When you purchase through links on our site, we may earn an affiliate commission.Heres how it works.
BothMidjourneyandChatGPThave recently released new versions of their AI image generators.
But, when put against each other, which is best?MidjourneyV7 or ChatGPT 4o image generation?
Left:ChatGPT /Right:Midjourney
With that in mind, these were the steps I took first.
For Midjourney, I used version 7.
This is the latest version but it is still in an experimental phase.
Left:ChatGPT /Right:Midjourney
Midjourney produces four versions of each image compared to ChatGPTs one attempt.
Photorealism
Prompt:Create a photorealistic image of a puffin flying over a cliff face with water below.
In the background is a mountain range.
Left:ChatGPT /Right:Midjourney
The image, while potentially over-saturated, is photorealistic.
On top of those points, it included the two people looking through the binoculars.
Sure, they arent looking at the puffin but otherwise, this is pretty spot on.
The original image given to the AI models
Midjourney
There is a lot going on here.
I cant disagree that everything has been included.
However, lets address the elephant (or puffin in this case) in the room.
Left:ChatGPT /Right:Midjourney
The puffin is giant and could take on Godzilla if needed.
The image also isnt really photorealistic, looking slightly more like an oil painting than anything.
Even with puffin sizing issues aside, I still think ChatGPT understood the cues more accurately.
Left:ChatGPT /Right:Midjourney
Both models created water underneath a cliff face, but ChatGPT understood the context of the prompt more accurately.
Winner: ChatGPTwins this one in just about every single way.
ChatGPT, on the other hand, nailed the brief.
Left:ChatGPT /Right:Midjourney
In the background is a river, and in the far distance is a forest.
However, all of the key details are here.
Despite all the details required, ChatGPT produced a high-quality and very detailed image.
Left:ChatGPT /Right:Midjourney
While Midjourney achieved the same image, it was the smaller details that were off.
Winner: ChatGPTtakes this one.
Again, I cant really fault the models work here.
It put the exact photo I supplied into the stylings of the Renaissance era.
Yes, this was the best of the four attempts Midjourney gave me.
I do see where the model was trying to go here.
It just couldnt quite make it.
I assume the brown border is also supposed to fit the theme?
It’s hard to tell.
It did exactly what I asked for.
It seems like Midjourney got halfway through and gave up.
It is set in a big bustling city.
Our detective takes centre stage, with a bustling (and rather futuristic city) nestled in the background.
It did take the prompt quite literally for text, adding the requested data with a slogan.
Overall, its impressive.
What Midjourney lacks in detail here, it makes up for with style.
Arguably, the skyscrapers look better here, and there is a lot more to see in this image.
Sadly, Midjourney falls behind with its blurry details.
While its more interesting, there is just too much wrong here.
Midjourney, on the other hand, just got too many things wrong here.
I do, however, like the direction it was going in.
Detail often trumps style.
This poster did everything I asked for, and more importantly, got all of the text exactly right.
While the poster is boring, it has hit the brief and achieved a tricky challenge for AI models.
I also like the energy it was going for with the picture of the band in the middle.
However, other than the words The band not a single bit of the text is readable.
Winner: ChatGPTmight not have been incredibly interesting here, but it completed the task perfectly.
As Midjourney showed, it is not always easy for AI models to deal with text in images.
When AI image generation first came about, one of the easiest ways to identify it was hands.
They would have incredibly long fingers, or fingers sticking out of the wrong places.
Now, while the hands here dont quite look completely human, the accuracy is really impressive.
Midjourney did a fantastic job here.
What I think is especially impressive about this image is the detail.
While the ChatGPT image is instantly recognisable as AI, this could pass for someones hands.
The only noticeable issue is the finger behind the glass not looking quite right.
It is also a very strange way to hold an orange, but each to their own.
Winner: Midjourneystole a win on arguably one of the best-known flaws of AI.
This goes to show how far it has come.
This isn’t to say ChatGPT did badly, it just didn’t quite match up.
Even though this doesnt exist, I want to eat it.
Just like ChatGPT, Midjourney did an excellent job here.
This looks like a real bowl of pasta that you would get in a nice restaurant.
There are even some random tomatoes and garlic scattered around, I assume for decoration.
Verdict: ChatGPT wins
Sadly for Midjourney, this wasn’t even close.
However, this latest version of GPT image generation is only a week or two older.
While the model’s were occasionally evenly matched, ChatGPT just so often excelled where Midjourney didn’t.
