Midjourney V5 + ChatGPT-4 = GOD MODE (FULL PROCESS)

We're gonna be putting MidJorney version five and chatGPT 4 together to harness the great powers that they contain .

And we're gonna be building better prompts and making the most of these new technologies .

We can imagine a chatGPT 4 as a wise wizard who has trained for many years , we can go to the wise wizard and ask him to define us an articulate and specific prompt for different contexts .

Dear Wizard , can you give me a prompt for a sweet lady protagonist for my film about cheese?

Of course, Young just put eight K at the end to perform this process, we will train chaGPT 4 in the art of prompt writing and help refine its outputs.

After this, we'll look at how these prompts come out in MidJorney and look for ways to improve our prompt writing wizard .

So let's dive right in.

The first step is to come to chatGPT make sure we set the model to chatGPT 4, and start a new conversation.

And what we're going to do is we're going to prime chatGPT 4 to act as our wizard prompt writer .

And to do that , I'm going to inform it that you need to act as a prompt engineer.

You will write me prompts for an AI art generator called MidJorney .

I will provide you with short content ideas, and your job is to elaborate these into full, explicit, coherent prompts.

So here I've defined the task.

I've told it what it's going to act is, and now I'm giving it more context around what an AI R generator is,

what a prompt is, and how I would like the response.

Formatted prompts involve describing the content and style of images.

It is useful to be explicit and use references to popular culture , artists and mediums .

Your focus needs to be on nouns and adjectives.

This prevents chatGPT from going off and describing in flowery ways the vacant gaze that somebody's having that reminds them of the first day of autumn .

And we're asking chatGPT to actually define what that would look like at the eyes are focused on something in the distance rather than they have a vacant stare.

I love to think of these prompts as casting spells into MidJorney, and with the right combination of words, we can elicit infinite possibilities.

When guard your MidJorney .

I then go on to tell it .

I will give it some example prompts to use .

Please define the exact camera that should be used.

It's helpful to get an exact camera lens if that is the medium you're using because it helps define the precise aesthetic we're looking for.

I then gone on to say Here is a formula for you to use brackets content.

Insert nouns here .

Medium inserts artistic medium here style.

Insert references to genres, artist, and popular culture here.

Lighting reference.

The lighting Here Colours reference the colour styles and palettes here .

Composition reference the cameras , specific lenses , shot types and positional elements here .

What I've done is broken the prompt down into specific variables so that we will make sure we get adjectives relating to these different component parts of an effective prompt .

This will make sure that we have accurate defined language for the whole array of possibilities of our prompt .

When giving a prompt , remove the brackets , speak in natural language and be more specific .

Use precise and articulate language .

Always output , meet two full prompt options .

This means that we'll get two options every time we ask for a prompt .

So this can be great for simultaneously creating different images inside of mid journey .

And it also gives us a little bit more flexibility to either choose one or the other or even combine parts of both into our own unique prompt .

Finally , I've given in it one example prompt to give us an idea of how I would like the output to be to get the most out of chatGPT .

It's important to give it a lot of contextual information.

ChatGPT four now takes up to 25,000 characters in contextual information, and this allows us to give it a lot more information, which it then can include in its own intelligence, allowing us to give it a lot of information and ask it to reflect and interpret that in original ways.

An interesting use case that I recently saw was somebody took a new feature from a coding language and input it the entire documentation into chatGPT form and asked it to spit out a tutorial that was aimed at beginners.

So we're taking really advanced, complex language and we're asking chat GPT to output us a more accessible version of that information.

So let's take a look at the content that we've got from chat GPT for our first prompts.

The first one is a tranquil underwater landscape medium oil painting style inspired by J.

M.

W.

Turner is the great Turner and HR Geiger.

So Turner was an English painter who worked explicitly in oil paints and created very beautiful atmospheric Seascapes.

Now, the first thing I noticed is that it still included the brackets.

So I will retrain chat G BT by asking it to rewrite the prompt without the brackets .

But brackets are the young boy I know more than you , wizard.

OK, so this is looking much better.

What we're gonna do is we're gonna copy this prompt, and we're going to hop into MidJorney .

We're gonna make sure that we're using version five of the algorithm.

Now we're gonna type in forward slash imagine paste in our brand new prompt, and this is gonna spit us out something quite remarkable.

And simultaneously we can come back and do the second idea as well .

Now , these are just ideas we've asked from chatGPT , but what we can also do is we can ask it to do something of our own evolution .

So I'm going to ask chatGPT for a vintage travel poster of the Alps .

Let's see how it gets on with this request , and we're gonna hop back into MidJorney and see how it's getting on with our original requests .

So the first prompt we put in was a tranquil underwater cityscape oil painting by J.M .W .

Turner , with warm , ethereal sunset lighting filtering through the water .

The colour should be rich blues , teals and warm oranges capture the scene with a wide angle lens , and it's created a pretty interesting concept piece here .

Let's upscale a couple of these .

Wow , it's fantastic how it's got this juxtaposition between the underwater scene and the cityscape on top , and the second problem I put in was a futuristic garden party with robots and people mingling it in the style of Alfonso Musa , who is a very popular artist to imitate .

He had an Art Deco style and created a number of stylistic advertisements in the early 20th century .

Also , please forgive me on the pronunciation of his name .

I believe I always butcher it .

But for the record , Alfons Mua Mua Alfons MUA is the British Alfons Mua .

And if you're interested in the American A A Ok , enough of that tangent .

Let's get back to our Alfons Mocha Robotic Garden Party and upscale a couple of these for a closer inspection .

And you can see we've got this very distinctive interesting concept of a robotic party in the style of Alfons Mocha.

I like it , but let's actually try the prompt that we've asked it for .

So now we're going to look at our vintage travel posters .

I'm also going to change the aspect ratio for this and make it vertical .

So for that , I'll change it to Dash Dash a R two by three.

This means that we're gonna have a poster outputted and for every 200 pixels of width , we're gonna have 300 pixels of height.

Now we're gonna go again with the second option and try that again with a two-by-three ratio.

In the meantime, we're gonna whack another one inside of chatGPT .

This time we will go for street photography portraits in New York.

MidJourney version five has really taken the levels and quality of AI art to new heights, and specifically, photo realism has increased immensely.

The details on finer elements of human anatomy are now so precise that it's becoming harder and harder to distinguish between AI art and real photography.

One thing that is rendered particularly well inside of Mid Journey now is hair strands of hair .

Wait, do you get to my age ?

And I'll show you the of hair boy .

Wow .

And look at these beautiful vintage style posters that we've now gotten outside of MidJorney .

Absolutely mesmerising .

These would work well for home decor.

If you're interested in a business idea , I can suggest creating very specific travel posters for different locations and opening an Etsy shop really targeted at a specific place that has a high number of rental properties .

Because Airbnb renters love to put specifically inspiring artworks that are relevant to a space on their walls , I think that is a great opportunity to monetize a piece of work like this .

Wow , look at that one .

I adore it .

The the colours and the composition are fantastic , and I really like the difference we've got between the two options , with the first being slightly more saturated with these brighter reds and the second having a more nuanced approach with these more pastel colours .

Now , you may have noticed that still , the text is being rendered pretty horrendously inside of mid journey , and this is something that hasn't been improved very much in version 51 thing they did mention is that they are trying to remove unnecessary text where possible , and there is some notion of that happening , and there is less text appearing in a lot of places .

But what we can always do is take an image like this and really help ourselves stand out by actually adding our own text .

You can use a tool like fig to easily add our own text .

You can paste an image in easily , and what we're gonna do here is actually we're just going to crop the image by drawing a frame with the F key and pasting the image inside this frame .

Then we're going to extend the image upwards to give us some room at the top to input our own text .

we're going to put in our own writing .

I'm gonna try here , pick a suitable font .

I'm gonna choose pints this time wack the font size all the way up to 100 and 60 .

Change the fun style to bold and we're gonna select a colour from inside of the artwork .

Make sure that we've got the whole word on one line and I'll slightly increase the letter spacing When you're using all caps , it's important to slightly increase the letter spacing .

I check my spelling of Shay there and I am correct .

Christ , being dyslexic sucks .

Thank God for a I , but one should not blame or one's ills of poor spelling on dyslexia , you can quickly take an image and actually vastly improve the quality that you have by adding your own text .

This is something that AI is massively struggling with still, and it's very interesting to see that it has overcome the issues with hands and guns .

Yet the text is still something that it is suffering with .

Another area the V five is still not able to deal with is being able to create specific elements, remember them and put them on future works .

For example, you could create a character and then reuse the same character in future.

The same goes with objects and locations .

But that's something hopefully we'll see before too long .

But here is my vintage travel star poster generated with MidJorney and chatGPT.

But let's have a little look at how we're getting on with our street photography.

Wow, these are beautiful.

Absolutely mesmerizing, really .

But you can also allow chatGPT to come up with its ideas.

So I've asked it to give me five.

Varied ideas include two that are photorealistic and one of a beautiful woman , and we'll take a look at the artwork that Chad G .

BT wanted to make .

What does the A .

I desire?

Hot air balloon scenes ?

Wow, wonderful French countryside.

And for the beautiful woman, it has A it has a Japanese woman in traditional attire.

It is interesting that I would say perhaps there is an inbuilt bias there in chat GP t to give us a very diverse output rather than a very, possibly narrow version of the most likely output.

And then we have a fantastic street scene.

So thank you, GPT, for your contribution to the art here.

I love just scrolling through the MidJorney community feed and seeing what people come up with.

And you would have to say that at least half of the images that are generated are based around attractive women, which is great because I love beautiful women .

I could also ask chatGPT for its opinion on:

Why is the majority of art created based on attractive women and chat?

GPT has told us that the prevalence of attractive young women and AI-generated art can be attributed to several factors reflecting both the biases within the A i itself and the preferences of the users.

Should we address this?

I don't think we should.

I don't think there's an issue with people choosing to engage beautiful women, but it is something that happens.

If anything , it's very interesting to me that I on one hand, I enjoy looking at attractive young women, but it seems almost fleetingly enjoyable.

It's a bit it is like watching pornography that it is fun, but it's very hollow .

I think there is more depth, more nuance, more beauty to be found in other places .

Creativity comes from combining tools in original ways and using the strengths of chatGPT and MidJorney allows us to create advanced, articulate prompts.

Check out my A I courses in the description below , and make sure to watch this video next for more on the state of A I .