The new GPT Image 1.5 vs Nano Banana Pro: Who Has the Better Image Model?

The AI image generation landscape just got more competitive. OpenAI launched GPT Image 1.5, which brings significant improvements to their image generation capabilities compared to their last model. Google's Nano Banana (Pro) on the other hand has already been blowing our minds for a couple of months.

For professional creatives, the question is clear: which model delivers better results ? To illustrate the differences between these two models, we generated the same images using both GPT Image 1.5 and Nano Banana Pro.

Let's break down how they compare across the dimensions that matter most to professional work.

This is a developing blog post. More examples are added throughout the day.

Style adherence

ChatGPT Image 1.5

Generated with ChatGPT

Nano Banana Pro

Generated using Pablo for Photoshop

Prompt: los angeles landscape skateboarding shot with the following style: late 1990s documentary street photography shot on 35mm color film, Leica M-style rangefinder camera with a 35mm lens, Kodak Portra 400 color palette, natural daylight, soft contrast, muted realistic colors, embedded film grain, slight edge softness, observational candid framing, no HDR, no modern digital sharpness, no cinematic lighting

GPT Image 1.5 wins

Only GPT image 1.5 correctly applied the film grain characteristic you would expect from the prompt. Nano Banana Pro on the other hand generated noticeably sharp image that doesn't align with the request.

Photorealism Test: iPhone Photography

For our second comparison, we tested how each model handles modern photorealistic rendering with a prompt designed to mimic contemporary smartphone photography.

ChatGPT Image 1.5

Generated with ChatGPT

Nano Banana Pro

Generated using Pablo for Photoshop

Prompt: A photorealistic photo a young woman at a calm Amsterdam outdoor restaurant on a crisp March morning, with shallow depth of field, shot using an iPhone

Nano Banana Pro wins

Nano banana generates a photo you would expect from a phone, while outputs GPT a telltale AI-generated look. Nano Banana even went above and beyond by adding signage of an actual Amsterdam cafe (though the location of the cafe is incorrect). Moreover, Nano Banana's output is more winter 'crisp' as requested.

Aspect Ratio

Aspect Ratio	ChatGPT Image 1.5	Nano Banana Pro
1:1 (Square)
3:2 (Landscape)
2:3 (Portrait)
4:3
3:4
16:9
9:16
21:9

Nano Banana Pro wins

Nano Banana supports 8 aspect ratios, whereas GPT 1.5 only supports 3.

Resolution

Resolution	ChatGPT Image 1.5	Nano Banana Pro
1K	(square only)
1.5K	(landscape/portrait)
2K
4K		(via upscaling)

Nano Banana Pro wins

Nano Banana supports way better resolution than GPT Image 1.5.

Generation Speed

Output Size	ChatGPT Image 1.5	Nano Banana Pro
1K	30-45 seconds	10-15 seconds
1.5K	50-60 seconds	N/A
2K	N/A	30-60 seconds
4K	N/A	Multiple minutes

Nano Banana Pro wins

3x faster at 1K: 10-15 seconds vs 30-45 seconds. Faster 2K generation (30-60 sec) compared to GPT's 1.5K (50-60 sec).

API Pricing

Resolution	ChatGPT Image 1.5	Nano Banana Pro
1K	~$0.15-$0.17	~$0.15-$0.17
2K	N/A	$0.15 - $0.17
4K	N/A	$0.26 - $0.28

Nano Banana Pro wins

Nano Banana has comparible pricing for 2K as GPT's 1K (~$0.15-$0.17). Better value proposition with higher resolution at same cost.

Edits

Feature	ChatGPT Image 1.5	Nano Banana Pro
General editing
Adheres to intent

It's a tie

Both support general editing capabilities. Both adhere to user intent reliably.

Reference Images

Feature	ChatGPT Image 1.5	Nano Banana Pro
Supports reference images
Control fidelity level
Max reference images	5 (with 'high' fidelity)	14

It's a tie

GPT offers fidelity control for reference matching. Nano Banana supports more reference images (14 vs 5). Different strengths make this category even.