Google’s nano banana just killed Photoshop... let’s run it

Google’s nano banana just killed Photoshop... let’s run it

August 29, 2025 3 min
📺 Watch Now

🤖 AI Summary

Overview

Google's release of Gemini Flash 2.5, nicknamed Nano Banana, is poised to revolutionize image editing with its ability to perform advanced photo alterations while maintaining character consistency. This tool promises to enhance productivity for animators, graphic designers, and game developers, but it also comes with limitations and quirks.

Notable Quotes

- Instead of learning how to use all these antique tools, you can now just prompt Nano Banana for changes and it’s able to deliver any photo alterations you can imagine.

- Google is finally back to its roots building cool stuff, and Flash 2.5 makes stable diffusion look like Microsoft Paint.

- Trying to generate anything that’s not safe for work is not going to happen.

🖼️ Nano Banana’s Capabilities

- Allows users to make complex photo edits with simple prompts while preserving the integrity of the original image.

- Supports blending multiple images seamlessly, enabling creative outputs like LinkedIn headshots or artistic mashups.

- Offers significant productivity boosts for animators and game developers by generating sprites or animations in a single prompt.

- Can generate realistic images based on real-world locations (e.g., pointing to a spot on Google Maps).

- Includes tools for sketching and visualizing concepts, such as AWS infrastructure diagrams.

🎮 Applications for Developers and Designers

- Game developers can use Nano Banana to quickly create high-quality assets, saving time on character and animation design.

- The tool can generate entire sprite sheets for animations, reducing the need for manual asset creation.

- Developers must disclose AI-generated assets when publishing on platforms like Steam, as Google embeds an invisible watermark (Synth ID) in all outputs.

⚠️ Limitations and Drawbacks

- Struggles with prompt accuracy, sometimes ignoring instructions or producing unintended results.

- Character consistency, while improved, still exhibits an uncanny valley effect in images of real humans.

- Text generation remains imperfect, often introducing errors like extra characters in words.

- Highly censored, preventing the creation of NSFW content.

💡 Implications for the Future of Image Editing

- Nano Banana’s affordability (3.9 cents per image via API) and speed make it accessible for widespread use.

- Raises questions about the future of traditional tools like Photoshop, as AI models simplify complex editing tasks.

- Google’s rumored Grande Banana model suggests even more advanced capabilities, though it may remain exclusive.

- The tool’s ability to manipulate images raises ethical concerns, such as its potential use in creating Mandela effects or altering historical visuals.

AI-generated content may not be accurate or complete and should not be relied upon as a sole source of truth.

📋 Video Description

Try Brilliant for free - https://brilliant.org/fireship and get 20% off a premium annual subscription.

A few days ago, image editing changed forever with Google's release of Gemini 2.5 Flash aka Nano Banana.

The new model can deliver any photo alterations you can imagine while maintaining character consistency. But how good is it in the real world?

#coding #programming #ai

💬 Chat with Me on Discord

https://discord.gg/fireship

🔗 Resources
- https://developers.googleblog.com/en/introducing-gemini-2-5-flash-image/

🔥 Get More Content - Upgrade to PRO

Upgrade at https://fireship.io/pro
Use code YT25 for 25% off PRO access

🎨 My Editor Settings

- Atom One Dark
- vscode-icons
- Fira Code Font

🔖 Topics Covered
- Gemini Flash 2.5 Nano Banana
- Character consistency
- Nano Banana for developers
- Nano Banana bugs