Creating content with AI sounds great — until you're staring at a blank prompt wondering what to do next.
In this power-packed live session of Leveraging AI, AI visual wizard Arminas Valūnas will walk you through a clear, repeatable process to turn business ideas into eye-catching images and videos using AI — all without needing a design degree. You'll learn how to use tools like Krea and Freepik, and even how to set up custom GPTs to stay on-brand every time.
We’ll cover everything from ideation to prompt generation, image creation to simple animation — with practical tips to make your visual content strategy 10x faster and 10x better. This isn’t a tool showcase. It’s a live, step-by-step masterclass in getting visual content done, the smart way.
Arminas — 12+ years in the creative space, a deep passion for AI, and now one of the go-to minds on brand-consistent, AI-powered visual content. He’s not just using the tools — he's building systems with them.
💡 Ready to go deeper? Check out the AI Business Transformation Course starting May 12 — and use code LEVERAGINGAI100 for $100 off.
About Leveraging AI
- The Ultimate AI Course for Business People: https://multiplai.ai/ai-course/
- YouTube Full Episodes: https://www.youtube.com/@Multiplai_AI/
- Connect with Isar Meitis: https://www.linkedin.com/in/isarmeitis/
- Join our Live Sessions, AI Hangouts and newsletter: https://services.multiplai.ai/events
If you’ve enjoyed or benefited from some of the insights of this episode, leave us a five-star review on your favorite podcast platform, and let us know what you learned, found helpful, or liked most about this show!
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Isar Meitis (00:00):
Hello and welcome to another live episode of the
(00:04):
Leveraging AI Podcast, thepodcast that shares practical,
ethical ways to improveefficiency, grow your business,
and advance your career.
This Isar Metis, your host, andwe have a really exciting show
for you today.
As you know, creating visualsthat gets people's attention has
been a key component ofeverything that we do.
Whether you're in marketing oryou just like to share content
(00:26):
online or build networks, beingable to capture people's
attention by generating theright images of the right videos
has been something that.
Companies has been born andgrown on.
And if you know how to do thisright, you can grow your
business.
Whether you are a part of a bigmachine like running your role
in a marketing department or asales department or something,
(00:48):
whether you're a solopreneur ora consultant, a content creator,
all of the above.
You need to know how to createvisuals that attract people's
attention and connect with thepeople that you're trying to
connect to.
And it needs to be aligned withyour brand, and it needs to be
aligned with your tone of voice,and it needs to be a lot of
things in order to actually doit right now.
Used to be a lot of work,especially when you go to the
video side of things.
You needed to actually have agood story and a good idea, and
(01:12):
you need to be able to createthe right process with
videographers and camera peopleand audio and visuals and
lighting and actors in a studioand like all these things to
actually get these things done.
And the good news is now youdon't have to, you can create
incredible visuals withouthaving a camera and without
(01:34):
knowing anything about design.
Now, obviously if you know aboutdesign, you can do a lot more in
a better, we're gonna talk aboutthis in a minute, but you don't
have to, and you can actuallyuse AI tools to do this.
Now, another good piece of newsis now there's a few tools that
aggregate a lot of thesecapabilities into one tool where
you can do Most of the steps ofthe process in one place without
leaving the tool.
(01:54):
And this tool brings into itmultiple other tools and AI
resources that otherwise youwould need to jump back and
forth, in order to create theoutput.
So today we are going to learnhow to create amazing visuals
that will be thumb stoppers onsocial or will grab people's
attention if it's an adsomewhere or on your website and
how to do this for both imagesand video.
(02:16):
And we are very lucky because wehave arming, Unas with us, and
Armen has been doing this for avery long time.
He's been in design as well asrunning a company that does
branding and design for otherbusinesses for many, many years.
So he both understands thevisual side and the concepts and
the professional side of this.
But in the last couple of years,he's built all in on ai and he's
(02:37):
been posting these incrediblethings on LinkedIn.
That's how I found him.
And he's teaching courses on howto do that.
So he really brings to the tableeverything you want.
As a guest of this podcast, hehas the professional background,
he has the business background.
He's been running his ownbusiness for the past six years,
and he knows AI very, very well,and he knows how to teach it
because he's been teachingcourses.
(02:57):
So if you wanna learn how tocreate incredible visuals with
ai, don't go anywhere in thenext 45 minutes to an hour.
Or if you're driving, stay put.
this is gonna be absolutelyfantastic.
I'm very, very excited to haveyou, Armin.
Welcome to leveraging ai.
Arminas Valunas (03:55):
thanks, Isar.
thank you so much for having me.
And, yeah, I think that will bea great, workshop and I have
prepared a lot of for you guys.
I want to mention that, ofcourse, the experience in
advertising industry is soimportant and I have been
working with the, the biggestbrands like IKEA and, sweat Bank
and others.
But at the same time, I want toencourage you, like Isar
(04:18):
mentioned, like these tools, AIempowers you to create and just,
throw yourself like, fully in,into ai and you will be able to
create the most, capturing and,like the highest quality visual.
So I think, let's jump rightinto this, right Isar?
Isar Meitis (04:35):
Awesome.
Yeah.
Before we jump in, just forthose of you who are joining us
live, either on LinkedIn or onzoom.
Thank you for joining us.
I know you can do other thingson Thursdays, on noontime
Eastern.
but I know a lot of you havebeen joining us every single
week, so I appreciate everysingle one of you.
I also really, really want to,thank you for, participating.
(04:56):
So if you have questions, thenask them in the chat again,
whether you're on LinkedIn, youcan just say it in the chat.
If you are on Zoom, you can sayit in the chat as well.
For now, just go ahead andintroduce yourselves.
this is one of the reasons youjoined these lives, so you can
network and get to know otherpeople.
So tell people where you are,where you're from, what you're
doing, what you're looking toget out of this.
But like I said, if you have anyquestions, please ask them.
So that's if you're here with uslive.
(05:17):
If you're not here with us live,the question is why we do this
every single Thursday withamazing people like Armen that
are gonna share.
Very practical use cases withai.
And then you can ask themquestions if you are around.
And if you're not, you can stilllisten and benefit from it, but
you can participate and you canengage.
and you don't get to experiencethat when you're just listening,
but there's a lot of chathappening in the chat as well,
(05:38):
so you can join thatconversation if you join us
live.
I'll say one last thing before,we dive into today's topic.
Today's show is brought to youby the AI Business
Transformation Course.
It's a course I've been teachingpersonally for the last two
years, at least once a month.
So we've taught hundreds ormaybe thousands of business
professionals on how toimplement AI in your business.
(06:01):
The course is four sessions oftwo hours over four weeks, and
it takes you from whatever yourlevel of knowledge is right now
to.
Understanding all the tools,what they are, what they can do,
how to use them.
A lot of hands-onexperimentation across multiple
aspects of the business.
And we end with businessstrategy, an actual blueprint on
how to implement AI successfullyin your business.
(06:23):
If you haven't done anythinglike this, anything structured
on how to implement AIsuccessfully, you owe this to
yourself.
You owe this to your businessand you owe this to your career.
And so if for being a listenerof this podcast, you can come
and join us with a promo code.
Then the promo code isleveraging AI 100 or uppercase.
There's gonna be a link in theshow notes, and we're gonna
(06:44):
share a link in the chat rightnow for those of you who are
with us live, and you can comeand join us for the session.
The next session starts on May12th.
So if we do these courses, likeI said, every month, but most of
them are private courses.
We teach them to companies andorganizations who, Book us to do
just for them.
And we open a public course oncea quarter.
The previous one was January andFebruary and now we're opening
(07:05):
one in May.
So if you need that, and if youhaven't done it, you need that,
come and join us on May 12th.
That's it.
Now to our session with Arm andArmin, the stage is yours.
show us your magic.
Arminas Valunas (07:18):
Oh yeah.
Thank you Isar.
Thanks so much.
So I think, I will start fromsharing the screen and, yeah, we
will go through, let's say,let's check the last version of
video that I've done, and wewill try to recreate this as, as
fast as we can.
Isar Meitis (07:35):
That would be fantastic.
For those of you who are notwatching, by the way, if you're
driving your car and so on,that's perfectly fine.
We will explain everythingthat's on the screen, but if you
can, there is a YouTube versionof this.
If you're watching this afterthe fact and in your show notes,
you can just open it and clickand go and watch the YouTube
video.
And then you can see,the visualsas well.
Arminas Valunas (07:54):
Okay, so let's this for now.
Isar Meitis (07:57):
Wax London, ethically crafted pieces
designed not just for seasons,but for life stories.
The foundation of lasting stylelies in superior fiber Wax,
London Clovis with character.
So for those of you who can'twatch, this was incredible and I
(08:18):
still can't believe this is AIgenerated.
So it's different images and notimages, like videos of a fashion
show and then actual people indifferent scenarios like.
Driving a boat and walking in abeautiful old city in Europe,
wearing nice fashion clothesand, bracelets and so on.
And I'm blown away that this isall ai.
(08:40):
So I'm personally really excitedto see how this was done.
Arminas Valunas (08:44):
yeah.
And it was so much fun, creatingthis.
So I think, I will go to, to thewhole, process and we will see
how to do this.
So at first, really big thanksfor, my colleague Joe who
inspired me, to create this,like I should mention that this
is real, product, real garment.
I took this from VAX London pageand I just, downloaded these
(09:07):
photos like you see, and Itrained Laura.
Then I trained the second Laurafor character, for my
appearance, but I didn't usethis in the video.
And I generated all these firstlike static images and from
them, like videos and thencreated the whole, show reel.
So let's dive deep, into thewhole production process.
(09:30):
So I chose the Freepik and itactually gave me like really
high quality and at the sametime I think it's, really like
user friendly and really easy toproduce these images.
And later on, all the videos.
So here we are.
In the homepage of Freepik.
And from here, if we wannacreate the images we are going
(09:55):
to create.
from here, we want to train theobject, the garment.
So from here we are choosingobject.
And you just have to press plusbutton.
But, actually I already trained.
So let's go through the process.
So here we say the name, let'ssee wax, then, shirt, the type.
(10:15):
And here we, upload all theimages.
I will upload.
These images.
Isar Meitis (10:20):
So while you're doing this, for those of you who
are not watching, Freepik is oneof those aggregators of tools
that brings you a lot ofdifferent other tools into them
and make it very user friendlyto use.
And what we're doing right now,when Armand says Laura, Laura is
just a way to train a visualmodel on a specific person or
style or object, you can trainit or different things.
And when you train it, it canthen knows how to regenerate new
(10:42):
images of the thing.
In this particular case, ahigh-end fashion shirt.
so what Armen did is hebasically just opened and said,
okay, let's create a newtraining, uploaded multiple
images that he, when I saymultiple, it's seven, like it's
not 50.
And he has seven images that hedownloaded from the website and
he is basically gonna create anew model that knows how to
(11:02):
create this shirt in anyscenario, on any person with any
background because it learns howto create the shirt.
Arminas Valunas (11:09):
This is exactly what I have done.
And actually, to be honest, youneed to upload, and, my, kind of
recommendation would be all thetime, follow all these tips and,
it says 12 to 25 images.
So for this, if you don't have12 at least, because if you have
o only seven, it'll not allowyou to train the lara.
But then what I did, I,basically changed the
(11:32):
composition of the images andflipped the images horizontally.
And I had 12 images and I wasable to train this Laura.
And yeah, actually it's so onpoint.
I wanna interrupt myself a bitand, maybe.
To explain how I understandLauras there are so many
technical, terms about, Lauras,but in general, it's, low rank
(11:53):
adaptation and, let's say, thisis our like flux.
And by the way, we are trainingon flux.
So let's say this is, all theflux model and all the whole
data is in here.
So we are training, like justone little piece, like this is,
our like train Laura.
And it, shows the model like, ifit's only, object or like
(12:14):
character, it shows how wewanna, generate the special,
like this special object.
So in this case, I already.
Generate Laura.
So let's say we, we generate it.
'cause otherwise we would bewaiting, pretty, long time.
Actually it's quite fast, butmaybe still takes 15, 20
(12:34):
minutes.
So we don't want to do this.
So I created Laura already.
Isar Meitis (12:39):
we'll do the cooking show thing, right?
We're pulling out of the ovenAnd for those of you who don't
know what flux is, so there areseveral different leading visual
image generating models in theworld today.
probably the best open sourceone is flux.
So it's just a name of an opensource, model that works very
well.
because it's open source,there's a very easy, process on
(13:00):
how to train it.
And in this particular case,it's built into a simple user
interface that runs in Freepik,which makes it even easier.
Arminas Valunas (13:06):
I think most adaptable and if I can say this,
like trainable, models outthere.
'cause it's open source and youcan do whatever you want with
flux and it gives you such ahigh quality.
So definitely I recommend, ifit's, for training objects,
characters or styles, just, use,flux.
You can do this, by the way, onlike older ones, like SDXL or SD
(13:28):
1.5, but Flux is, the best atthis point.
we have already our train objectin this case, this V London
shirt.
And by, by the way, there arelike many, pre-trained objects
in, Freepik that you can just,choose and maybe test if you
don't want to, let's say trainyour own law.
'cause it costs a lot ofcredits.
(13:50):
So at first it's a good idea to,play around with a pre-trained
object.
So when you have this trainedobject, in this case our
garment, we just select this oneand at Lido X, it's my, train
Laura name, and it appeared inthis field, in this box.
And here, if it's, active, itwill, generate in this train
(14:12):
Laura product.
here, I can, start typing andcreating prompt, but actually I
already have a lot of promptsprepared for us.
So I will not be doing, creatingfrom scratch.
let's dive deeper a bit into mythinking.
So I have a product and I was,exploring, two cases, like
consistent character and,different characters.
(14:33):
And, yeah.
Let's talk a bit, before I startJanuary, let's talk about, the
process and the thinking.
I divide, or at least I amworking in three stages.
So the first stage ispre-production, where like
creative ideas are born, whereI'm creating like mood work
where I find, the tone of, nottone of voice in this case, but,
(14:55):
color palette and, the wholewiden mood.
And then I am usually drawingsome sketches, like rough
sketches.
But, if you don't want to draw,it's, not necessary, but just
creative process and,pre-production is so crucial and
so important for, getting thebest results.
And also, of course, nowadays,helps, like AI tools and LLMs in
(15:15):
general, let's say chat, GPT.
It helps in every process,especially in creative process,
in pre-production.
So I am, like chatting with the,like generating creative ideas,
chatting, with the, in this casechat g pt.
But, also I'm exploring othertools, as well.
So I think it really, depends onyou and your style, but,
nowadays it's just theleveraging your creative
(15:38):
capabilities and you don't haveto.
let, the AI kind of drive yourcreative ideas and your
creativity, but you shouldempower and leverage, your
creativity with ai.
So the second stage productionitself, where I am, generating
images, videos, making someselection from all the material
(16:00):
that I have editing, combiningmusic, voiceover and everything
falls in into place.
And last touches also, this isreally important.
I think this is where magichappens, is, post-production.
And it's really important,because retouching and color
grading and, it's just, liftsyou into that.
(16:20):
This like pro quality that youare reaching.
Isar Meitis (16:22):
Yeah, so quick summary, three steps.
one is, pre-production where youget the ideas basically and more
zoom in and what exactly you'retrying to create.
And as Armina said, if you'revery creative, use your own
creative ideas.
If you're not, you can use largelanguage models to help you
through the creative process.
And think of an idea that willwork for your target audience
that is aligned with what you'retrying to do.
(16:43):
Literally just have aconversation with it.
Explain what you're trying to doand it can help you.
creating mood boards, roughideas on how the video, so the
video that we've seen had, likesomebody, it started with
somebody walking in a fashionshow and then people walking the
street and then somebody in aboat, and then a closeup.
there's all these componentsthat in your head you need to
know that you need in order toactually show them afterwards in
(17:05):
the results.
So this is more in the creativeprocess, and then you create all
these components and then youput them together.
So now let's go to the steps ofactually how to do it.
Arminas Valunas (17:13):
Let's do this.
I was jumping around a bit, but,it's really important to,
mention these steps.
'cause yeah, absolutely.
You skip something, it'll bemessy and, it's even like before
ai all the time, we are usingthis kind of, process.
let's say we already havetrained object, garment at in
this case, and let's say I'mjust, create like some simple,
(17:35):
prompt and then I will comparehow it, appears with the
advanced prompts.
So man walking in the street,natural daylight.
it's important to point that,this, works with a flux model,
and if you want to, oh, it's,and you see it's, not working
all the time.
So it give me like fourvariations, but the first one is
(17:57):
maybe the most accurate.
that's why I'm more into othertools and, like using confi, but
this is a whole another topic.
So.
it's important to mention that,here you can, demo mode and you
can choose the model.
so it's, like you see, it'smystic, it igram, imagine three,
but it works only with the flux.
(18:18):
because we train Laura on flux,we can't train, on like other
models.
yeah, so
Isar Meitis (18:23):
again, for those of you who are not watching in
Freepik and similar tools aswell, like Korea, you can choose
many of the image generationmodels.
But now, because we trainedflux, we gotta use flex.
But if you're just generatingimages, not on a trained model,
you can use all of them.
Arminas Valunas (18:38):
Exactly.
I'm using a bit more advancedprompts and, this is also deep
topic it is an art of itself andwhen I'm using more advanced.
Prompts it gives, well, for meat least, it is much better
quality and much moreinteresting.
Isar Meitis (18:53):
let's read the section of this prompt just to
tell people the understanding.
So they understand what you meanby a more advanced prompt.
So let's just read some of it.
Arminas Valunas (19:00):
Yeah.
So, the prompt, mid-lengthfashion, runway, short subject
focus, male model, walking,wearing white shirt, subject
details, fit, male model, whiteswept back brown hair, we point,
more accurate, details toeverything, to characteristics
to character, what he's wearing.
and when you prompting withELOs, in this case, you
(19:23):
shouldn't be confusing themodel, let's say if I, would try
it.
Like red t-shirt or somethingtotally different.
It would be, confused and, won'tgive you like good results, but
this is also, maybe I wanna showyou, a bit, where you can start,
like, how can you, learn how toprompt?
So I think the best start is,just, let's say download this
(19:46):
one and just, to upload, theimage into the chat, GPT and
just ask, describe the photo.
And I'm in the camp where likepeople are saying like, but you
are copying, you are doing thisor that, and this is bad.
But actually it's not like youare just trying to figure this
out.
What model, because vision modelitself, it gives you the answer
(20:09):
how it interprets this photo,and you just, borrow these, key
phrases, but you are making yourown prompt.
it's really good base.
yeah, again, to
Isar Meitis (20:18):
explain, for those of you who are listening, you
can take an image that you wannamimic the style of, or the
concept, or in this case it's amodel on a runway how.
To start prompting better, youcan just drop an image that is
your inspiration and say, Iwanna write a prompt that will
generate a similar image in animage generation model.
I want you to write a verydetailed prompt that will mimic
(20:39):
everything in this image,including the style, what he's
wearing, the background, and soon, the lighting.
And it will give you a verylong, detailed image that then
you can use as your baseline tomake changes and massage to
whatever you need.
One more thing with regards toprompting, pre-trained models
with Laura is I'll say moreextreme than what you said.
It's not just don't confuse it,but tell it what it is.
(21:00):
if you would say a buttoned up,stylish white shirt, describe
the thing that you trained iton, it makes it even better and
it will give you more consistentresults.
So don't just trust the trainingof it to be perfect, but also
describe it in your prompt andyou will get more consistent
results, than if you don't.
So let's continue with theprocess.
So now you have the images ofthe guy in the fashion show.
(21:22):
I assume you do the same exactthing for all the other
characters, right?
The guy in the boat, the guy inthe street.
I'm actually very curious aboutthe closeup one because one of
them was very different, right?
Most of them were like fullbody, relatively, kinda like
style was similar.
One of them, you literallyspecifically asked for closeups
of the fabric and closeups ofthe person,
Arminas Valunas (21:41):
tip centric.
And I will, reveal all thesecrets.
Okay.
Awesome.
Maybe let's, dive deeper and,maybe let's go with the like
generating video and then I willgo to this micro shot.
let's say we, really love thisshot.
then, what usually I'm doing,actually you can go like
straight to the great video,but, actually I'm, upscaling and
(22:02):
really good at, Freepik has themagnifi upscale, which is, the
best upscale, I would say.
Yeah.
So I am editing I'm pressinglike edit button, and then I am
upscaling and it's basically thesame parameters that in native
Magnifi on its own, but, yeah,everything is the same.
I have a few presets when Idon't want to change the
(22:25):
character appearance, I tend to,lower all the creativity stuff.
Parameters or, like portraitsoft is really good.
So let's say, I will upscale andit'll take some time, but, not
that much.
during this time while wewaiting, I can, reveal my
secret.
So actually, it's not aboutgenerating, especially when we
(22:45):
are working with the realproducts, right?
And garments and clothing, it'snot all the time just, generate
for the sake of generate, atleast in my thinking.
So I actually just took thisphoto.
it's the same photo, but I tookthis and, actually I generated
using.
runway.
runway is, really coolespecially like junk four.
(23:06):
And they released this latestmodel, I think two weeks ago.
So it's really new runway
Isar Meitis (23:11):
version four.
so that's a good trick again forpeople.
for those of you again, who arelistening, what he's done to get
the really extreme closeups isactually use.
Actual closeup photos from thewebsite and then animated them
with tools.
In this particular case, runwayversion four is really good with
consistency.
which is very important whenyou're trying to do stuff like
that and actually have the shirtlook like the shirt.
(23:33):
so now you have the standalonecomponents, you upscale them And
then you animate straight fromthere.
Arminas Valunas (23:40):
Yeah, actually from upscale photo, But, when we
upscaled, we can't, generatevideo directly from here.
So we have to go back tomigrations and.
Press here, and now we talking.
So now we can create video.
So we are pressing create video,and here is the video and also
(24:00):
you see the section.
the first stage images, andsecond section would be videos.
And it automatically gave me aprom, but, in this case,
actually it's quite good.
a male model confidently walksdown a minimalist runway.
So actually in this case, I willuse this, but, I can, give away
another secret.
what I'm doing, I created my ownArmada, video prompter, and
(24:24):
usually I'm just, Using this, itjust elaborates your prompts.
it just makes better.
So I upload, the photo and,let's say man is walking towards
camera and we will get reallydetailed, prompt, and even two
prompts actually where itdescribes like what is, the
(24:44):
composition, the, wide angleshot.
how the model looks like and allthese things helps to generate
like much more accurate, videosand actually it made my videos
much better.
I just wanna
Isar Meitis (24:57):
pause you again to explain.
For those of you who are notgreat prompters, and especially
when you're moving, even if youare a great prompter on an LLM
and now you need to prompt avideo model, it's a little
different.
And the best way to do this isto have some kind of a
framework.
And if you don't have one, thenthis particular case Armen
created a custom GPT that doesit, and all he does is He
uploads the image that he isalready created into the custom
(25:18):
GPT and tells it a general ideaof what it is, and it creates a
very detailed prompt.
Now, if you don't know what toput in a video prompt, you can
ask.
Cha pt say, I wanna build avideo prompt What component
needs to be in it?
And it's gonna tell you it needsthe composition and the lighting
and the motion of the camera,and the motion of the character
and the feeling you want to getand stuff like that.
(25:39):
and then more details anddifferent characteristics of the
person and what's happening inthe shop.
And so it will tell you all thedifferent components and then
you can ask it to build like aprompt generator for you based
on that.
If you fit it an image, and thenit will do the work for you.
So it sounds really fancy, butyou can start very quickly and
get probably not the same levelof results that arming got
(26:00):
because he's been doing this forx number of years.
So he knows what he's lookingfor, but he will get you from
knowing nothing about it to 75%there, which is way ahead of
most of the people in thepopulation.
Arminas Valunas (26:12):
Yeah, definitely.
And I wanna share some, thinkingbehind this.
So actually you can do thisperfect.
custom gpt on your own.
Just, let's say, this is a greatexample.
I created also, custom GPT forgenerating, describing pictures.
So you just, go to the page ofthe.
model itself.
(26:32):
let's say this is frames byrunway, this is like prompting
guide.
So the best thing is not to tryto guess how to create, custom
GPT, these, developers, the,giving you all the information
how to prompt.
just copy this, all the infowith the example and, feed to
the knowledge base.
And you have perfect, Custom gt.
Great idea.
(26:52):
Yeah.
yeah, let's, continue.
I decided, my own prompt with mycustom GPT is better, so I copy
paste here.
And, let's check a bit, aboutthe video models itself.
so now it says, CL 1.6 Raw, butyou can press here and, you can
choose all different models.
so I think, in my experienceit's still Ling 1.6 is the model
(27:16):
that I am going, most oftenwith, especially, when using
Freepik, like Google VO two,it's also real super, good and
like really high quality.
But I'm using more, from text tovideo.
'cause actually from image tovideo, it is, just in my
experience, like ling.
Delivers better, better results.
Isar Meitis (27:36):
Yeah.
And again, for all of you, the,one of the beauties of tools
like Freepik is that it givesyou access to all of these
tools, right?
So you can pick and choosewhether you want to use, this
image generator or this videogenerator.
And the cool thing is you cantry it with three different
ones.
And yes, you're gonna pay tokensfor all of them, so it's gonna
cost you a little bit of money.
But if you're doing this for abusiness purpose and not just
(27:59):
for fun, then it's still gonnabe significantly less money than
you spend ever on creating aprofessional video for anything.
yes, you're gonna run this on VOand Cling and Sora and Runway
and all four videos are gonnacost you.
$10.
it's still nothing compared towhat it would've cost you to
(28:19):
even just get the actor for 30seconds would've cost you more
money than that.
And so it's worth sometimesbecause what you are trying to
do might be different than whatARM is trying to do.
And the only way to know whetherthe style and the thing you're
looking for works better.
The other thing is you maylisten to this episode two weeks
after we recording it, which mayhave something completely
different on one of thesemodels.
(28:40):
So it's always worth trying todo this and just trying
different models and see how itcomes out.
And once you've done a few andyou consistently like, like
Armen is saying, he alreadyknows that for the stuff that
he's doing, cling works best.
And I'm sure that a month and ahalf from now when a new model's
gonna be out, he's gonna try theother model as well and see what
is actually working better.
But you gotta experimentyourself in your style and the
(29:00):
thing you're trying to do inorder to see what's gonna work
for you.
Arminas Valunas (29:04):
Yeah, so great.
wow.
definitely.
I agree 100%.
And, it's changing daily.
Like maybe tomorrow it'll bedifferent in case.
Yeah.
let's choose then cl 1.6 andsometimes I mess this part.
So it's really important tochoose like different, aspect
radio.
So you have ability to choosefrom these three, in this case,
(29:25):
in, when using three pick, inothers, like you can choose,
other aspect radios too, buthere, like three aspect radios,
so we are choosing social story'cause it is vertical.
Yeah.
And then click generate.
So while it is generating, ofcourse I will be showing other
things, but, basically it's thesame process for all the shots
(29:47):
that we have, right?
Yeah.
This is the first one.
We will not be able to generateall these shots, during this
workshop, but you get the idea.
And then I am combining, I'mcompositing everything.
in After Effects.
I'm using After Effects, I wasdiving deep into, character, LL
Laura training for characters,and I was testing with my
(30:08):
appearance.
So actually not that many peopleknow that you can combine
Laura's, in three pick as well.
while generating, let's go backand, it's the same process.
you can generate, train Laurason style, on characters and
objects.
You select the gender.
you upload the images.
and then, actually I didn'tmention, but, if you wanna even
(30:31):
like better quality, you should,choose ultra and then again,
create your character and youhave your character here.
it appears in this panel, andyou can just press the arm and
we have, okay, it appears at theend of the prompt, So we have
two, character and object aswell.
So let's try generate with atool r.
(30:53):
Yeah.
So
Isar Meitis (30:53):
again, for those of you who are listening, what
Armen is showing right now isactually very powerful because
you can train the model on acharacter.
This could be basically yourmodel.
And this could be yourself, itcould be somebody else.
you need obviously permission ofthat, somebody, but it could be
somebody that's made up, meaningyou can create a model with an
image generator that doesn'texist, and then train on that
(31:16):
and create more and more imagesof that person.
And the interesting thing isthat then you can dress up that
model with whatever object inthis particular case, a shirt
that you trained in a differenttraining set.
So now you can combine theperson and the object into a
single image and then createvideos.
(31:37):
from that.
And the same thing for style.
Like you can train on style andthat could be the style of your
company or just the theme youwant for that particular, shot
or video, and you can do that aswell.
And the output, we now seeimages of arm with a lot of
hair.
No, no driving, driving a boat,but wearing the shirt that we
(31:57):
were creating previously, whichis really cool.
Arminas Valunas (31:59):
Yeah.
I think I, have to read theprompt, but I created the, like
previously and you see it'scool, yeah,
Isar Meitis (32:05):
great
Arminas Valunas (32:05):
shots and of course it's, we are giving away
a bit quality wise, whencombining two ours.
And, it's not, not that accuratemaybe, but here it's good.
It's not bad.
It's not bad.
if, you are not like, gettingthe best, result, you can lower
the strength.
Like you can, choose theparameters of the strengths so I
(32:25):
can lower the strength of my,character and then, try again.
But at the same time, I willlose a bit of likeliness.
But, like we see, it's prettygreat results actually, and a
combined two lowers.
And, from here I can generatemore
Isar Meitis (32:41):
let's go back to a process for a second because I
want to put it all together.
So I'll do the review to wherewe are till now, and then I want
you to say, what are thefollowing steps.
So step number one is getting anidea.
You can do this with AI andbrainstorm back and forth in
defining what you're doing withit.
Step number two is getting yourresources.
So in this particular case itwas images of you, so the model
(33:03):
or images of a general model andimages of the actual product.
In this particular case, it wasa shirt and we had multiple
views, including closeups of theproduct.
And then we trained a LoRa,which basically means training
an AI model.
In this particular case, themodel was flux.
And you do this, it soundsreally fancy, but you do this
literally by following theprocess on a tool like Freepik.
(33:25):
You upload a bunch of images andyou train the model, and now you
can use that train model togenerate images of that object
or that person, or like we sawthe combination of them again
and again.
So this way you create theimages, which will become the
different shots in your video.
Then you upscale each and everyone of them.
So within, still within the sametool, you upscale the images to
(33:45):
get a higher resolution.
By the way, that's true in allthese tools.
Every single image generationtool you're going to use, the
initial output is a relativelylow quality.
And if you want to use it foranything professional, you
probably wanna upscale that.
If you need just for socialmedia, you probably could do it
what it is.
But if you need anything morethan that, you wanna upscale it.
Once it's upscaled, there'sliterally a button.
Once you're looking at the imageto create a video, then you can
(34:08):
prompt it again to define whatthe video.
And as Armen mentioned, you canuse a custom GPT that you can
build on your own very easily tohelp you write these prompts, to
get better at prompting thevideo output of the tool.
And in the end, you just editthem all together in an editing
tool.
That could be a professionaltool or just a basic tool.
(34:30):
You can go as basic as Canva oras advanced as.
After effects and Premier andtools like that and anything in
between.
But it will allow you to put allthese short videos together, cut
them and do the transitions asyou need, add text on top of
them, and so on.
Anything else that you add inaddition to get to the final
product?
Arminas Valunas (34:49):
Yeah, maybe, first of all, you so good at,
summarizing and putting all thedots in, into places, connecting
all the dots, so I think, Idon't know if you, if you heard
the sound of this video while Ishow Oh yeah,
Isar Meitis (35:03):
there was a nice music in the background
Arminas Valunas (35:05):
and voiceover,
Isar Meitis (35:06):
Did pieces designed not just for season.
Arminas Valunas (35:10):
so yeah, the last step, I think of course,
like music and you can generatemusic, if you want to.
AI generated music, the besttools are, soon on and Audio.
And, both of them, by
Isar Meitis (35:23):
the way, are free.
So you can generate any musicyou want as many times as you
want for completely free, whichis mind blowing.
So again, the tools are, SUNOand UIO are two very solid
competitors and they keep onimproving all the time.
But you can create any stylewith voice, with singing,
without singing, and until youland on the one you really like.
Arminas Valunas (35:42):
Yeah.
and, the last component, in thiscase it was, generating
voiceover.
So I just, created some,copyright, some text generated
wax, London ethically
Isar Meitis (35:53):
crafted pieces.
Arminas Valunas (35:54):
This is not the best, but, you get the point.
you can go to text to speech 11labs.
It's, the best at generatingvoices at this moment.
And you can choose from likelibrary desk that has, I don't
know, like thousands andthousands, voices.
And also what is really coolabout this, you can, train your
own voice and use it, even, Idunno, for many cases.
Isar Meitis (36:17):
so one more thing about 11 labs and the voices,
yes, it comes with all thesevoices, which are, again,
endless, but even within eachvoice, you can control how fast
it speaks and how soft itspeaks, and how much emotion
it's gonna have, and how muchconsistency it's gonna have.
So once you find a voice, youcan still control that voice for
that particular sentence.
And then you can run it againand say, okay, Next second
(36:38):
sentence faster or whatever youwant.
So you have a lot of control on,even within a specific voice,
how it's gonna sound, so you canmake it even more realistic
between your different scenes.
Arminas Valunas (36:47):
Yeah.
and this, how it's calledcharacter voice acting.
So 11 labs released, like fewweeks ago.
I think the voice acting, youcan upload your own recorded
video with your own intonationsand, drive the video, apply
let's say the voice of this,Johnny Boy, and get your own
style.
(37:07):
Style and
Isar Meitis (37:08):
intonation and, yeah.
Arminas Valunas (37:09):
Yeah.
Yeah.
Yeah.
So it's, it's definitely sopowerful and, I think it's also
the whole another topic, to divedeep into 11 labs.
So I think we don't have, somuch time, but, yeah, I think,
this is, the whole process andlet's check a bit, behind the
scenes.
So I am using.
like I mentioned, the aftereffects and these are all the
(37:29):
different, generated voiceovers.
This is soundtrack and, it's notthat kind of complicated, I
just, edited the video maybe.
sometimes slow down Ah, one morething.
let's say, post-production.
didn't mention this, but, allthe time I'm using top as video
ai.
So now I will turn this on.
it's the best, video op scaler.
(37:51):
it's just like next level, interms of quality.
'cause usually you also aregetting not the best quality in
terms of, resolution.
of course, some, video modelslike, let's say the last, gen
four, it, gives you ability toupscale to 4K.
I already upscaled this one.
So you can also upscale nativelyin the runway if you are using
(38:13):
one, but if you are using othermodels, welcoming, so it gives
you full hd.
But, usually I'm upscaling to 4Kat least.
Isar Meitis (38:21):
okay, so I'll put the final step together that you
mentioned, creating music.
You can do with uio or with Sunoyou can create the voiceover
with 11 labs, which isdefinitely the most advanced
tools for these two things.
And you can put it all together,like you said, whatever editing
software.
You mentioned two tools forupscaling, Magee is probably the
(38:42):
best image upscale are out theretoday.
And, Topaz for video.
Both of them are really good.
Both of them are reallyexpensive.
So there are other options thatare not as expensive, that are
good enough probably for most,use cases.
There's even some open sourcetools that are completely free
that you can use, but definitelyif you want the best, then topaz
for video and Magnifi.
(39:02):
Four images are the best ways todo up scalers.
And if you're doing thisprofessionally, Armin does, then
it makes perfect sense.
Armin, this was very powerful.
Like literally anybody who wantsto create these kind of videos,
or images or a combination ofthem, this was a great session
for them to learn.
If people want to learn morefrom you, follow you, see your
work, work with you, what arethe best ways to do that?
Arminas Valunas (39:24):
So follow me on LinkedIn.
I'm most active there at thismoment, and I'm thinking of,
launching a wait list and just,to get, know the kind of
position of people, whether theywant, learn and, to, collaborate
together.
and, then we will decide if Iwill be doing some kind of,
(39:44):
workshops or online courses.
Isar Meitis (39:47):
Awesome.
Cool.
one last thing that I wanna say.
we touched a little bit aboutFreepik and so on there, there
are multiple ways to do what wedid because in, at the end of
the day, there's multiple toolsbehind them.
The easiest way to get startedbecause it puts everything in
one simple user interface withclear things to click and so on,
is either Freepik or choa.
Both of them do similar things.
(40:08):
I must admit I'm not a pro onany of them.
I played with both of them justenough to be dangerous.
but both of them do the samething.
They bring in multiple visual.
Tools into one tool, and you canpick and choose what you wanna
do.
And in most cases, they stillgive you the flexibility of the
parameters in each of the nativetools.
So whether you're using an imagegenerator and the parameters in
(40:29):
it, or whether you're using,LoRa and training capabilities,
or whether you're generatingvideos and you have controls,
that comes with that.
So if you want to get startedand you don't want to get a
license to six or seven or eightdifferent tools, the easiest
ways to get started is to get alicense and buy x number of
credits in one of these tools,either Korea or Freepik.
And you may have a better, idealon which one will probably work
(40:51):
better.
once you have that play aroundand if you do say, okay, yes,
this is too expensive for me, Ijust wanna get one tool, you can
always go and do that.
But I think as a starting point,it's a very solid starting point
because it's a relatively simpleuser interface that brings
together a lot of other toolsthat you would otherwise have to
get individually.
Arminas Valunas (41:08):
definitely.
I think, you can, explore, maybeseparately, let's say, image
generators, like Mid Journey andothers.
and then to combine also, buysubscription like natively, CL
or Minimax or, runway, but it'llbe much more expensive.
So all in one platforms, I wouldgo with a Freepik or Korea at
(41:29):
this moment.
Yeah.
Isar Meitis (41:31):
Yep.
Fantastic.
I just wanna say thank you foreverybody who is, who are
joining us live again, we hadpeople today again, just to tell
you, we have Patrick from India.
We have.
Paul from the Netherlands.
We have, Asai from, he didn'tsay where he is from, but based
on the name, he's, probably fromIndia as well.
We have, Rahil from Pakistan.
(41:51):
We have obviously multiplepeople from the us and so really
people from all around theworld.
This is ah, Berlin.
So we have Marta from Berlin.
And so really great to seeeverybody from all around the
world in this live session.
I really appreciate all of you,joining us live.
great work.
Armen, I think you opened theeyes of people.
Some people, wrote in the chatlike, okay, that's obvious that
you need design skills to dothis.
and the answer is it helps alot, right?
(42:14):
But it's definitely notnecessary.
So I have zero design skills andI do stuff like that as well,
and I don't do it as frequentlyas Armen does, but I'm getting
pretty good results.
So all you need is toexperiment.
Like literally go and tryyourself, get yourself a license
to Freepik or choa and just togive yourself a test project and
just play with it.
Try different models, trydifferent, prompting skills.
(42:34):
Use AI, whether Chachi pt orClaude or Gemini, it doesn't
matter, to help you prompt andplay around.
And I think you'll be reallysurprised with how good your
outputs are going to be based onwhat you think your skills are,
and then you can move forwardfrom there and get better and
better results.
Thanks again, Armin.
Thanks everybody.
Have an awesome rest of yourday, and I will see you next
(42:55):
Thursday.
Bye everyone.
Hello and welcome to another live episode of the
(00:04):
Leveraging AI Podcast, thepodcast that shares practical,
ethical ways to improveefficiency, grow your business,
and advance your career.
This Isar Metis, your host, andwe have a really exciting show
for you today.
As you know, creating visualsthat gets people's attention has
been a key component ofeverything that we do.
Whether you're in marketing oryou just like to share content
(00:26):
online or build networks, beingable to capture people's
attention by generating theright images of the right videos
has been something that.
Companies has been born andgrown on.
And if you know how to do thisright, you can grow your
business.
Whether you are a part of a bigmachine like running your role
in a marketing department or asales department or something,
(00:48):
whether you're a solopreneur ora consultant, a content creator,
all of the above.
You need to know how to createvisuals that attract people's
attention and connect with thepeople that you're trying to
connect to.
And it needs to be aligned withyour brand, and it needs to be
aligned with your tone of voice,and it needs to be a lot of
things in order to actually doit right now.
Used to be a lot of work,especially when you go to the
video side of things.
You needed to actually have agood story and a good idea, and
(01:12):
you need to be able to createthe right process with
videographers and camera peopleand audio and visuals and
lighting and actors in a studioand like all these things to
actually get these things done.
And the good news is now youdon't have to, you can create
incredible visuals withouthaving a camera and without
(01:34):
knowing anything about design.
Now, obviously if you know aboutdesign, you can do a lot more in
a better, we're gonna talk aboutthis in a minute, but you don't
have to, and you can actuallyuse AI tools to do this.
Now, another good piece of newsis now there's a few tools that
aggregate a lot of thesecapabilities into one tool where
you can do Most of the steps ofthe process in one place without
leaving the tool.
(01:54):
And this tool brings into itmultiple other tools and AI
resources that otherwise youwould need to jump back and
forth, in order to create theoutput.
So today we are going to learnhow to create amazing visuals
that will be thumb stoppers onsocial or will grab people's
attention if it's an adsomewhere or on your website and
how to do this for both imagesand video.
(02:16):
And we are very lucky because wehave arming, Unas with us, and
Armen has been doing this for avery long time.
He's been in design as well asrunning a company that does
branding and design for otherbusinesses for many, many years.
So he both understands thevisual side and the concepts and
the professional side of this.
But in the last couple of years,he's built all in on ai and he's
(02:37):
been posting these incrediblethings on LinkedIn.
That's how I found him.
And he's teaching courses on howto do that.
So he really brings to the tableeverything you want.
As a guest of this podcast, hehas the professional background,
he has the business background.
He's been running his ownbusiness for the past six years,
and he knows AI very, very well,and he knows how to teach it
because he's been teachingcourses.
(02:57):
So if you wanna learn how tocreate incredible visuals with
ai, don't go anywhere in thenext 45 minutes to an hour.
Or if you're driving, stay put.
this is gonna be absolutelyfantastic.
I'm very, very excited to haveyou, Armin.
Welcome to leveraging ai.
Arminas Valunas (03:55):
thanks, Isar.
thank you so much for having me.
And, yeah, I think that will bea great, workshop and I have
prepared a lot of for you guys.
I want to mention that, ofcourse, the experience in
advertising industry is soimportant and I have been
working with the, the biggestbrands like IKEA and, sweat Bank
and others.
But at the same time, I want toencourage you, like Isar
(04:18):
mentioned, like these tools, AIempowers you to create and just,
throw yourself like, fully in,into ai and you will be able to
create the most, capturing and,like the highest quality visual.
So I think, let's jump rightinto this, right Isar?
Isar Meitis (04:35):
Awesome.
Yeah.
Before we jump in, just forthose of you who are joining us
live, either on LinkedIn or onzoom.
Thank you for joining us.
I know you can do other thingson Thursdays, on noontime
Eastern.
but I know a lot of you havebeen joining us every single
week, so I appreciate everysingle one of you.
I also really, really want to,thank you for, participating.
(04:56):
So if you have questions, thenask them in the chat again,
whether you're on LinkedIn, youcan just say it in the chat.
If you are on Zoom, you can sayit in the chat as well.
For now, just go ahead andintroduce yourselves.
this is one of the reasons youjoined these lives, so you can
network and get to know otherpeople.
So tell people where you are,where you're from, what you're
doing, what you're looking toget out of this.
But like I said, if you have anyquestions, please ask them.
So that's if you're here with uslive.
(05:17):
If you're not here with us live,the question is why we do this
every single Thursday withamazing people like Armen that
are gonna share.
Very practical use cases withai.
And then you can ask themquestions if you are around.
And if you're not, you can stilllisten and benefit from it, but
you can participate and you canengage.
and you don't get to experiencethat when you're just listening,
but there's a lot of chathappening in the chat as well,
(05:38):
so you can join thatconversation if you join us
live.
I'll say one last thing before,we dive into today's topic.
Today's show is brought to youby the AI Business
Transformation Course.
It's a course I've been teachingpersonally for the last two
years, at least once a month.
So we've taught hundreds ormaybe thousands of business
professionals on how toimplement AI in your business.
(06:01):
The course is four sessions oftwo hours over four weeks, and
it takes you from whatever yourlevel of knowledge is right now
to.
Understanding all the tools,what they are, what they can do,
how to use them.
A lot of hands-onexperimentation across multiple
aspects of the business.
And we end with businessstrategy, an actual blueprint on
how to implement AI successfullyin your business.
(06:23):
If you haven't done anythinglike this, anything structured
on how to implement AIsuccessfully, you owe this to
yourself.
You owe this to your businessand you owe this to your career.
And so if for being a listenerof this podcast, you can come
and join us with a promo code.
Then the promo code isleveraging AI 100 or uppercase.
There's gonna be a link in theshow notes, and we're gonna
(06:44):
share a link in the chat rightnow for those of you who are
with us live, and you can comeand join us for the session.
The next session starts on May12th.
So if we do these courses, likeI said, every month, but most of
them are private courses.
We teach them to companies andorganizations who, Book us to do
just for them.
And we open a public course oncea quarter.
The previous one was January andFebruary and now we're opening
(07:05):
one in May.
So if you need that, and if youhaven't done it, you need that,
come and join us on May 12th.
That's it.
Now to our session with Arm andArmin, the stage is yours.
show us your magic.
Arminas Valunas (07:18):
Oh yeah.
Thank you Isar.
Thanks so much.
So I think, I will start fromsharing the screen and, yeah, we
will go through, let's say,let's check the last version of
video that I've done, and wewill try to recreate this as, as
fast as we can.
Isar Meitis (07:35):
That would be fantastic.
For those of you who are notwatching, by the way, if you're
driving your car and so on,that's perfectly fine.
We will explain everythingthat's on the screen, but if you
can, there is a YouTube versionof this.
If you're watching this afterthe fact and in your show notes,
you can just open it and clickand go and watch the YouTube
video.
And then you can see,the visualsas well.
Arminas Valunas (07:54):
Okay, so let's this for now.
Isar Meitis (07:57):
Wax London, ethically crafted pieces
designed not just for seasons,but for life stories.
The foundation of lasting stylelies in superior fiber Wax,
London Clovis with character.
So for those of you who can'twatch, this was incredible and I
(08:18):
still can't believe this is AIgenerated.
So it's different images and notimages, like videos of a fashion
show and then actual people indifferent scenarios like.
Driving a boat and walking in abeautiful old city in Europe,
wearing nice fashion clothesand, bracelets and so on.
And I'm blown away that this isall ai.
(08:40):
So I'm personally really excitedto see how this was done.
Arminas Valunas (08:44):
yeah.
And it was so much fun, creatingthis.
So I think, I will go to, to thewhole, process and we will see
how to do this.
So at first, really big thanksfor, my colleague Joe who
inspired me, to create this,like I should mention that this
is real, product, real garment.
I took this from VAX London pageand I just, downloaded these
(09:07):
photos like you see, and Itrained Laura.
Then I trained the second Laurafor character, for my
appearance, but I didn't usethis in the video.
And I generated all these firstlike static images and from
them, like videos and thencreated the whole, show reel.
So let's dive deep, into thewhole production process.
(09:30):
So I chose the Freepik and itactually gave me like really
high quality and at the sametime I think it's, really like
user friendly and really easy toproduce these images.
And later on, all the videos.
So here we are.
In the homepage of Freepik.
And from here, if we wannacreate the images we are going
(09:55):
to create.
from here, we want to train theobject, the garment.
So from here we are choosingobject.
And you just have to press plusbutton.
But, actually I already trained.
So let's go through the process.
So here we say the name, let'ssee wax, then, shirt, the type.
(10:15):
And here we, upload all theimages.
I will upload.
These images.
Isar Meitis (10:20):
So while you're doing this, for those of you who
are not watching, Freepik is oneof those aggregators of tools
that brings you a lot ofdifferent other tools into them
and make it very user friendlyto use.
And what we're doing right now,when Armand says Laura, Laura is
just a way to train a visualmodel on a specific person or
style or object, you can trainit or different things.
And when you train it, it canthen knows how to regenerate new
(10:42):
images of the thing.
In this particular case, ahigh-end fashion shirt.
so what Armen did is hebasically just opened and said,
okay, let's create a newtraining, uploaded multiple
images that he, when I saymultiple, it's seven, like it's
not 50.
And he has seven images that hedownloaded from the website and
he is basically gonna create anew model that knows how to
(11:02):
create this shirt in anyscenario, on any person with any
background because it learns howto create the shirt.
Arminas Valunas (11:09):
This is exactly what I have done.
And actually, to be honest, youneed to upload, and, my, kind of
recommendation would be all thetime, follow all these tips and,
it says 12 to 25 images.
So for this, if you don't have12 at least, because if you have
o only seven, it'll not allowyou to train the lara.
But then what I did, I,basically changed the
(11:32):
composition of the images andflipped the images horizontally.
And I had 12 images and I wasable to train this Laura.
And yeah, actually it's so onpoint.
I wanna interrupt myself a bitand, maybe.
To explain how I understandLauras there are so many
technical, terms about, Lauras,but in general, it's, low rank
(11:53):
adaptation and, let's say, thisis our like flux.
And by the way, we are trainingon flux.
So let's say this is, all theflux model and all the whole
data is in here.
So we are training, like justone little piece, like this is,
our like train Laura.
And it, shows the model like, ifit's only, object or like
(12:14):
character, it shows how wewanna, generate the special,
like this special object.
So in this case, I already.
Generate Laura.
So let's say we, we generate it.
'cause otherwise we would bewaiting, pretty, long time.
Actually it's quite fast, butmaybe still takes 15, 20
(12:34):
minutes.
So we don't want to do this.
So I created Laura already.
Isar Meitis (12:39):
we'll do the cooking show thing, right?
We're pulling out of the ovenAnd for those of you who don't
know what flux is, so there areseveral different leading visual
image generating models in theworld today.
probably the best open sourceone is flux.
So it's just a name of an opensource, model that works very
well.
because it's open source,there's a very easy, process on
(13:00):
how to train it.
And in this particular case,it's built into a simple user
interface that runs in Freepik,which makes it even easier.
Arminas Valunas (13:06):
I think most adaptable and if I can say this,
like trainable, models outthere.
'cause it's open source and youcan do whatever you want with
flux and it gives you such ahigh quality.
So definitely I recommend, ifit's, for training objects,
characters or styles, just, use,flux.
You can do this, by the way, onlike older ones, like SDXL or SD
(13:28):
1.5, but Flux is, the best atthis point.
we have already our train objectin this case, this V London
shirt.
And by, by the way, there arelike many, pre-trained objects
in, Freepik that you can just,choose and maybe test if you
don't want to, let's say trainyour own law.
'cause it costs a lot ofcredits.
(13:50):
So at first it's a good idea to,play around with a pre-trained
object.
So when you have this trainedobject, in this case our
garment, we just select this oneand at Lido X, it's my, train
Laura name, and it appeared inthis field, in this box.
And here, if it's, active, itwill, generate in this train
(14:12):
Laura product.
here, I can, start typing andcreating prompt, but actually I
already have a lot of promptsprepared for us.
So I will not be doing, creatingfrom scratch.
let's dive deeper a bit into mythinking.
So I have a product and I was,exploring, two cases, like
consistent character and,different characters.
(14:33):
And, yeah.
Let's talk a bit, before I startJanuary, let's talk about, the
process and the thinking.
I divide, or at least I amworking in three stages.
So the first stage ispre-production, where like
creative ideas are born, whereI'm creating like mood work
where I find, the tone of, nottone of voice in this case, but,
(14:55):
color palette and, the wholewiden mood.
And then I am usually drawingsome sketches, like rough
sketches.
But, if you don't want to draw,it's, not necessary, but just
creative process and,pre-production is so crucial and
so important for, getting thebest results.
And also, of course, nowadays,helps, like AI tools and LLMs in
(15:15):
general, let's say chat, GPT.
It helps in every process,especially in creative process,
in pre-production.
So I am, like chatting with the,like generating creative ideas,
chatting, with the, in this casechat g pt.
But, also I'm exploring othertools, as well.
So I think it really, depends onyou and your style, but,
nowadays it's just theleveraging your creative
(15:38):
capabilities and you don't haveto.
let, the AI kind of drive yourcreative ideas and your
creativity, but you shouldempower and leverage, your
creativity with ai.
So the second stage productionitself, where I am, generating
images, videos, making someselection from all the material
(16:00):
that I have editing, combiningmusic, voiceover and everything
falls in into place.
And last touches also, this isreally important.
I think this is where magichappens, is, post-production.
And it's really important,because retouching and color
grading and, it's just, liftsyou into that.
(16:20):
This like pro quality that youare reaching.
Isar Meitis (16:22):
Yeah, so quick summary, three steps.
one is, pre-production where youget the ideas basically and more
zoom in and what exactly you'retrying to create.
And as Armina said, if you'revery creative, use your own
creative ideas.
If you're not, you can use largelanguage models to help you
through the creative process.
And think of an idea that willwork for your target audience
that is aligned with what you'retrying to do.
(16:43):
Literally just have aconversation with it.
Explain what you're trying to doand it can help you.
creating mood boards, roughideas on how the video, so the
video that we've seen had, likesomebody, it started with
somebody walking in a fashionshow and then people walking the
street and then somebody in aboat, and then a closeup.
there's all these componentsthat in your head you need to
know that you need in order toactually show them afterwards in
(17:05):
the results.
So this is more in the creativeprocess, and then you create all
these components and then youput them together.
So now let's go to the steps ofactually how to do it.
Arminas Valunas (17:13):
Let's do this.
I was jumping around a bit, but,it's really important to,
mention these steps.
'cause yeah, absolutely.
You skip something, it'll bemessy and, it's even like before
ai all the time, we are usingthis kind of, process.
let's say we already havetrained object, garment at in
this case, and let's say I'mjust, create like some simple,
(17:35):
prompt and then I will comparehow it, appears with the
advanced prompts.
So man walking in the street,natural daylight.
it's important to point that,this, works with a flux model,
and if you want to, oh, it's,and you see it's, not working
all the time.
So it give me like fourvariations, but the first one is
(17:57):
maybe the most accurate.
that's why I'm more into othertools and, like using confi, but
this is a whole another topic.
So.
it's important to mention that,here you can, demo mode and you
can choose the model.
so it's, like you see, it'smystic, it igram, imagine three,
but it works only with the flux.
(18:18):
because we train Laura on flux,we can't train, on like other
models.
yeah, so
Isar Meitis (18:23):
again, for those of you who are not watching in
Freepik and similar tools aswell, like Korea, you can choose
many of the image generationmodels.
But now, because we trainedflux, we gotta use flex.
But if you're just generatingimages, not on a trained model,
you can use all of them.
Arminas Valunas (18:38):
Exactly.
I'm using a bit more advancedprompts and, this is also deep
topic it is an art of itself andwhen I'm using more advanced.
Prompts it gives, well, for meat least, it is much better
quality and much moreinteresting.
Isar Meitis (18:53):
let's read the section of this prompt just to
tell people the understanding.
So they understand what you meanby a more advanced prompt.
So let's just read some of it.
Arminas Valunas (19:00):
Yeah.
So, the prompt, mid-lengthfashion, runway, short subject
focus, male model, walking,wearing white shirt, subject
details, fit, male model, whiteswept back brown hair, we point,
more accurate, details toeverything, to characteristics
to character, what he's wearing.
and when you prompting withELOs, in this case, you
(19:23):
shouldn't be confusing themodel, let's say if I, would try
it.
Like red t-shirt or somethingtotally different.
It would be, confused and, won'tgive you like good results, but
this is also, maybe I wanna showyou, a bit, where you can start,
like, how can you, learn how toprompt?
So I think the best start is,just, let's say download this
(19:46):
one and just, to upload, theimage into the chat, GPT and
just ask, describe the photo.
And I'm in the camp where likepeople are saying like, but you
are copying, you are doing thisor that, and this is bad.
But actually it's not like youare just trying to figure this
out.
What model, because vision modelitself, it gives you the answer
(20:09):
how it interprets this photo,and you just, borrow these, key
phrases, but you are making yourown prompt.
it's really good base.
yeah, again, to
Isar Meitis (20:18):
explain, for those of you who are listening, you
can take an image that you wannamimic the style of, or the
concept, or in this case it's amodel on a runway how.
To start prompting better, youcan just drop an image that is
your inspiration and say, Iwanna write a prompt that will
generate a similar image in animage generation model.
I want you to write a verydetailed prompt that will mimic
(20:39):
everything in this image,including the style, what he's
wearing, the background, and soon, the lighting.
And it will give you a verylong, detailed image that then
you can use as your baseline tomake changes and massage to
whatever you need.
One more thing with regards toprompting, pre-trained models
with Laura is I'll say moreextreme than what you said.
It's not just don't confuse it,but tell it what it is.
(21:00):
if you would say a buttoned up,stylish white shirt, describe
the thing that you trained iton, it makes it even better and
it will give you more consistentresults.
So don't just trust the trainingof it to be perfect, but also
describe it in your prompt andyou will get more consistent
results, than if you don't.
So let's continue with theprocess.
So now you have the images ofthe guy in the fashion show.
(21:22):
I assume you do the same exactthing for all the other
characters, right?
The guy in the boat, the guy inthe street.
I'm actually very curious aboutthe closeup one because one of
them was very different, right?
Most of them were like fullbody, relatively, kinda like
style was similar.
One of them, you literallyspecifically asked for closeups
of the fabric and closeups ofthe person,
Arminas Valunas (21:41):
tip centric.
And I will, reveal all thesecrets.
Okay.
Awesome.
Maybe let's, dive deeper and,maybe let's go with the like
generating video and then I willgo to this micro shot.
let's say we, really love thisshot.
then, what usually I'm doing,actually you can go like
straight to the great video,but, actually I'm, upscaling and
(22:02):
really good at, Freepik has themagnifi upscale, which is, the
best upscale, I would say.
Yeah.
So I am editing I'm pressinglike edit button, and then I am
upscaling and it's basically thesame parameters that in native
Magnifi on its own, but, yeah,everything is the same.
I have a few presets when Idon't want to change the
(22:25):
character appearance, I tend to,lower all the creativity stuff.
Parameters or, like portraitsoft is really good.
So let's say, I will upscale andit'll take some time, but, not
that much.
during this time while wewaiting, I can, reveal my
secret.
So actually, it's not aboutgenerating, especially when we
(22:45):
are working with the realproducts, right?
And garments and clothing, it'snot all the time just, generate
for the sake of generate, atleast in my thinking.
So I actually just took thisphoto.
it's the same photo, but I tookthis and, actually I generated
using.
runway.
runway is, really coolespecially like junk four.
(23:06):
And they released this latestmodel, I think two weeks ago.
So it's really new runway
Isar Meitis (23:11):
version four.
so that's a good trick again forpeople.
for those of you again, who arelistening, what he's done to get
the really extreme closeups isactually use.
Actual closeup photos from thewebsite and then animated them
with tools.
In this particular case, runwayversion four is really good with
consistency.
which is very important whenyou're trying to do stuff like
that and actually have the shirtlook like the shirt.
(23:33):
so now you have the standalonecomponents, you upscale them And
then you animate straight fromthere.
Arminas Valunas (23:40):
Yeah, actually from upscale photo, But, when we
upscaled, we can't, generatevideo directly from here.
So we have to go back tomigrations and.
Press here, and now we talking.
So now we can create video.
So we are pressing create video,and here is the video and also
(24:00):
you see the section.
the first stage images, andsecond section would be videos.
And it automatically gave me aprom, but, in this case,
actually it's quite good.
a male model confidently walksdown a minimalist runway.
So actually in this case, I willuse this, but, I can, give away
another secret.
what I'm doing, I created my ownArmada, video prompter, and
(24:24):
usually I'm just, Using this, itjust elaborates your prompts.
it just makes better.
So I upload, the photo and,let's say man is walking towards
camera and we will get reallydetailed, prompt, and even two
prompts actually where itdescribes like what is, the
(24:44):
composition, the, wide angleshot.
how the model looks like and allthese things helps to generate
like much more accurate, videosand actually it made my videos
much better.
I just wanna
Isar Meitis (24:57):
pause you again to explain.
For those of you who are notgreat prompters, and especially
when you're moving, even if youare a great prompter on an LLM
and now you need to prompt avideo model, it's a little
different.
And the best way to do this isto have some kind of a
framework.
And if you don't have one, thenthis particular case Armen
created a custom GPT that doesit, and all he does is He
uploads the image that he isalready created into the custom
(25:18):
GPT and tells it a general ideaof what it is, and it creates a
very detailed prompt.
Now, if you don't know what toput in a video prompt, you can
ask.
Cha pt say, I wanna build avideo prompt What component
needs to be in it?
And it's gonna tell you it needsthe composition and the lighting
and the motion of the camera,and the motion of the character
and the feeling you want to getand stuff like that.
(25:39):
and then more details anddifferent characteristics of the
person and what's happening inthe shop.
And so it will tell you all thedifferent components and then
you can ask it to build like aprompt generator for you based
on that.
If you fit it an image, and thenit will do the work for you.
So it sounds really fancy, butyou can start very quickly and
get probably not the same levelof results that arming got
(26:00):
because he's been doing this forx number of years.
So he knows what he's lookingfor, but he will get you from
knowing nothing about it to 75%there, which is way ahead of
most of the people in thepopulation.
Arminas Valunas (26:12):
Yeah, definitely.
And I wanna share some, thinkingbehind this.
So actually you can do thisperfect.
custom gpt on your own.
Just, let's say, this is a greatexample.
I created also, custom GPT forgenerating, describing pictures.
So you just, go to the page ofthe.
model itself.
(26:32):
let's say this is frames byrunway, this is like prompting
guide.
So the best thing is not to tryto guess how to create, custom
GPT, these, developers, the,giving you all the information
how to prompt.
just copy this, all the infowith the example and, feed to
the knowledge base.
And you have perfect, Custom gt.
Great idea.
(26:52):
Yeah.
yeah, let's, continue.
I decided, my own prompt with mycustom GPT is better, so I copy
paste here.
And, let's check a bit, aboutthe video models itself.
so now it says, CL 1.6 Raw, butyou can press here and, you can
choose all different models.
so I think, in my experienceit's still Ling 1.6 is the model
(27:16):
that I am going, most oftenwith, especially, when using
Freepik, like Google VO two,it's also real super, good and
like really high quality.
But I'm using more, from text tovideo.
'cause actually from image tovideo, it is, just in my
experience, like ling.
Delivers better, better results.
Isar Meitis (27:36):
Yeah.
And again, for all of you, the,one of the beauties of tools
like Freepik is that it givesyou access to all of these
tools, right?
So you can pick and choosewhether you want to use, this
image generator or this videogenerator.
And the cool thing is you cantry it with three different
ones.
And yes, you're gonna pay tokensfor all of them, so it's gonna
cost you a little bit of money.
But if you're doing this for abusiness purpose and not just
(27:59):
for fun, then it's still gonnabe significantly less money than
you spend ever on creating aprofessional video for anything.
yes, you're gonna run this on VOand Cling and Sora and Runway
and all four videos are gonnacost you.
$10.
it's still nothing compared towhat it would've cost you to
(28:19):
even just get the actor for 30seconds would've cost you more
money than that.
And so it's worth sometimesbecause what you are trying to
do might be different than whatARM is trying to do.
And the only way to know whetherthe style and the thing you're
looking for works better.
The other thing is you maylisten to this episode two weeks
after we recording it, which mayhave something completely
different on one of thesemodels.
(28:40):
So it's always worth trying todo this and just trying
different models and see how itcomes out.
And once you've done a few andyou consistently like, like
Armen is saying, he alreadyknows that for the stuff that
he's doing, cling works best.
And I'm sure that a month and ahalf from now when a new model's
gonna be out, he's gonna try theother model as well and see what
is actually working better.
But you gotta experimentyourself in your style and the
(29:00):
thing you're trying to do inorder to see what's gonna work
for you.
Arminas Valunas (29:04):
Yeah, so great.
wow.
definitely.
I agree 100%.
And, it's changing daily.
Like maybe tomorrow it'll bedifferent in case.
Yeah.
let's choose then cl 1.6 andsometimes I mess this part.
So it's really important tochoose like different, aspect
radio.
So you have ability to choosefrom these three, in this case,
(29:25):
in, when using three pick, inothers, like you can choose,
other aspect radios too, buthere, like three aspect radios,
so we are choosing social story'cause it is vertical.
Yeah.
And then click generate.
So while it is generating, ofcourse I will be showing other
things, but, basically it's thesame process for all the shots
(29:47):
that we have, right?
Yeah.
This is the first one.
We will not be able to generateall these shots, during this
workshop, but you get the idea.
And then I am combining, I'mcompositing everything.
in After Effects.
I'm using After Effects, I wasdiving deep into, character, LL
Laura training for characters,and I was testing with my
(30:08):
appearance.
So actually not that many peopleknow that you can combine
Laura's, in three pick as well.
while generating, let's go backand, it's the same process.
you can generate, train Laurason style, on characters and
objects.
You select the gender.
you upload the images.
and then, actually I didn'tmention, but, if you wanna even
(30:31):
like better quality, you should,choose ultra and then again,
create your character and youhave your character here.
it appears in this panel, andyou can just press the arm and
we have, okay, it appears at theend of the prompt, So we have
two, character and object aswell.
So let's try generate with atool r.
(30:53):
Yeah.
So
Isar Meitis (30:53):
again, for those of you who are listening, what
Armen is showing right now isactually very powerful because
you can train the model on acharacter.
This could be basically yourmodel.
And this could be yourself, itcould be somebody else.
you need obviously permission ofthat, somebody, but it could be
somebody that's made up, meaningyou can create a model with an
image generator that doesn'texist, and then train on that
(31:16):
and create more and more imagesof that person.
And the interesting thing isthat then you can dress up that
model with whatever object inthis particular case, a shirt
that you trained in a differenttraining set.
So now you can combine theperson and the object into a
single image and then createvideos.
(31:37):
from that.
And the same thing for style.
Like you can train on style andthat could be the style of your
company or just the theme youwant for that particular, shot
or video, and you can do that aswell.
And the output, we now seeimages of arm with a lot of
hair.
No, no driving, driving a boat,but wearing the shirt that we
(31:57):
were creating previously, whichis really cool.
Arminas Valunas (31:59):
Yeah.
I think I, have to read theprompt, but I created the, like
previously and you see it'scool, yeah,
Isar Meitis (32:05):
great
Arminas Valunas (32:05):
shots and of course it's, we are giving away
a bit quality wise, whencombining two ours.
And, it's not, not that accuratemaybe, but here it's good.
It's not bad.
It's not bad.
if, you are not like, gettingthe best, result, you can lower
the strength.
Like you can, choose theparameters of the strengths so I
(32:25):
can lower the strength of my,character and then, try again.
But at the same time, I willlose a bit of likeliness.
But, like we see, it's prettygreat results actually, and a
combined two lowers.
And, from here I can generatemore
Isar Meitis (32:41):
let's go back to a process for a second because I
want to put it all together.
So I'll do the review to wherewe are till now, and then I want
you to say, what are thefollowing steps.
So step number one is getting anidea.
You can do this with AI andbrainstorm back and forth in
defining what you're doing withit.
Step number two is getting yourresources.
So in this particular case itwas images of you, so the model
(33:03):
or images of a general model andimages of the actual product.
In this particular case, it wasa shirt and we had multiple
views, including closeups of theproduct.
And then we trained a LoRa,which basically means training
an AI model.
In this particular case, themodel was flux.
And you do this, it soundsreally fancy, but you do this
literally by following theprocess on a tool like Freepik.
(33:25):
You upload a bunch of images andyou train the model, and now you
can use that train model togenerate images of that object
or that person, or like we sawthe combination of them again
and again.
So this way you create theimages, which will become the
different shots in your video.
Then you upscale each and everyone of them.
So within, still within the sametool, you upscale the images to
(33:45):
get a higher resolution.
By the way, that's true in allthese tools.
Every single image generationtool you're going to use, the
initial output is a relativelylow quality.
And if you want to use it foranything professional, you
probably wanna upscale that.
If you need just for socialmedia, you probably could do it
what it is.
But if you need anything morethan that, you wanna upscale it.
Once it's upscaled, there'sliterally a button.
Once you're looking at the imageto create a video, then you can
(34:08):
prompt it again to define whatthe video.
And as Armen mentioned, you canuse a custom GPT that you can
build on your own very easily tohelp you write these prompts, to
get better at prompting thevideo output of the tool.
And in the end, you just editthem all together in an editing
tool.
That could be a professionaltool or just a basic tool.
(34:30):
You can go as basic as Canva oras advanced as.
After effects and Premier andtools like that and anything in
between.
But it will allow you to put allthese short videos together, cut
them and do the transitions asyou need, add text on top of
them, and so on.
Anything else that you add inaddition to get to the final
product?
Arminas Valunas (34:49):
Yeah, maybe, first of all, you so good at,
summarizing and putting all thedots in, into places, connecting
all the dots, so I think, Idon't know if you, if you heard
the sound of this video while Ishow Oh yeah,
Isar Meitis (35:03):
there was a nice music in the background
Arminas Valunas (35:05):
and voiceover,
Isar Meitis (35:06):
Did pieces designed not just for season.
Arminas Valunas (35:10):
so yeah, the last step, I think of course,
like music and you can generatemusic, if you want to.
AI generated music, the besttools are, soon on and Audio.
And, both of them, by
Isar Meitis (35:23):
the way, are free.
So you can generate any musicyou want as many times as you
want for completely free, whichis mind blowing.
So again, the tools are, SUNOand UIO are two very solid
competitors and they keep onimproving all the time.
But you can create any stylewith voice, with singing,
without singing, and until youland on the one you really like.
Arminas Valunas (35:42):
Yeah.
and, the last component, in thiscase it was, generating
voiceover.
So I just, created some,copyright, some text generated
wax, London ethically
Isar Meitis (35:53):
crafted pieces.
Arminas Valunas (35:54):
This is not the best, but, you get the point.
you can go to text to speech 11labs.
It's, the best at generatingvoices at this moment.
And you can choose from likelibrary desk that has, I don't
know, like thousands andthousands, voices.
And also what is really coolabout this, you can, train your
own voice and use it, even, Idunno, for many cases.
Isar Meitis (36:17):
so one more thing about 11 labs and the voices,
yes, it comes with all thesevoices, which are, again,
endless, but even within eachvoice, you can control how fast
it speaks and how soft itspeaks, and how much emotion
it's gonna have, and how muchconsistency it's gonna have.
So once you find a voice, youcan still control that voice for
that particular sentence.
And then you can run it againand say, okay, Next second
(36:38):
sentence faster or whatever youwant.
So you have a lot of control on,even within a specific voice,
how it's gonna sound, so you canmake it even more realistic
between your different scenes.
Arminas Valunas (36:47):
Yeah.
and this, how it's calledcharacter voice acting.
So 11 labs released, like fewweeks ago.
I think the voice acting, youcan upload your own recorded
video with your own intonationsand, drive the video, apply
let's say the voice of this,Johnny Boy, and get your own
style.
(37:07):
Style and
Isar Meitis (37:08):
intonation and, yeah.
Arminas Valunas (37:09):
Yeah.
Yeah.
Yeah.
So it's, it's definitely sopowerful and, I think it's also
the whole another topic, to divedeep into 11 labs.
So I think we don't have, somuch time, but, yeah, I think,
this is, the whole process andlet's check a bit, behind the
scenes.
So I am using.
like I mentioned, the aftereffects and these are all the
(37:29):
different, generated voiceovers.
This is soundtrack and, it's notthat kind of complicated, I
just, edited the video maybe.
sometimes slow down Ah, one morething.
let's say, post-production.
didn't mention this, but, allthe time I'm using top as video
ai.
So now I will turn this on.
it's the best, video op scaler.
(37:51):
it's just like next level, interms of quality.
'cause usually you also aregetting not the best quality in
terms of, resolution.
of course, some, video modelslike, let's say the last, gen
four, it, gives you ability toupscale to 4K.
I already upscaled this one.
So you can also upscale nativelyin the runway if you are using
(38:13):
one, but if you are using othermodels, welcoming, so it gives
you full hd.
But, usually I'm upscaling to 4Kat least.
Isar Meitis (38:21):
okay, so I'll put the final step together that you
mentioned, creating music.
You can do with uio or with Sunoyou can create the voiceover
with 11 labs, which isdefinitely the most advanced
tools for these two things.
And you can put it all together,like you said, whatever editing
software.
You mentioned two tools forupscaling, Magee is probably the
(38:42):
best image upscale are out theretoday.
And, Topaz for video.
Both of them are really good.
Both of them are reallyexpensive.
So there are other options thatare not as expensive, that are
good enough probably for most,use cases.
There's even some open sourcetools that are completely free
that you can use, but definitelyif you want the best, then topaz
for video and Magnifi.
(39:02):
Four images are the best ways todo up scalers.
And if you're doing thisprofessionally, Armin does, then
it makes perfect sense.
Armin, this was very powerful.
Like literally anybody who wantsto create these kind of videos,
or images or a combination ofthem, this was a great session
for them to learn.
If people want to learn morefrom you, follow you, see your
work, work with you, what arethe best ways to do that?
Arminas Valunas (39:24):
So follow me on LinkedIn.
I'm most active there at thismoment, and I'm thinking of,
launching a wait list and just,to get, know the kind of
position of people, whether theywant, learn and, to, collaborate
together.
and, then we will decide if Iwill be doing some kind of,
(39:44):
workshops or online courses.
Isar Meitis (39:47):
Awesome.
Cool.
one last thing that I wanna say.
we touched a little bit aboutFreepik and so on there, there
are multiple ways to do what wedid because in, at the end of
the day, there's multiple toolsbehind them.
The easiest way to get startedbecause it puts everything in
one simple user interface withclear things to click and so on,
is either Freepik or choa.
Both of them do similar things.
(40:08):
I must admit I'm not a pro onany of them.
I played with both of them justenough to be dangerous.
but both of them do the samething.
They bring in multiple visual.
Tools into one tool, and you canpick and choose what you wanna
do.
And in most cases, they stillgive you the flexibility of the
parameters in each of the nativetools.
So whether you're using an imagegenerator and the parameters in
(40:29):
it, or whether you're using,LoRa and training capabilities,
or whether you're generatingvideos and you have controls,
that comes with that.
So if you want to get startedand you don't want to get a
license to six or seven or eightdifferent tools, the easiest
ways to get started is to get alicense and buy x number of
credits in one of these tools,either Korea or Freepik.
And you may have a better, idealon which one will probably work
(40:51):
better.
once you have that play aroundand if you do say, okay, yes,
this is too expensive for me, Ijust wanna get one tool, you can
always go and do that.
But I think as a starting point,it's a very solid starting point
because it's a relatively simpleuser interface that brings
together a lot of other toolsthat you would otherwise have to
get individually.
Arminas Valunas (41:08):
definitely.
I think, you can, explore, maybeseparately, let's say, image
generators, like Mid Journey andothers.
and then to combine also, buysubscription like natively, CL
or Minimax or, runway, but it'llbe much more expensive.
So all in one platforms, I wouldgo with a Freepik or Korea at
(41:29):
this moment.
Yeah.
Isar Meitis (41:31):
Yep.
Fantastic.
I just wanna say thank you foreverybody who is, who are
joining us live again, we hadpeople today again, just to tell
you, we have Patrick from India.
We have.
Paul from the Netherlands.
We have, Asai from, he didn'tsay where he is from, but based
on the name, he's, probably fromIndia as well.
We have, Rahil from Pakistan.
(41:51):
We have obviously multiplepeople from the us and so really
people from all around theworld.
This is ah, Berlin.
So we have Marta from Berlin.
And so really great to seeeverybody from all around the
world in this live session.
I really appreciate all of you,joining us live.
great work.
Armen, I think you opened theeyes of people.
Some people, wrote in the chatlike, okay, that's obvious that
you need design skills to dothis.
and the answer is it helps alot, right?
(42:14):
But it's definitely notnecessary.
So I have zero design skills andI do stuff like that as well,
and I don't do it as frequentlyas Armen does, but I'm getting
pretty good results.
So all you need is toexperiment.
Like literally go and tryyourself, get yourself a license
to Freepik or choa and just togive yourself a test project and
just play with it.
Try different models, trydifferent, prompting skills.
(42:34):
Use AI, whether Chachi pt orClaude or Gemini, it doesn't
matter, to help you prompt andplay around.
And I think you'll be reallysurprised with how good your
outputs are going to be based onwhat you think your skills are,
and then you can move forwardfrom there and get better and
better results.
Thanks again, Armin.
Thanks everybody.
Have an awesome rest of yourday, and I will see you next
(42:55):
Thursday.
Bye everyone.
Popular Podcasts
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com
On Purpose with Jay Shetty
I’m Jay Shetty host of On Purpose the worlds #1 Mental Health podcast and I’m so grateful you found us. I started this podcast 5 years ago to invite you into conversations and workshops that are designed to help make you happier, healthier and more healed. I believe that when you (yes you) feel seen, heard and understood you’re able to deal with relationship struggles, work challenges and life’s ups and downs with more ease and grace. I interview experts, celebrities, thought leaders and athletes so that we can grow our mindset, build better habits and uncover a side of them we’ve never seen before. New episodes every Monday and Friday. Your support means the world to me and I don’t take it for granted — click the follow button and leave a review to help us spread the love with On Purpose. I can’t wait for you to listen to your first or 500th episode!