Goodbye, Photoshop

Google just dropped a new game-changing AI image model.

In partnership with

đź‘‹ Hey there,

I spent the day testing Google’s new image model Nano Banana — and it genuinely surprised me. It takes edits that used to require advanced Photoshop skills and makes them possible in seconds with a simple prompt.

Nano-Banana In Action

The standout feature is character consistency. You can keep the same character(s) across different edits while:

  • Changing facial expressions

  • Adjusting clothing

  • Relighting scenes or shifting the camera angle

  • Swapping backgrounds or adding/removing objects

That level of editing used to be a specialized skill. Now it’s available to anyone.

Potential use cases

  • Recreate high-performing YouTube thumbnails with your character in different styles or expressions

  • Storyboard scenes with consistent characters for short-form content or campaigns

  • Generate lifestyle product shots for marketing

  • Redesign interiors or swap backgrounds

  • Colorize old black and white photos

  • Remove unwanted objects or logos

There are honestly so many use cases and I’m just scratching the surface.

My workflow: Nano Banana + Canva AI

I tested Nano Banana on a set of images, then polished them in Canva AI for things like:

  • Expanding the frame

  • Removing logos or watermarks

  • Modifying text

  • Making background adjustments

Photoshop is of course an amazing tool, but it’s not one of my strengths. I prefer to keep my toolkit lean — the fewer tools I need to get results, the better. Nano Banana plus Canva gives me speed, consistency, and quality without the steep learning curve.

Try it yourself

👉 Nano Banana: ai.studio/banana (also available via the Gemini 2.5 Flash Image)
👉 Canva AI: Built into Canva under Magic Studio

Training Generative AI? It starts with the right data.

Your AI is only as good as the data you feed it. If you're building or fine-tuning generative models, Shutterstock offers enterprise-grade training data across images, video, 3D, audio, and templates—all rights-cleared and enriched with 20+ years of human-reviewed metadata.

With 600M+ assets and scalable licensing, our datasets help leading AI teams accelerate development, simplify procurement, and boost model performance—safely and efficiently.

Book a 30-minute discovery call to explore how our multimodal catalog supports smarter model training. Qualified decision-makers will receive a $100 Amazon gift card.

For complete terms and conditions, see the offer page.

That’s my takeaway from today’s experiments. These tools make pro-level editing faster and more accessible, which is exactly what I look for as a creator.

Catch you in the next one,
Sabrina @ DG Mastery