Whoa, hold on. Is Photoshop finally getting a run for its money from AI?
I just saw this incredible post from Tianyu Xu, who did a full deep-dive on Google’s brand new image model, Gemini 2.5 Flash Image (aka Nano Banana).
He put its most hyped features, editing and blending, to the test. Here’s the awesome breakdown he shared.
✨ The Good Stuff (Strengths)
Tianyu found the new model is a major upgrade. It’s great at:
- ✅ Keeping characters looking consistent.
- ✅ Replicating elements from the original images.
- ✅ Showing the same object from different angles.
- ✅ Producing much higher quality images than the last version.
- ✅ Being super fast and easy to use.
⚙️ The Not-So-Good Stuff (Weaknesses)
But it’s not perfect. Tianyu pointed out a few key areas where it falls short:
- ❌ You can’t control the aspect ratio.
- ❌ The editing can look a little bit like a ‘copy and paste’ job.
- ❌ Character resolution drops after you make an edit.
- ❌ It struggles to display long bits of text accurately in images.
🚀 The Final Verdict?
So, is it time to uninstall Photoshop? Tianyu says not yet.
BUT, he found it’s an absolute game-changer for quick concept testing, building out AI workflows, and creating social media content fast.
📌 Pro-Tips from Tianyu Xu
To help you get the best results, he shared these handy tips:
- ↳ Use close-up shots of characters or objects.
- ↳ Avoid creating images that need a lot of text.
- ↳ For more features, try using it with 3rd party tools.
- ↳ If you get stuck, just start a new chat!
This is just my quick summary of his fantastic work. To see the full analysis and a video he created, you have to check out the original post from Tianyu Xu!