I think it has to start with
your idea of a story, right? I think, you know, people might
think, okay, you press a button, it spits out a book, but I think it
has to start with your imagination. And then we will provide that to ChatGPT
to kind of give us a base for our story. I think then we'll iterate with ChatGPT
almost like a brainstorming partner. We're gonna go back and forth. We're gonna expand on characters
and the arcs that we might want to, you know, go through. And I think once we have that,
Then we go back to imagining again. We have to think through how do you take
that script and that story and you bring it to life, how do you visualize it? And that's where MidJourney comes in. And we're gonna generate art that
fits that narrative and expresses that narrative in a really nice way. And then we can combine it all
together with you know, pages to create that book format. Hey everyone, and welcome to
the Hitchhikers Guide to ai. I'm your tour guide AJ Aser, and in this
podcast I explore the world of artificial intelligence to learn how AI will
impact the way we live, work, and play. Now, if you're a parent like me in the
middle of reading a book to your kids, this thought may have crossed your mind. Hey, I think I could write one of
these, but the idea of writing and publishing a children's book to many. Is a distant fantasy that is until
now, because generative AI is making it easier than ever for anyone to
become an author or illustrator. Just like today's guest, Ammaar Reshi
who wrote illustrated and published a children's book for his friend's
children in one weekend using the latest AI products including ChatGPT
and MidJourney in this episode. Ammaar's going to show
us exactly how he did it. So Hitch A Ride with me is we explore the
exciting world of generative AI in this episode of the Hitchhiker Guide to ai. Hi Ammaar it's great to
have you on the podcast. Hi. Great to be here, AJ. How are you doing? I'm great. I'm so excited for you to join me on
this podcast especially to be one of the first people I'm interviewing. It's gonna be a learning experience for
me, and we'll work it out together. But anyway, I'm so
excited to have you here. I talked about you in my newsletter in
the first post because I thought what you did by publishing your book, Alison
Sparkles, was such a great example of how AI is gonna change the world around
us and really make creativity and being a creator a much more achievable and
approachable thing for most people. Since your book was published on Amazon
in December of last year, you have sold, what is it, over 900 copies. Is that right? Yeah.
It's about 1,200 now, so yeah. Crazy That is amazing! Yeah, it's been wild That is so cool. And at the same time, you've found
yourself at the center of a growing debate about AI and the future of art. So tell us how it all happened. Rewind us back to the start. What made you a designer at a tech company
decide to publish a children's book? I guess what kicked it off to go
all the way back to two of my best friends basically had their first kids. And I went to visit one of them. She had turned one years old. And I went over and it was around
her bedtime where she grabbed my hand and took me upstairs. And I was like, what's going on? And they're like, she's picked
you tonight to read her bedtime story . So I was like, wow. I was like, I am honored. This is one step closer
to being that cool uncle. She hands me this book I was
something about getting all these animals delivered from the zoo. And so I was, I mean my friend was
there and I was reading her this book and we were both laughing cuz we were
like, this book makes no sense at all. This story is so random. But she loved it. You know, she loved it. She loved the art, she
loved everything about it. And it then kind of hit me in that moment. I was like, it'd be really fun to
tell her story of my own, you know? I just had no idea how I was
gonna go and do that yet. I told my friend, I was like, I
think the next time I come over, there's gonna be a book on her shelf. It's gonna be mine. And he was like how are you gonna do that? I was like, well, gimme a weekend. I'll figure it out, right.. I had already been playing
with MidJourney like sometime in February of uh, last year. And so, You know, I, I knew
generative AI and the artwork stuff was there and it was really cool. And Dall-E also had blown up around then. And so yeah I knew okay, if I
wanted to illustrate this book, I could lean on MidJourney to help
me with some of the creation, but I hadn't yet come across ChatGPT. And a friend of mine actually, just
that moment, like that Friday message meeting, he's have you seen ChatGPT? I've been playing with
it all weekend, all week. I've even created music and chords and
like chord progressions and stuff with it. And I was like, that's crazy. Like I wonder if it could help me
craft a story, like a children's story. And then I wanted the story
to be something a little meta, you know, something about. But also a little personal. I remember as a kid, like my dad let
me play with his computer when I was like four or five years old, right? And I, that kind of led me down the
path of going into tech and like all of that and that curiosity. And so I basically
wanted to mash those two. It was this young girl who's curious
about technology, and specifically about ai and then ends up making her own. And that's essentially the prompt that
I gave ChatGPT and that's what set off, the path into making this book. That is such a cool story. I think the bit you talked about where
you're like reading this book with a child and you're lucky because as an uncle
you don't have to do it a hundred times. That's what he said. Yeah. Yeah. It can get pretty tiresome and you're
like, and you do wonder often wow. This book doesn't make a lot
of sense, but like hundreds or thousands of copies have been sold. It's really cool that you took
the initiative to do that. Now, you were in the Washington
Post recently in an article titled he made a children's book
using AI, then came the Rage. Talk us about that. Why did you make so many people
angry with the children's book? Yeah, that was also
dramatically unexpected. So when I first created the book on
that weekend, my goal was like, I need a paperback in hand as soon as possible. And Amazon, KDP, which I think is the most
underrated part of this whole discussion, where it's like there's a platform
out there that can get you a paperback within a week , just upload a PDF. No one talks about that. I used KDP, got the book and
initially, just gave it to my friends. That's, that was the goal. And it was out there. And then, I was like, this would
actually be really fun to share with other friends as well. And so I put it on my Instagram
and have a good amount of friends who are not in tech, and so they
replied and I put in my story. If you want a copy, I'm
gonna gift it to you. Let me know. And so a lot of folks were
like, oh, this is so cool. I want a copy. I want a copy. And everyone's reacting
in a super positive way. And so this is forming my initial
um, You know, opinion of how the story is going to be perceived. It's going to be perceived in a
way where everyone thinks this is very cool concept, right? Like the same way I thought it was. But boy was I wrong. Then after the Instagram story, and I
think this was the most Instagram messages I've received in a while in one go. A friend of mine was like,
you gotta put this on Twitter. I think everyone should see this. And I was like, okay, yeah, why not? So I quickly drafted up a tweet and
put it out there first 24 hours. Tons of love and praise. You know, I had parents reaching
out saying, I wanna make a book with my child over the weekend. Can you walk me through it? Then I vividly remember it
was like 4:00 AM the next day. And my phone is just
buzzing like it is going. And I'm getting all these
messages and it's you're scum. Like we hate you, like
you're stole from us. I was just like, whoa. What is happening? And at the time, I hadn't read up on
what had happened with Lensa or any of these other AI tools that were
allegedly being trained on copyright material and and art without consent. And I had not, I was just
not aware of any of this. I was digging into it and I
was like, why am I getting all this hate all of a sudden? And I realized that I'd been
retweeted by some artists who had very large followings. We're talking about 40, 50,000 people. And I think then Tim Ferriss liked the
tweet and I just blew it up to another yeah, I think he has like a million
followers who, another, huge set of folks. And then it was spreading across like
illustrators, writers, artists, and. and I know why they have
these concerns, right? It's like you're seeing a piece of
technology that is doing what you do on a day-to-day basis without
you involved at any single part of that creation of that cycle, right? I think AI, we've been talking
about it for forever, right? Especially if you've been in
the tech field for a long time. , but it's felt abstract. It's not tangible. And now you finally have this physical
object that blends in with everything else that's out there, a children's book. And if I didn't say it was
created by ai, I think most people would've just said, oh, it's just
another random children's book. And so I think that provoked
the discussion and created that fear that, wow, this is not. AI is good. It's so damn good that you could publish
a book and it could be out there and no one would know, if you didn't say so. And I think that struck a chord and
that led to the reaction that I got. Death threats, everything in between. It was quite, quite the storm. I found myself caught in right after that. Going through that experience
you saw this other side of ai. , as people in tech that have been using
ai, probably with this optimism and excitement, you don't really realize
how folks that aren't as familiar with it or folks that really find
it threatening to their livelihood see how it might impact them. One thing I'm curious about is did
you experience or hear from any artists that thought about it in
a positive way or excited about AI and how it could help them? I did get a few dms and there were DMs. They literally said, I don't
wanna put this out there. They started the DM with that. So I think there was already this
fear of backlash based on how the broader community was reacting to this. But they had said that They find this
really exciting because of the way it could speed up their workflows. They saw it as an opportunity
to brainstorm faster, come to concepts much faster than they
could, and then use, their skill to hand draw and expand on that. And I think that's really promising too. It's that view that this is supplemental
and not a replacement and actually can fit into your existing workflows. I think that's really exciting. . And I think the problem is like the
rhetoric around all of this is stuck between it's being conflated, right? It's one on the one hand, this is a very
exciting progression in technology because you're enabling a new set of creators. People who, could imagine all of
these things, but couldn't dream of creating them because they
were limited by their skills. Maybe they couldn't pay for the
courses or anything like that, right? And now your imagination's limit and
the technology is just empowering you to create, which I think is amazing, right? We're gonna get a whole new set of people. I'm sure there are young Spielbergs
out there that now can create things they couldn't be for. Very awesome. But it's being conflated with the
other, A aspect of this, which is it is being trained on copyright material,
it is being trained on work that's out there without people's consent. And I. , you do have to address that. But at the same time, you can still
be excited about where this is going. And unfortunately, it's become this blob
of an argument where it's just bad period. And I think that's what people need to
unpack because there are a whole set of artists out there who also think
this is very cool and would just like it to be trained in a more ethical way. Which yeah, I would be So for that,
I'm not anti artist in any way. It's Let's enable the artist to create,
cuz again, their imaginations allowed this tool to exist and create some
things that we couldn't even imagine. So imagine what they could
do combined with this tool. I'm sure we'd see stuff we haven't even
imagined yet which is even more awesome. Yeah. A lot of people make that argument in
the same way that you know, that I think this is like a classic business argument
of the early part of the 20th century where the factories came and people
thought it was gonna replace jobs, but it actually created more opportunity
and more growth in the economy, but it's hard to see that viscerally
when you see it impacting your work. One of the interesting things
about AI is there's been this inability to predict what will be
easy and what will be hard for ai. So for example, you and I can learn to
drive a car maybe in about 10 hours, and that actually is really hard for AI. But for me to become an illustrator
or a master chess player as a different example, would
probably take many years, right? I couldn't imagine myself
becoming an illustrator. If I pick up a pen or, or a, a
paint and try painting, it would take me a really long time. But AI has learned to unexpectedly
quickly, which is really interesting. And you went through this experience
now after you went through this and experienced that, that kind of wave
of first people being really excited and then people really being mad
at you how did you feel after that? Did it stop you from wanting to go out
there and make more stuff like this? Or did you keep going? it Was interesting because in the
beginning it kind of forced some introspection, some reflection on
like, why did it strike such a chord? What could I have done differently? I think realizing and seeing that,
okay, this is copyright material uh, in these companies as well of really
kind of dodging this question, right? I think I watched an NBC nightly
short where David Holz from MidJourney is asked Hey, you're
caught in this copyright arguing. He's like, I don't wanna
talk about that basically. I think they, these things
aren't being addressed and. I was like, okay, I still
really enjoy creating with this. I think it's allowed me, like I
said, I felt empowered when I was using these tools and I'm sure
a lot of other folks do as well. But I was, I was not going to continue
to monetize with the art I think. The book itself was just an experiment. And then, and again the only way
to get that paper back really quickly was to put it on Amazon. I didn't take the book down,
which is another counter-argument you could give to me. Okay, if you don't wanna monetize,
why is the book still up there? well, I, we left the book up
there because I think it, it sparked an interesting discussion. And that discussion is now at a
point where, we are having this, we are having this conversation. The Washington Post has elevated
this conversation and I think the pessimistic point of view is oh, this
is a quick cash grab or whatever. But I think the somewhat optimistic
point of view the realist in you says okay, this discussion has now
gotten so much light that we might make more progress on our concerns. I think if you look at it that way
the pragmatic point of view I think. . I think that's why the
book is still up there. It's, we are now talking about this
all over the place and it'll might actually lead to progress with, with
getting these companies to maybe do things in a more responsible way. So that's where I like, did not continue
on the monetization path, but that didn't stop me on the creation path because I
think it's still really cool to see how these tools can bring your ideas to life. And a book was just one of
the ideas that struck me that. But then as I was browsing Twitter one
other weekend , I saw this like very short animated clip where someone had
just animated this person, walk into a tavern, seen this mysterious and I've
got sucked into this very short clip. I was like, this is so intriguing. And. and that was before I realized that it was
actually made using immuno generative ai. And I was like, what? Like how did they do this? There was no source to
who made this video. And so I had to just spend like a
few hours just de decomp and thinking about how they did this in reverse
engineering the process in my own head. But it got me so excited again
because film is one of my. Favorite like things, it's like
a hobby of mine to watch and log all the movies I watch. If I didn't study computer science,
it definitely would've been film. And so to then see an avenue where I
could tell my own story and animate it and create it was super exciting. And yeah. And then one weekend I
was like, you know what? I'm gonna do this . I'm going
to try to create my own short. And I do it with one of my favorite
superheroes, Batman, which I think has like such a great audience as well. Like lots of people love the superhero. So it. To tell my own Batman story, and
that's when I decided to make a little Anma animated short. And again, tweeted about it this
time, racing for impact a little bit given previous reactions. And within a few days
it got 7 million views. So it was insane to see how it,
resonated with folks again, but also of course struck a chord again. 7 million views. Seven That's amazing. Okay.
Ammar. You wrote illustrated and published
a children's book and put it online for the world to buy in a weekend. Yeah. many people may not believe
that's even possible. And in fact, many people that are
listening to this podcast may not have tried Chat G P T or MidJourney
or any of the other cool generative AI tools that you and I have tried. And so I thought it would be a
really fun exercise for you to teach me exactly how you did it and
for us to make a children's book. Are you game? let's go. Let's do it Let's start at a high level. Tell me the three to five steps
that you went through to publish Alison Sparkles a weekend. Yeah. I think it has to start with
your idea of a story, right? I think, you know, people might
think, okay, you press a button, it spits out a book, but I think it
has to start with your imagination. So I'm sure AJ, you've got a fun story
we can craft together, but you know, it'll start with what you think that is. And then we will provide that to ChatGPT
to kind of give us a base for our story. I think then we'll iterate with ChatGPT,
almost like a brainstorming partner. We're gonna go back and forth. We're gonna expand on characters
and the arcs that we might want to, you know, go through. And I think once we have that,
Then we go back to imagining again. We have to think through how do you take
that script and that story and you bring it to life, how do you visualize it? And that's where MidJourney comes in. And we're gonna generate art that
fits that narrative and expresses that narrative in a really nice way. And then we can combine it all
together with you know, pages to create that book format. Okay, so to recap, we've gotta come
up with a story using our imagination. That's probably the one area
where I might be able to help. Then we're gonna let's go. Yes. we're gonna ask ChatGPT to help us
turn it into a story, for a book. Then we're gonna. Iterate on it a little
bit and develop the story. Then we're gonna take that and work
out how to turn it into illustrations. Also think about the character
arc and the different characters involved and how we describe them. And then we're gonna try and
put it all together into a book which we're gonna publish. Is that correct? Sounds good. Yeah. All right. So we need a story now. I've got this idea for a
book that I wanna publish. It may have been inspired
by a book I read recently. It's a great fairytale. It has a prince, he meets a
princess, they fall in love. There's some tragedy, but
it has a happy ending. so the character in the
book is Prince Harold. he's young, he loses his mother Oh, man. And the only way for his heart to be
mended is for him to meet someone special. And he this actress named Megs and they fall
in love and their love eventually men's his heart, he live happily ever after. That's a great story. Yeah. I th I think we can make
something off of this for sure. Let's do it. The first step you said was,
we're gonna take this story and we're gonna put it in ChatGPT. So let's walk through that and I'd love
you to show me how you use chat GB t The URL is chat.openai.com will include
the link in the notes for the podcast too. And you need to sign up, I think you
can use a Google account on Microsoft account or use a, your email address. But ChatGPT is completely free
so anyone can try this just like Ammaar's about to show us. All right let's work off of that original
story And you know, I like to start with something that just gives us a
little bit of a base to work off of. You know, we could do, write a short
story about a prince, whoops, can't spell, prince, called Harold, who
loses his mother at a young age. And the reason I'm giving it that is
because I want it to introduce some tragedy into the short story, and let's
see if it can kind of work off of that. He eventually meets the love of
his life, an actress named Max. Okay. So let's see what it's creating for us. So once upon a time, there was
a young prince named Harold. He lived a life of luxury. Wow. it was a life that was missing
something very important, the love and care of his mother. Wow. This is this is really building
up the way you were describing it. She passed away when he was just a boy,
leaving him with a broken heart and a longing for someone to fill the void. Wow. As he grew up, Harold became
known for his adventurous spirit and charming personality. you say that lines up with
how you imagined Harold? AJ just like the Harold I was imagining. It's like ChatGPT knew exactly
what I was thinking about. Yeah. Amazing. Let's continue. He traveled the world, met new
people and tried new things, but he was still searching for that. Someone special. One day he went to a play
and met actress named Megs. She was the star of the show, and as soon
as Harold laid eyes on her, he knew she was the one he had been searching for. Damn You can already uh, sparks. Yeah. Megs was suggested intended by Harold,
and soon they were inseparable. They went on adventures together, laughing
and falling more in love every day. Harold finally found the love and
comfort he had been missing for so long, and he knew that Megs was the
missing piece to complete his life. This is quite the fairytale. Wow. The two of them got married in a grand
ceremony with friends and family from far and wide coming to celebrate their. Harold and Megs lived happily ever after. And their love continued to grow
stronger with each passing day. the end, Harold realized that even
though he had lost his mother, he had gained so much more in Megs. She was his rock, his partner in
life, and the love of his heart. And together they built a life full of
happiness, venture and endless love. Wow. Chachi b t essentially wrote this story
based off a few prompts that you gave it. So you said write a one prompt. right? One prompt, which is write a short
story about a prince called Harold, who loses his mother at a young age. He eventually meets the love of
his life, an actress named Max, ChatGPT, has this whole story. And in it, you know, Harold
becomes known for his adventures. He has a broken heart, but
then he meets this actress at a play, which is really cool. And the two of them get married in a grand
ceremony and they live happily ever after. And all of that ChatGPT came up with. So we've kind of already got parts of
the story, so what's the next step? How do we turn this into a book? Yeah. So the next step is gonna be taking
that story and putting that I just like to work in Apple Notes, but
putting that story in there and then thinking about what scenes we're
imagining for that part of the story. So let's brainstorm a little
bit, AJ, and figure that out, and then we can go to MidJourney and
start to illustrate that stuff. What do you think? That sounds good. Let's try it. All right, so I've just copied the story. I'm just gonna paste it in. Okay, so we've got a beginning. A once upon a Time there was
a young prince named Harold. What do you think we could do here? I think it could be maybe a
young boy in a kingdom, you know, to show that Prince growing up think that could be cool. Let's think about what it might look like. I'm thinking like maybe
a redhead be kind of cool yeah.
You're really original with this. Yeah. I'm thinking the kingdom
would have a lot of castles, From the medieval times. That might be kind of cool. of rolling green hills. I love that. very scenic. Yeah. we could add some soldiers
wearing red tunics and really tall black hats made out of fur. I'm you know, I've just never seen anything like that. That sounds so incredible. We're kind of coming together with a
story right now and you are writing it out and you are doing it in
Apple, in your Apple notebook, but this like in a Google Doc or you could write out really anywhere. And what you're doing is you're
essentially taking a story that ChatGPT created and just kind of
describing the different scenes. where, right? exercise to do and we're using
a lot of our imagination. But I was curious, could
chat g p d do this too? Like it, could it describe
some of the scenes? Sure. Yeah.
Why not? Let's just switch back to ChatGPT and
pick a paragraph and then tell it to describe what that scene might look
like and let's see what it gives us. That would be really cool. All right. So we're back in ChatGPT, we're still in
the middle of our conversation with it. And let's, you know, let's just
take, let's take that first paragraph and say, describe how
you would illustrate this scene. And I'm just gonna paste in the
thing and let's see what it does Now there we go. This is a really great
description of what it described. So we started with the first
paragraph, which just to remind everyone was, once upon a time, there
was a young prince named Harold. He lived a life of luxury, but
it was a life that was missing something very important, the
love and care of his mother. She passed away when he was just a boy,
leaving him with a broken heart and the longing for someone to fill the void. We asked basically to describe
how it would illustrate the scene. So here's what we got in response. To illustrate the scene of Prince Harold's
life, I would depict a young prince standing in a grand castle surrounded
by riches and luxury, but with a lonely and sad expression on his face. The room would be spacious
and well appointed, but with a feeling of emptiness. Wow. In the background, there would be a
portrait of Harold's mother with a veil of sadness covering her face, symbolizing
the loss of her love and care for her son. The window of the room would show
a view of a gray and gloomy sky reflecting the prince's heartache
and longing for someone to fill the void left by his mother's passing. This is very dramatic and emotional. To emphasize the Prince's loneliness, I
would have him standing alone with no one in sight and his head bowed and sadness. The overall mood of the illustration
would be somber with muted colors and soft light, but with a hint of hope
in the prince's eyes hinting at the bright future that lies ahead for him. So that was really cool because
when we were talking about it, we kind of had a few words or Yeah, it. But when we went back to ChatGPT and
actually just said, Hey, ChatGPT I want you to illustrate, how you would
describe this part of the story. It actually went into a
lot of detail to do that. And what it means is for someone that
isn't necessarily good at imagining this and really describing it to
illustrate it, you can actually shortcut that and let ChatGPT do some of that
work for you, which is really cool. So we've got an idea, a scene now
for the first part of the book. How do we turn this into an illustration? So this is where
MidJourney comes into play. so what is MidJourney Ammaar? Yeah. So MidJourney is the generative AI tool
we're gonna use where chat G B T is kind of giving us text descriptions of things. MidJourney allows us to visualize that. So with a prompt, the same way
we gave it to ChatGPT, it's gonna create images for us that we could
start using and, you know, a book. So let's dive in. the first step to using MidJourney
is heading over to MidJourney.com. And you know, you come across
this very trippy homepage very eighties hacker esque. And honestly that's probably reflective
of what it feels like using MidJourney. It's not the most approachable but
it's not that hard to get started. So what you wanna do is click Join
the Beta, and once you click that you're going to be guided to Discord. And so this is where you need
a Discord account to join essentially the MidJourney channel. It's like joining a Slack channel,
basically where you can then talk to the MidJourney bot and provide at the prompts. And so for those who are not familiar
with what Discord is, it's basically it's basically Slack for communities. So if you've ever used Microsoft
Teams or Slack or any of these tools that allow you to communicate with
people, discord is aimed at those niche communities of people who just
are hobbyists in different fields. Could be movies, you know, cartoons, games
really started with video games actually. And and now you know,
it's got AI enthusiasts. So this just a channel a home for
anyone who's really interested in generating art to join this channel
and have conversations and share their creations with each other. Okay, so in discord. So this is Discord. This is what it looks like. You know, you've got essentially. seems like a chat app, like
an instant messaging app. If you've ever played with MSN
Messenger back in the day, or Yahoo Messenger, this is just like that. Or AIM I think in the States. But what we're going to do, I said
that, you know, MidJourney had its own channel where you can see the community
and here's just a preview of that. It, you know, you can see someone's
creations, looks like they've made some incredible art about, you
know, with Spider-Man and The Hulk. Beautiful style. But what we wanna do is we want to
communicate with the MidJourney Bot. And the MidJourney bot is essentially
this automated, you know, chatbot just like ChatGPT that lives inside of Discord. And we're going to tell it what we want to
see and what we want to imagine, and it's going to end up creating images for us. So let's jump over to the MidJourney
bot and start generating some images. All right, so we are in MidJourney and
we are about to bring Prince Harold to life, . Let's see what we had. So AJ, your description was a young boy
in the kingdom redhead with freckles has a lot of castles, scenic soldiers. All right, so I'm just
gonna copy that over. And let's work with, let's work with this. To use MidJourney, the first thing
you wanna do is you type slash Imagine and so slash imagine allows
you to start entering your prompt and creating images and artwork. And so I copied that description that
we had written in Apple Notes, and I'm just pasting it in MidJourney,
and I'm saying young boy in a kingdom redheaded with freckles. Kingdom has a lot of castles, scenic
soldiers with large black hats. And I'm actually just gonna add
a few more adjectives to this. Maybe I'm gonna say a prince actually
in a kingdom, a young prince. I wanted to create and generate some
of that royalty and that feeling of royalty in this image, right? And I'm also gonna say a children's
book illustration to make it, you know, approachable and approachable art
style, children's book illustration. That bit is really interesting that you
just talked about the art style, because I've seen so many different styles
of art come out in MidJourney and it seems like a big part of successfully
using a product like MidJourney is really being able to describe
the kind of style of art you want. You know, it does everything from
like photorealistic art that looks like a photograph all the way
through to, you know, comic style art that might look like, you
know, a graphic novel or a comic. And then, you know, in between. Like I'm sure we could get it to generate
an illustration that looks like something from the Pixar universe, for example. That's really cool. And then when you put it in and you
say Children's book illustration, is that enough or do you try to add more? What's kind of some of the tips
you have for making a really good prompt in MidJourney? Yeah it's really interesting you asked
that because I think the more specific you can get, the better your results are. And sometimes you really need to, you
know, I think this prompt, if I was gonna critique it, I would actually
say it's probably got too much going. You know, it's going to try to
get that children's book style. It's going to try to
bring a young prince in. We're giving descriptions to the prince. We're describing the kingdom around them. So there's a lot going on here,
and I think we're gonna, you know, we'll generate and we'll
see where the results are. But then the really the way to get
better at this is to whittle down that prompt to get to just the parts that
are yielding exactly what you want. And you know, our prompt here, children's
book illustration, A young prince in a kingdom redhead with freckles. And what's gonna be interesting there
is will it know to associate the redhead with freckles with the prince. We don't know that yet. Yep. Kingdom has a lot of castles. Now where's it gonna place this print? Because now we're describing kind of
the background and the setting and the, you know, it's a scenic background,
so that's also gonna be interesting. And then soldiers with large black
hats, so another character has been introduced as well in this prompt. Usually I like to stick to one
character in a prompt or maybe two max. And, you know, the setting behind them. But, you know, I think this is just gonna
be a really great way to see where we end up and, you know, work with that. That was a really good point, by the way
on the number of different characters. Oftentimes when I've seen general
AI has had one character in it, and there's a few times where I've tested
out with multiple characters that it kind of finds it a little bit
harder to discern between the two. Let's see how this one works. And then if we need to, we can always
remove the the second characters. Yeah.
That sounds great. Let's let's do it. So I'm just gonna hit enter and we
are gonna start generating some art. So the thing I really enjoy about using
MidJourney is you start to get a preview of how that image is being composed live. And for folks that don't know how
MidJourney works, it actually uses AI approach called Stable Diffusion. And what that does is it actually takes
images and destroys the images into noise. Like the noise you would see on an old
television you know, before we had cable just with like white and black dots, and
then it learns how to take that noise and rebuild it back into an image again. And so what MidJourney and other
products like it stable diffusion and like Dali have done is they've
taken millions of images and done the process of destroying it to noise
and building it back up into image. And over time as you do that, you train
the model to learn exactly how an image is made in all the different parts of an. and how to take text that's related
to that image using a separate model, which is usually a language
model and associate them together. And the process that we just saw that
am that Ammar showed us is actually that live process of the idea that Ammar fed
into MidJourney, the prompt being turned from noise into an image bit by bit. And cool. What do we have? All right, so the first thing it
does is it gives us this grid of four images, and it just likes to
give us a few options to work with. And so looking at this grid, we
can see that it has indeed placed castles behind this prince. And really it's a closeup
shot of the prince. We didn't even specify that, but
it decided to kind of give us that perspective, which is pretty cool. It looks though that while it
nailed our scenic background and that magical kingdom feel our young
prince is wearing the outfit that we had planned for the soldiers. So he is wearing that black hat. He's dressed in military
uniform, I have to say. He looks pretty sharp, it's
really cool to see that. While in some of the images it
kind of dropped those freckles. It looks like it's not a fan, but
in others it seems to be present. So we see four images,
1, 2, 3, and four, and. . You can see there's a slight
variation in the art style. You know, the first one is a
little bit it's got a little bit of that painted, like touch to it. The second one's a bit more
of a, you know, pencil drawing kind of feel on the third. The fourth one is like almost very
hyper-realistic to some extent. So now the cool thing is MidJourney
then presents eight buttons to you. Nine actually. U1, U2, U3, U4 and V1, V2, V3, V4. So what does that mean? U1, U2, U3, U4 the image on the grid. So image number one, image number
two, you can choose to upscale that. So if you like any of these images
and you actually want to use it somewhere, you can click u2. And we're gonna get image number two on
that grid in a high resolution format that we can start using elsewhere. Now, if we like what's happening in
image number two, but maybe we wanted to see something a little different, we'd
click v2 and that just means variations on image number two, variations on
image number one or three or four. And so that's just a fun way to
remix and kind of still get to a style that you know you really like
before you settle on something. And then you've got that little
spiny arrows, and that just means restart this whole prompt again. I didn't like anything. And so that's if you just want a
little reset, but you don't really wanna change the description. I actually really what we have
here and I almost want to double down on, you know, number three. What do you think AJ? Awesome. Yeah I mean, it's really cool to see
how it generates those four different images and how they're kind of different. And one thing I've noticed about that
is, You a little bit of choice of, you know, which image you want to go with. All four of them look pretty great. The only thing I'm thinking about is that
black hat kind of makes them look a little bit more like a soldier than a prince. So I'm wondering if we need to change
it up a little bit to remove the hat. What do you think? Yeah, we could try that. So why don't we pick an image we like. I kind of like number three
and I'm just gonna click v3. And what's cool here is MidJourney then
brings up that prompt again and allows me to change any part of the description
so that I could tweak that prompt and maybe change specific detail about it. So in this case, you know,
let's remove that Soldiers with Black Hats part from our prompt. And so I'm just gonna delete this bit. and I'm gonna add a young
prince in a kingdom redheaded with freckles wearing a crown. And so our final prompt is
children's book illustration. A young prince in a kingdom redheaded
with freckles wearing a crown. The kingdom has a lot of castles
and scenic background, and we removed the part where it was
black soldiers with black hats. That's gone. So with that, we can hit submit again. Let's see what we get. So how long does it usually take for
MidJourney to give you a response? And does it depend on how many people
are using it, or is it fairly consistent? It it can be pretty fast. You usually get images
generated within 30 seconds. But that's if you're on the paid plan. So if you're on the paid plan, you have
what they call fast image generations and fast image generations allow you
to basically prioritize your prompt amongst all the other people that
might be generating at the same time. So you get priority in the queue
and you get your images faster. For most people though, you'd be on the
relaxed queue, and in that it can take up to five to 10 minutes, sometimes
even to get some of your images back. So it can be a bit of an involved process. Some of these products are starting
to use speed and access to getting back the thing you're asking for
as a way to kind of differentiate their priced versus free version. You know, the free version, you can get a
response, but it might take a bit longer. And then the fast version, no matter
how busy it is or how many people are using MidJourney you'll get a response
much faster, but you have to pay for it. How much does it cost? Yeah, so I think the basic plan is
$10 per user per month, and then $30, and then just introduced a pro plan,
which is $60 per user per month. That just means you get more, more fast
image generations which they've capped per plan which is pretty interesting. Awesome. So if you are finding that you use this
tool a lot, or it's useful to you or you want to kind of come back and make lots
of different images, it could be worth spending that extra 10 bucks a month to,
to get faster feedback from MidJourney. Totally. Cool. So MidJourney is working away in the
background, and for folks that don't know how this works, the MidJourney team
have thousands of servers or hundreds of servers running in the background
that are essentially taking all these prompts from all these different people
that are using the Discord channel and churning out these images, sending them
back to us so we can take a look at them. Exactly. And so it looks like we've got new output
and the one thing you're gonna notice is. Our prince looks like
an entirely new person. And that's because every fresh
prompt just starts from scratch. Again, you're not maintaining
your previous history. It's not chat g b t where it understands
the context that it was in prior. This is just starting fresh again. And so we're working with a new set
of images and a completely fresh looking print . What I really like
though about the images we just got is this crown looks fantastic. You have another great closeup shot
of the prince in all four images and you're seeing that somber personality
of his come through and the way he's looking, you know, in the distance,
but composed calm for a young child. Yeah. For folks that are listening to this,
by the way and I encourage you to watch the video in the show notes. The princes already do have this
kind of somber look to them. And the fourth one in particular it kind of looks like some a prince
that's you know, experienced some hardship but has some hopeful hopefulness. He's looking directly at the camera, but
a little bit off center, kind of with that kind of vulnerable look in his eyes. And it looks like the perfect
prince for us, I think. So that's the one I would go with. Let's go with number four. I completely agree. The first one was looking much more
like a soldier, I think, in this path. But this one has that innocence
in his eyes, which is beautiful. So let's get an upskilled
image of that one. So I'm gonna click U4 and that's
going to pick the fourth image on the grid and upscale it. And the fourth image is
the one we really enjoyed. And so now what's gonna happen is
MidJourney is going to actually add a few more details to this image. Might even change the way the
prince looks a little bit because it's trying to, you know, create a
high resolution version of what was otherwise a very small square grid. And we're gonna see that come to life in. And that's a really cool feature that
MidJourney has actually, is that it takes that small image and kind of fills it out. And it's not just enlarging the
photo so we can see it bigger. It's actually adding extra detail to
make it a higher resolution image. And as you mentioned, when it does
that, it's not just adding extra detail in pixels, but it might
actually add extra features into the image itself, which is really cool. You know, now we get another reveal of
seeing what the upscaled image is gonna look like, which I'm so excited to see. Exactly. I think that's one of the
most fun parts of the process. You just, you know, you're imagining
something, it's coming to life and then it's going in a direction maybe you didn't
expect, but you enjoy and want to keep. And I think that process of iteration and
back and forth that, you know, we saw with ChatGPT when it was kind of expressing
the story and we were able to expand on it, MidJourney kind of does that visually. And that's really fun as. Yeah, that's one thing I actually
really love about generative ai, and especially if you're not someone with any
experience actually using tools like this. And, you know, if you haven't ex had
experience using something like Photoshop to come up with an illustration is
it's much more of an iter iterative and conversational experience where
you're like going back and forth with this AI to come up with the answer. And it just feels a lot more approachable,
and I would dare to say a lot more human in the interface than, you
know, pointing and clicking on a bunch of different buttons and a bunch of
different you know, squares and circles and stuff to try and make this image. And so to me that makes it way
more approachable for anyone to really try and have a go at this. And, you know, in the space of
about 10 minutes of iterating, we've now come up with this awesome
very vulnerable but hopeful prince standing in front of his castle
that we can use in our in our story. Absolutely. So you can see it's made him a
little more stern in this final image that we've gotten but still
see that childlike innocence. He's still kind of
looking in the distance. Slightly off camera. One other thing we can do real quick
is we can just hit light, upscale, redo, and that is just another
way to maybe say the MidJourney. Hey. Give it another shot at that upscale
process that you just did, and again, maybe try to tweak some of those details
because I still really liked that original prints had a bit more innocence
to him and less that let stern looks. I'm really hoping that light
upscale redo button gets us that. But let's see what happens. Yeah. And as you do this, one thing to bear in
mind is that there's a lot of randomness involved in using generative ai. You know, it isn't something where
every time you put the same prompt in, you'll get the same result. And so we're actually gonna see what
a different look might look like and exactly how you just talked about that. We now see a prince that does look
a bit more innocent and is a bit closer to our original version. The other cool thing to bear
in mind is you're doing this in discord in a chat channel. So every single step of the process,
you get to see that as an image, and you can always go back to the step and
download that image if you don't like what you get when you know, do the redo. Exactly nothing is lost. You can just keep expanding on your
iterations, which is really fun and looks like it's giving us that young,
innocent prince that we wanted in a high resolution version, which is awesome. Very cool. So we have our Prince Harold. He's taking shape. We're seeing him in front of his castle. We have an upscaled image of Prince
Harold that you created using generative AI using MidJourney, and we did it. By first having the story
that we made in chat G p T. And then from the story we created
some scenes, which we described. Now we described it ourselves, but we
also showed you how you could describe the scene in chat G P T and use some of
that language from describing in chat G P T to actually then create the prompt
that you put into MidJourney as well. And you know, there's many different
ways you can approach this. You can use your imagination, you
can ask chat g p t to help you. It's a really fun process and one thing
I've really enjoyed about using generative AI is that kind of back and forth fun of
trying different ways and experimenting. And I really encourage everyone
that's listening to this and wanting to try it out for yourself to just
experiment a lot and try different processes, try different ways, click
the different buttons and try the different variations to see what you get. And don't be afraid to,
you know, experiment. Absolutely. It is just as much of a process,
of just iteration and back and forth and, you know, brainstorming
with this bot, you know, almost to come and bring your ideas to life. All right, so we've got
this image of Prince Harold. He's staring into the distance. He's hopeful, he's looking a
little bit sad, but this is kind of the beginning of our story. How do we get this onto a page
and then turn it into a book Yeah. So the first thing you're gonna notice
is even though we've gotten, what I would say is a high resolution image
of what was on the grid, it's still not high resolution enough for print. And so we're going to use another
tool called Pixel Made for Mac which you can get on the Mac App Store. And it's got this amazing feature called
Super Resolution, which uses machine learning to try and expand the image that
you have to a high resolution version and maintain the details that were there. And I'm gonna show you how you
can do that in just a couple of clicks and it's just magical. So we've got this image, but
we wanna make it even bigger. And I assume that's because in order to. this as a book, you need a
super high resolution image. And so you're gonna use a
different tool for that. Now remind me, that tool
is called Pixel Meter It's a Mac app, that you can
install off the app store. We'll include a link to that
app in the show notes for anyone that wants to try it out. And there are many apps like this that do
upscaling that you can Google for as well. But we're gonna try this one. Exactly. Awesome. So I'm going to save this image
from MidJourney to my desktop and then I'm gonna fire a pixel made
and we're just gonna blow this image up, so that's ready for prime time. We're in PixelMator and all I've done is dragged that image
that I saved from a journey onto the PixelMator icon on my dock. But if you just fire open the PixelMator
app, you can just open image, select the image you downloaded and it opens up. So now the main thing I want
you to focus on is look at the resolution of this image. It's 1536 by 1536 pixels. So it's not that big. It's a bit of a, it's a square, right? But I want this to be really big. I want it to be good
enough for a book cover. I want it to be good enough for pages
that are gonna come in high quality print. And all I'm gonna do, there's
just two clicks and we're gonna make that way bigger. So I just click the three dots
in the corner and hit super re. and it works like magic. And so now it gives me this
before and after where you can see the details that are actually
preserved, there's no blurriness. So notice that we've got this
1536 by 1536 pixel image. You know, it's a good enough size square,
want something a lot bigger, something that could be printed and high quality on
pages, on book covers, posters, whatever. So to do that, I just have to click
the three dots in the corner here. And then you wanna scroll down
and look at this thing here in the side, which says super resolution. And so when I click that, it's going
to blow up this image and take our image from the small square 15 by
1500 to something a lot bigger. And there you go. So in just that one or two seconds,
you know, you're seeing that there's no level of detail that's
really lost between the two. But more importantly, that image is
now a 4,000 by 4,000 pixel image. and you know, I can just keep going. I can just go again and click super
resolution and it's a little slower this time because it's making it huge, right? And you probably don't have to go this
big, but you can, and this is helpful if you're making an animated short and
you want it to be a 4K resolution shot. But now you can see it's a 13,000 by
13,000 pixel image to really high quality. And, you know, you can zoom in
and you can see that there's no blurred lines or anything like that. This is gonna work great for our book. This is really cool and it's a little
bit harder to see it in the video, but I've tried this myself and seen
how impressive it is to see the amount of pixels that it fills. And so it's something worth
definitely trying yourself. We're not just making the image bigger. We're actually adding more pixels to
it, and it's done using artificial intelligence to actually work out
where the image should add pixels and what those pixels should look like. And now we get an image that's big
enough for us to put on a book. All right, so now that we have our high
resolution image, let's just put this on a page of a book with the description we
got from chat G b t to bring it to life. So the first thing I'm gonna do is
I'm going to export the image that I just created with PixelMator and,
you know, pick the JPEG format. It's gonna be a five megabyte image. Gonna click export here, and I'm gonna
just choose my desktop and save it. I think because I'm sharing my screen
a certain way, you can't see the save dialogue, but just imagine that
classic Max Save dialogue is there and I'm just choosing my desktop. And now we're gonna move over
to Pages, which allows us, comes free with all Most Max today. And that just allows us to compose
our book by giving us the right templates to start doing that. And it's really easy.
Okay, so we've got a
high resolution image. We've got some texts that
we generated with ChatGPT. We took that image from MidJourney. We scaled it up using PixelMator, and
now we're gonna put it into pages, absolutely. It just comes with your Mac. And if it's not on your Mac
pre-installed, it's free on the app store so you can easily grab it. So now I'm in pages and you know, when
you click new document, you're asked what kind of document, choose a template. And on the left hand side you can
see basic reports, books, letters, where after books here, right? So you can click books and you can see
that it's got a bunch of, different templates for us to work with. A basic photo book, contemporary
novel you've got a storybook. There's some really nice ones
for us to work with here. I like the storybook one. It looks like a children's book. It kind of fits the vibe we're going for. So let's go ahead and
create with that one. So I clicked that and now I have
essentially a template to work off of. It's given me a few
different layouts, right? We've gotten the cover page a page here,
which tells a little bit of a story with a big image as like the focus. A page that's just dedicated to an image. And this is great because we've got
enough here to work with to kind of lay out our book and give it that style. So let's just use that image that
we had of the Prince and, you know, start our story the way ChatGPT
kind of helped us describe it. So what I'm gonna do is I'm going to
grab that image from my desktop, and I am just going to drag it here and
bring it to life by putting it in there. So as you can see, I just dragged
my image over to Pages and it gave us the Prince as the focus of this
first page, which looks great. We can obviously also just double
click and slightly move it. If you wanna maybe emphasize
this crown a little bit. You could also resize a little bit,
so maybe, it's not exactly that whole width, but you're getting a
scene of that castle as well in it. Again, it was cropped out
before, slightly above the chin. Let's give him some of that room. And there you go. You've got the prince looking there
at the reader, which is pretty fun. And now I'm gonna go grab that description
we got from ChatGPT so I've just copied the text that we already had
saved, and I'm gonna paste it in here. So one thing you'll notice is messed
up the formatting, but that's okay. What we're gonna do is go to text
and just choose the body template text that it's already given us. And that'll fix it. But now you'll notice that it's
a little out of the box, right? It's not fitting. So we can just slightly resize that and
it fits into place but it's also given us these nice headers that we can work with. So what I'm gonna do is actually, I'm
just gonna cut out this once upon a time from this part and paste that in here. And that just gives it that nice dramatic
storybook feel as you're reading it. And I don't think we really need this
one, so I'm just gonna go delete that. And now what we've actually done is
we've created a little bit of room for ourselves, so we can actually
increase the size of the text again and drag the box down just a little bit. And there you go. There's our first page of the storybook
for us to go ahead and roll with. Wow, that was amazing. So we went from an idea for a storybook
to then generating the actual story using ChatGPT to then creating some descriptions
for what the first scene might look like. Putting that in MidJourney, going
through a few iterations to come up with an illustration, and then using
PixelMator to make that image even bigger so that we can use it in print. And then we brought it into a
Mac app called, pages, which is available on your MacBook. And we've used a template to turn
it into the first page of a story. And this is amazing. So we've actually started writing
a story now, and obviously you can keep doing this and you can continue
the rest of the story, which is what exactly what I'm gonna do now that
Ammar has shown me how to do it. But there's one piece that I still
don't understand how you did Ammar. So we, let's say we made whole book. How did you get it? Into the Amazon bookstore, how do
you make it into an actual book that someone can have in their hands? Yeah, for sure. So once you've kind of composed all
of your pages, what you want to do is export this book and that export
functionality is available on pages. You just click on the MAC toolbar,
click export, and export to pdf. And so once you have that pdf,
you're going to go to Amazon KDP and publish your title. what's Amazon KDP? Yeah.
So for those who don't know, KDP is the Kindle Direct Publishing
platform for Amazon, and that essentially allows anyone to
publish their own Kindle books. They just make you sign up, provide tax
information if you're selling that book. And then you can go and fill out
the information about your book. So the title, who the authors are
illustrators, description, and then you just upload your pdf. Then once you're on KDP, it's just gonna
ask you if the formatting looks good. You can also enable if you want
it to be a paperback and click next, next, next, and you're done. And then it's live on the Amazon store. Within 72 hours if approved. That is amazing. So within 72 hours of having this
book ready in pages, you can actually have it on the Amazon bookstore. And now it's not just a Kindle book. They actually give you a paperback
version or a hardback version too, that people can then buy. And did you have to spend any
money to publish this book? I didn't have to spend any money apart
from the MidJourney subscription. That was the only thing
that cost money here. That's so cool. So you really didn't have to
pay for publishing the book. Amazon is basically kind of
putting the book there and then if people want it, I guess they
print it and then send it to 'em. So it's kind of on demand. It's on demand. Print on demand is this new phenomenon
actually, that they they've somewhat pioneered, which is, yeah, they don't
have to hold all this inventory. They can just print on demand with
all these printers across the world. And the way they make money
from it is if there's a sale, they take a cut from your sales. And so you don't have to
put up any upfront capital. So if you're someone who wants to
put your book out there, you don't have to worry about buying a load of
books and hoping that someone's going to buy them and hold that inventory. Amazon's taking care of that for you. Wow. So really thanks to Amazon, anyone can
be their own publisher, which is so cool. And I'm gonna go do this. I'm so excited to make this into a real
book and publish it and then get a copy of it delivered to me so I can show everyone
and all my friends just like you did. Now, do you have a copy of your book? I really wanna see what it looked like. Here's the book, it's
the hardcover version. And, you know, it's it's in my
hands which is kind of crazy, right? Yeah, I love some how some
of these images came out. And yeah, the print quality as
well was also really impressive. This one's my favorite image in
the book kind of shows Alice all grown up with her robot friend. So yeah, there you go. That is so cool. And one of the things to also think about
is if you don't wanna publish this book to everyone and you just want to kind of
make a gift, let's say it's for Mother's Day or for your friend, or maybe you want
to gift it to a niece or a nephew, you can just publish it and then buy one copy. And I guess after that you
can stop publishing that book. So it's, that's kind of a cool hack to
just make a custom book for yourself. Absolutely. Yeah. I think this is a great way to just gift
personal stories to people, which, you know, is just, it's amazing that we can
now go ahead and do that and realize that. thank you so much Ammaar for
being down to show us exactly how you illustrated and published a
book in the space of a weekend. And anyone can try this. Just follow along with
the steps in the video. It's very straightforward. We'll include all the links
in the show notes as well, so you can give it a try to. Ammar, so glad that you
were able to make it. I really appreciate you joining
me for one of the first podcast episodes . Do you have any future
plans to create any more cool stuff? One area you haven't
ventured into is music. Should we expect an Ammaar Reshi
billboard top 10 anytime soon? Yeah. I think I'm waiting for Google to
release that model so that we can start working with some music. I've also been seeing a lot of
these 3D tools out there now where you can text to 3D models and so
might be fun to make a little video game with generated AI assets. That could be really fun. I'm just gonna let inspiration
take the wheel, so I'll let you know when that happens. Amazing. Thank you so much for listening. I really appreciate it. If you enjoyed this podcast and wanna
learn more about generative ai, about the world of ai, and follow me as I
explore, artificial intelligence and the way it changes how we live, work, and
play, just subscribe to this podcast and your favorite podcast player and we'll
have more episodes coming up soon too. Thank you, Amara, and have a great day. Thanks for having me. Thanks.
