How to make AI images with ChatGPT for beginners

If you're a writer, marketer, communications professional or content creator, and you’ve ever struggled to find the perfect image for your content - these tips are for you.

I’m going to show you, step by step, how to use ChatGPT to make stunning and realistic AI images, even if you’ve never done it before. I’m going to include some use cases and lots of examples, and I’ll share some less obvious tips as well. 

🎥 If you’d rather watch the detailed tutorial video, it’s on my YouTube channel here.

Here’s a basic formula to include in your prompt to generate an image in ChatGPT (or another AI tool):

➡️ Subject + scene or setting + style + details

So, instead of saying:
“Create an image of coffee.”

Try this:
✅ “A steaming cup of coffee on a rustic wooden table, morning sunlight coming through a window, in soft cinematic lighting.”

The better your prompt, the better your image.

⭐️ Image format

One thing to mention here is that because you’re likely creating an image for a specific piece of content, you can specify the dimensions in your prompt. You can tell ChatGPT that you need a square image for Instagram or a wide image for a blog header. 

Here’s an example:

✅ “A square image of a vibrant, colourful smoothie bowl with fruit and seeds, tropical vibes, styled like a trendy Instagram post.” 

➡️ Specify art style or era

Want it to feel vintage? Ask for:

✅ “1970s magazine ad style”

Want a hand-drawn look? Try:

✅ “Children’s book illustration style”

You can also say:

✅ “hyper-realistic”, “surreal”, or “editorial fashion shoot”

➡️ Use photography terms

Use real photography terms like:

✅ "Shallow depth of field" for a blurry background

✅ "Backlit" or "golden hour lighting" for warm, realistic light

✅ “Soft studio lighting” for a polished, professional look

Try this prompt in ChatGPT:

✅ “A woman reading on a couch in natural window light, shallow depth of field, candid photo style.”

🎥 If you’d rather watch the detailed tutorial video, it’s on my YouTube channel here.

➡️Give ChatGPT instructions on what you need specifically.

Instead of just saying:
“A woman standing outside”

Try this:
✅ “A 30-something South Asian woman with curly hair, wearing casual jeans and a white linen blouse, standing outside a small bookshop, smiling naturally”

➡️ Ground them in a real environment.

Place people in realistic scenes:
✅ “at a local market,” “in a messy living room,” “on a rainy pavement”

➡️ Describe the emotion.

Emotion connects with viewers. Use prompts to convey specific feelings and reactions.

Instead of saying:

“A person looking at a laptop"

Try this:
✅ "A young man looking at a laptop with a surprised and excited expression, as if he’s just received good news."

⭐️ Sometimes you may not want a person in your picture.

Try these prompts:
✅ “With their back to the camera”
✅ “Seen from behind”
✅ “An image showing a person’s hands using a laptop” 

➡️ Add imperfections and everyday details.

Perfection looks fake. Real life is messy and there’s nothing wrong with it. 

Try these:
✅“old and dirty trainers”
✅ “a cafe with slightly messy tables in the background”
✅ “a weathered wooden table”

The same applies to people:
✅ “uneven skin”
✅ “thin hair”
✅ “not conventionally good-looking”

This adds authenticity and relatability.

Ground your image in something people recognise - demo

Before you start creating tons of images, it's important to think about ethics. Make sure you're not using AI to create images that deceive your audience, that are harmful, misleading, or infringe on someone else's copyright. Be transparent about using AI-generated images, especially if you’re using them in a commercial context.

🎥 If you’d rather watch the detailed tutorial video, it’s on my YouTube channel here.