype machine? As with all Google Labs experiments, only time will tell if Whisk will expand beyond its US-only launch and become a global tool for designers everywhere.

Subscribe to our global Design Journal and stay updated with the daily design news.