Nano Banana Prompt: 12 Ultimate Use Cases That Will Blow Your Mind

Nano Banana (officially named Gemini 2.5 Flash Image) is a high-performance AI image generation and editing model developed by Google DeepMind. This model has undergone over 5 million blind tests on the authoritative LMArena platform, significantly outperforming mainstream models including GPT-4o Image and FLUX.1, earning the title of the new “king” in image editing.

After thorough testing, I found it even more impressive than when GPT-4o first launched.

This comprehensive guide covers 12 incredible use cases，Let’s dive straight into the examples!

1. Custom Figurine Creation

The trending figurine style that can transform anything into collectible figures.

I transformed my avatar into a figurine – it’s the first time I’ve seen my profile picture with a complete body!

I also created a figurine of my cat, Meat Bun, and the results were surprisingly good!

Prompt

Use the nano-banana model to create a 1/7 scale commercialized figure of thecharacter in the illustration， in a realistic style and environment. Place the figure on a computer desk， using a circular transparent acrylic base without any text.On the computer screen， display the ZBrush modeling process of the figure. Next to the computer screen， place a BANDAI-style toy packaging box printed with the original artwork

2. Virtual Character to Real Person Transformation

Beyond creating figurines, we can reverse the process by transforming cartoon characters into real people.

I recently watched “A Record of Mortal’s Journey to Immortality,” took a screenshot from the video, and had AI transform it into a realistic cosplay photo. The effect was amazing – it felt like breaking through dimensional barriers!

Prompt

This girl is cosplaying as the character in the picture. She’s having her photo taken outdoors at Comic Market.japanese cute girl

3. Element Merging

Banana excels at element merging. You can combine multiple images while specifying actions and clothing. For example, making Ultraman wear GPT’s outfit while doing gymnastics…

For women, this could revolutionize portrait photography! Simply upload your photo, desired clothing, and background – AI will seamlessly combine them all!

The realism is truly impressive!

4. Mood Transformation

Upload a photo and let AI change the mood and background for you.

Prompt

Make it sunny and make her smile

5. Hairstyle Experimentation

If you’re considering a new hairstyle but worried about your stylist’s interpretation, send your photo to AI for reference images, then show them to your stylist!

I previously tried this with GPT-4o with unsatisfactory results, but Banana delivered excellent outcomes.

Prompt

Give me formal hair with a full mustache

6. Text and Icon Integration

AI can directly add text and icons to images. This example shows adding Google and banana (🍌) icons with excellent results.

Note: Chinese text integration isn’t as effective – consider using alternative tools for Chinese content.

Prompt

Put a Google logo and a Banana on her folder

7. Action Synthesis

Use AI for action synthesis by uploading two characters and specifying corresponding actions to generate images with those movements.

This feature is quite interesting and can even create fighting scenes between characters.

8. Perspective Transformation

Transform the perspective of existing photos. If the original angle wasn’t ideal, let AI change it for you.

Prompt

Change the perspective to a high angle, looking down from above as if from the ceiling corner

9. Product Deconstruction

AI can help create product breakdowns. For example, deconstructing a Xiaomi YU7 with impressive results.

Prompt

Ultra-detailed exploded view of a product, metallic parts and electronic components floating in mid-air, perfectly aligned, revealing inner structure, futuristic technology aesthetic, 8K resolution, soft cinematic lighting, highly realistic

10. AR Location Marking

X platform experts discovered a new application: AI can mark specific locations using AR-style annotations.

Prompt

you are a location-based AR experience generator. highlight [point of interest] in this image and annotate relevant information about it

I also found a photo from the internet and asked it to mark the round stadium in the middle, giving it a sense of technological flair.

11. Object Plushification

This technique, discovered by expert Guizang, transforms photographed objects into adorable plush toys. For instance, converting a bubble tea photo into a fabric toy.

Prompt

Design the main object in the photo as a soft, rounded, and airy plush balloon or inflatable toy.Using smooth matte fabric texture, Do not have a plastic feeling. complemented by subtle fabric wrinkles and stitching to emphasize its inflated effect. The shape should be slightly irregular and soft, with gentle shadows and lighting to highlight its volume and realism. Place it on a clean, minimalist background (light gray or light blue) to maintain a playful sculptural aesthetic

12. AI Concept Visualization

Another discovery by Guizang: AI can directly create visual explanations of concepts. I had AI create an infographic explaining “AI Agent” with decent results, though Chinese text rendering needs improvement.

Prompt

Help me generate multiple 16:9 doodle-style images to explain the concept of “Agent” to middle school students. The images should have a consistent colorful, thick-pencil hand-drawn style, be rich in information, feature English text, use solid color backgrounds, have outlines around the cards, and include uniform titles, similar to a PowerPoint presentation