AI Image Showdown: Same Prompt, 10 Different Platforms, Interesting Results.

I absolutely love new technology and, as AI is the most groundbreaking advancement in the history of the Virtual Assistance industry, I am all over it.?

New technology and AI are evolving at an unprecedented rate and any VA who wants to stay competitive really should stay on top of these advancements.

Just like our clients, we need to stay relevant to stay in business.

Many VAs say they aren't interested in AI as they offer traditional PA services, but AI is already incorporated into numerous day-to-day admin tools VAs use such as Grammarly and the transcription platform Otter.?

AI can summarise PDFs, transcribe handwritten notes, generate Excel formulas, analyse data, summarise a report into bullet points and 1000 other incredible things. So whatever services you offer, there will be an AI tool to help you do your job faster and better.

Plus, as AI is the future of business, clients are becoming more aware of all the amazing things it can do and starting to ask their VAs to help them understand it and use it to stay ahead of their competition.

It’s a very exciting time in the VA industry and certainly not a time for us to rest on our laurels.

Okay, now let’s talk about AI-generated images!

I’ve been playing around with various AI tools over the past few months and sharing my findings with my All Stars membership group . The All Stars is a place for established VAs to have more “next-level” discussions and take their business up a notch - so they’re all over AI as well.

However, as I’ve been doing more comparison posts in the group lately, I thought it might be a good idea to write up my findings as a LinkedIn article instead.

This way, I can share the article in my other Facebook groups as well as my Coffee Break newsletter .

Right, let's get into it.

Comparing Ten AI Image Tools Using The Same Prompt

The other day I came across Microsoft Designer. I’m a Google gal so I haven’t played around with any Microsoft AI tools that much.

While I was trying it out, I thought it might be interesting to put the same prompt in a few other AI-generator tools to see how they differed.

Bard, Claude and Perplexity Labs cannot generate images so I used:

1. MS Designer
2. Bing
3. DALL-E in ChatGPT
4. Cosmic Dream in ChatGPT
5. DALL-E in Canva
6. Midjourney
7. 123RF
8. NightCafe
9. Leonardo
10. Adobe Firefly

Wanna see the results?

The prompt

"A cosy rainy day inside scene with books, armchair, cup of tea, open fire."

As you can see, I used an incredibly basic prompt for this experiment. I just wanted to see how each platform interpreted it.

The results

1) Microsoft Designer (free)

LinkedIn broke the images in my original article so these are new designs. In the first test, Designer only generated one image. There was no evidence of a rainy day but the image was quite realistic. Nothing was floating and the cup had the correct number of handles.

In these two new pics, it's raining inside and the second image contains two cups of tea with one waiting to be kicked over on the floor.

2) Bing (free)

Bing (which is powered by GPT-4) gave me four images that contained all the prompt criteria.

As LinkedIn broke all of the images in my original article these are also new designs as I failed to save the originals! These look cute, but the original pics had extra cups an incorrect number of table legs and were as cluttered as these ones.

3) DALL-E in ChatGPT ($20 per month)

ChatGPT provided one image that met all of the criteria. It's also detailed with some nice textures and the flame reflections are coming from the right directions.

However, there is a huge amount of steam coming from the cup, the cushions look weird, the spoon is just chucked on the floor and there's an odd leaf/shovel hybrid on the rug.

Although it's not particularly good at hands or text, DALL-E in ChatGPT+ is my go-to image creator as it's great at creating the pop art images I use in my content.

4) Cosmic Dream (a feature inside ChatGPT Plus)

All images generated by Cosmic Dream are in this style so it's a bit different than the others.

But the cup is floating in mid-air and puffing like a steam train, it's "raining" inside and the image contains random, unidentifiable objects.

5) DALL-E in Canva (Included with free & paid plans)

This is the best Canva could come up with. Originally, Canva did generate "real life" images but they were dreadful. After that, it only gave me shonky picture book illustrations like these.

I pay for Canva Pro but I rarely use the text-to-image generator because, and I think you will agree, the results are subpar.

6) Midjourney ($10 per month)

While a bit of a mess to use, Midjourney is quite astonishing and is currently the daddy of AI imagery. I don't use it much because I feel ChatGPT provides the results I need and I don't use the kind of realistic images it can generate.

You can give very detailed prompts to Midjourney (Wes Anderson style, cyberpunk, vivid neon etc) and it's known for creating images that look like real people.

These are the results from my basic prompt though. If you look closely, flames are coming out of a jug in pic one (and no teacup), the huge cup in pic three has two handles and there is a weird glass cup in pic four.

I don't think these are very good but, to be fair, the prompt was very basic for Midjourney and it's far better at creating more realistic images like this one

7) 123RF (You purchase credits)

The results are pretty boring and basic but meet the brief and the light is coming from the correct direction. I only buy extended license images from 123RF and I don't use the image-generation features.

However, the site is good overall and has most of the features offered by Canva including background remover, image extender, and background remix. You can also ask it to create variations of existing stock images.

8) NightCafe (Free)

These images from Nightcafe did not meet the brief as there is no fire. But the reflections from the candle are good, there are no random objects floating around, and the chair has the correct number of legs.

9) Leonardo (Free credits and then you buy more)

These are pretty good at first glance. They meet the brief (aside from image one which has no fire) and everything has the correct number of legs.

But there are additional cups in pics two and three, the cup is also floating above the chair and the reflection from the fire is coming from the wrong direction in image three.

10) Adobe Firefly (Free)

As you can see, Adobe only generated illustrations. I tried to edit the prompt to get real-life images but it wouldn't play ball.

AI I used in this post

I did not use any AI in the content of this article but I did ask ChatGPT to create 10 suggestions for the headline. My request was very simple:

"Please create an engaging title for a LinkedIn article I'm writing. The article is on comparing different AI image-creating platforms using the same prompt. It should be short and snappy and make people want to click to read."

I used a combination of headlines and then edited it again myself. I then asked for a visual representation of the headline I chose.

This is the image it generated.

As the image was square, I uploaded it to Canva and used their Magic Expand feature to make it the right size for a LinkedIn article header.

Canva can be hit and miss at this task but I actually liked every single design it created.

What do you think?

Are you using any of these AI image-generating platforms yourself and which platform did you feel provided the best and most accurate images based on the prompt?

Jo. x

~ View a more in-depth version of this experiment on my website

~ Join over 22,000 global members in the VA Handbookers Facebook group