I always have been envious of those with genuine artistic talent.
But now AI is changing this.
I used to fail when using the old way: layering masks, adjusting contrast curves, pixel-by-pixel restoration.
But I feel much more competent with the new way: “Make this shirt blue and add a dog by the door.”
For the past week the internet has been abuzz talking about Google’s new image AI, nicknamed Nano Banana, which delivers studio-quality results from a simple prompt—without losing identity, tone, or texture.
So far I’ve been impressed but it’s not without its faults so read on.
Join senior executives & enterprise leaders for Charlotte’s largest AI conference — two days of strategic frameworks, operational playbooks, and peer-to-peer exchange on scaling AI from pilots to productivity.
Seats are strictly limited and selling fast. Don’t miss your chance!
We are currently calling for speakers — share your AI expertise and submit your topic here. Deadline is on September 15.
Edit Images Like Magic with Google’s “Nano Banana”
Precision photo edits using just words—no Photoshop skills required.
Nano Banana is the nickname for Gemini 2.5 Flash Image, a new model designed to handle image editing tasks through natural language. It’s currently integrated into the Gemini app and Adobe Firefly products, offering:
Natural Language Editing: Add, remove, or modify image elements with detailed prompts.
Image Consistency: Faces, limbs, lighting, and perspective remain intact across multiple edits.
Layered Commands: Chain actions—“Add glasses. Now make them gold.”
Image Restoration: Reverse or restore parts of an image using “highlight and revert” tools.
Fast Output: Edits render in seconds, rivaling performance from tools like Midjourney or Firefly.
Embedded Ethics: Watermarked with visible + SynthID marks for traceability.
Nano Banana interface in Google AI Studio
Natural Language AI Editing
What is the big deal about Nano Banana? It’s a change from using tools to draw artwork to “vibe editing” images. This is a huge boon for business, marketing, and content workflows using natural language:
Competes with Photoshop for light to moderate edits
Integrated into Adobe Firefly, challenging Adobe’s own foundation model bets
Trusted facial + object consistency—important for brand images, e-commerce, and avatars
Multi-modal future: Powers tools like Cling for video morphing and HeyGen Avatar 4 for gesture-based digital twins
Nano Banana Use Cases
Here’s the thing I like about AI-generated artwork. The old way to do this was to spend hours going through stock art sites to find images for the web, presentations, and social posts. And it worked but sometimes I saw someone else using the same clipart, other times, I settled for art that didn’t ideally match what I needed.
Marketing: Instantly tailor product photos to different regions (e.g., packaging, weather).
E-commerce: Fix photoshoots with a few edits—adjust lighting, restore objects, or remove distractions.
Training Materials: Easily create clean visuals, diagram enhancements, or focus callouts.
Personalized Video Content: Use tools like Cling + Gemini to generate motion graphics from static frames.
Workflow Examples
Here’s a hypothetical use case. Let’s say you’re a real estate marketer updating a listing. Your client paid their friend to take “professional” images and you are stuck with mediocre images for their listing. Here’s how AI can save you:
Upload exterior shot
Prompt: “Make the grass greener and sky clearer”
Next: “Add a for-sale sign near the driveway”
Final: “Style image for Instagram – warm tones, soft shadows”
Output = polished listing photo, ready to post
This Edition’s AI Feature Image
The feature image for this edition of The Artificially Intelligent Enterprise was created with Nano Banana. It generated a great picture, actually I generated two pretty decent images with a lot of detail. You can generate an image.
Here’s the prompt I used:
Create a landscape aspect ratio (16:9) image of Nano Banana, the AI Art Virtuoso: A cinematic shot of Nano Banana in a sleek, modern art studio, holding a digital stylus and interacting with a transparent display showing an evolving AI-generated painting. Subtle neural network patterns glow in the background. Do not include text in the image.
How to Edit an Image in Nano Banana
Now here’s where I got stuck.
I actually generated the picture on the right first and then tried to have it crop to a 16:9 aspect ratio.
That didn’t really work.
The second attempt I asked it to make the image more panoramic which is what you see on the left above. They are both square.
To get it to 16:9 aspect ratio for the website and newsletter, I ended up just stretching it in Photoshop.
So why am I telling you about how Nano Banana doesn’t work? Because it did work for my executive assistant but not me. That’s because these models are probabilistic not deterministic.
Also I am guessing that this will get much bigger much more quickly. Anyhow to get started
open the Gemini app (mobile — iPhone or Android, or desktop). I used Google AI Studio to generate this, but they all work the same.
Upload or select an image you already created in Nano Banana
Use a conversational prompt to start editing
Tap highlighted areas to refine or revert changes
Download watermarked image, or continue iterating
From Photoshop to Promptshop with AI
With Nano Banana, image editing is no longer a technical skill — it’s a way to manifest your vision via a creative conversation. You don’t need design software, expensive plug-ins, or editing know-how. Just ideas, a prompt, and a few seconds. That’s all it takes to transform static images into dynamic visuals—with identity, context, and control intact.
I appreciate your support.
Your AI Sherpa,
Mark R. Hinkle
Publisher, The AIE Network
Connect with me on LinkedIn
Follow Me on Twitter
