I Asked ChatGPT 1.5 Image to Turn My Wife into Mona Lisa

OpenAI released ChatGPT Images, but can it be the replacement of Nano Banana?

OpenAI released a new Image model yesterday. How to initiate it?

ChatGPT Image

Visit here. Select any style to try fast.

After selecting the style, you are prompted to upload your photo, and a new chat opens with the adjusted prompt.

My wife as The Girl with a Mona Lisa portrait.

My Wife and I- American Gothic by Grant Wood

Dramatic

3D glam Doll

Old Photo

Create a Holiday Cart

Now let’s test the best image generation prompts with Nano Banana Pro and ChatGPT.

You can start ChatGPT Image by selecting Image as the tool or just by pasting the prompt, but selecting Image works more reliably.

1. The List of Best Prompts for Image Generation

Man Sitting on the Street

A photorealistic wide drone shot of a colossal man (exact face/body from the reference) casually sitting across a London street, one knee raised, hand resting. He wears a navy overcoat, knit sweater, dark trousers, boots, and a minimalist beanie. Tiny cars, buses, bikes, and pedestrians move around him, with classic London red-brick buildings, black lamps, and cobblestone streets dwarfed by his size. Soft overcast London daylight highlights wet pavement.

Recursive Images

Recursive image of an orange cat sitting in an office chair holding up an iPad. On the iPad is the same cat in the same scene holding up the same iPad. Repeated on each iPad.

Character Consistency Selfie with Movie Character

I’m taking a selfie with [Leonardo DiCaprio] on the set of [Inception].

Keep the person exactly as shown in the reference image with 100% identical facial features, bone structure, skin tone, facial expression, pose, and appearance. 1:1 aspect ratio, 4K detail.

Unfortunately, ChatGPT could not create or edit images due to possible copyright issues.

2. The List of Best Prompts for Infographics

Let’s create infographics.

Concept Visualization (Text to Infographic)

Create an educational infographic explaining how Large Language Models (LLMs) work.
Visual elements: user prompt input, tokenization, neural network layers, training data, and generated text output.
Style: clean, flat vector illustration suitable for a high school AI textbook.
Use arrows to show the flow of information.
Labels: clearly label each element in English.

TimeLine

Create a detailed infographic on the history of rock music, the illustrations in montage photo real newspaper clippings, include dates and a timeline, music genres and styles to music today in 2025. 1x1 ratio.

Whiteboard explaining concepts

convert [how image generation with LLM] into an image of a professor explaining the content on a whiteboard in English. Use diagrams, arrows, boxes, and captions to visually explain the core ideas. Use color as well.

3. Vault

Just shipped Infographics Studio to the Vault.

Pick your topic

→ Select type (timeline, comparison, process flow)

→ Choose style and colors

→ Done.

One click. Publication-ready infographic, using Nano BananaPro API.

Also added 50 NanoBanana Pro prompts you can preview and test.

No prompt writing. No design skills. Just clicks.

The Vault is available to paid subscribers. After subscribing, visit the Vault, sign up with the same email you used on Substack, and access it.

Thanks for reading!