Transcripts
1. Intro Flux Ai: Right. Welcome to Flex AI
consistent character mastery. In this transformative course, you will unlock the power of
AI to create and personalize your unique characters
and insert them into any scene using the Flux AI
and a special hagipt formula. First start, I'm showing you some amazing photos
of my wife that demonstrates how you can insert yourself into any
scene with Flux AI. I'm sure these stunning
images will captivate your interest and set the
stage for what's to come. Either, have you ever
struggle to create an eye catching social
media time leves that truly stand out, or maybe you have imagined
yourself in a cinematic scene, but you didn't know how
to make that happen. If so, you are in
the right place. I'm Soli art, and I'm super
excited to show you how to do all this and
more using flux AI, a tool that is an awesome
alternative to me Jenny. In this course, you will learn how to insert
yourself into any scene and design social media time
neils that really pop. We'll start with
a quick and easy Flux AI tutorial
to get you going. Then I'll share my
Go to go prompt trex to help you create
top notch images. After that, we'll work on
training or photos to keep your character consistent
in any scene using flux AI. And to wrap things up,
I'll teach you how to make professional looking social
media time nels with bold texts and the perfect
facial expressions. Plus, you will get access to all my prompts and formula in a handy
power pointer slate. I can't wait to get
a started that you?
2. Flux AI Introduction and Advanced Settings: Access to Flux Laura Model, first, we have to sign
up on Hugin face. Let's go to hugging face.com on the right
side Tabn sign up. Since I've already logged in, you just going to let me in. After you sign in, you have two ways to access
Flux Lora Model. If you sit on the right side, tab on it, Flux
Laura, the Explorer. And remember, always look
for the new Flux model here. Sometimes the Flux Laura, the explorer is runtime error. It's getting an error, right? So you always work with the new one Flux 01 development
version, Flex 01 Chanel, Flex realism, so just open them up and use them easily.
So don't forget. Always look for the new
version of the flux here. And these models will
be updated every day. So, for example, here, flex realism laura emigerator. Put your prompt
here and generate, or the simples one, flex 01 chanel, which is giving
you the exact same thing, and the settings are here, or flex 01 development version. Given you the better
quality for your images. All right. Let's start
with one of them. And you're just
going to jump in. And also in your
PowerPoint a slide show. The link is here, just
tab on it and urine. Flux AI is an advanced
open source text to mage AI model developed by Black Forest lab is free
and it's like met journey. Here in Laura Gallery, we have too many filters. If you're looking for cartoons
or animation tab on it, put your prom here,
and you're done. But in our case, we only need flux
realism. Just tab on it. Make sure here is type on prom for flux realism is appeared. It means we are good to go. Now in prompt section, let's type realistic portrait
of a beautiful blonde girl. Tab on generate, and
let's see what we get. As you see, it says, it's going to take
around 46 second. And this is the maximum. Most of the time,
it's just going to be finished around 22nd. All right. It's done. And
how beautiful is that? Without even touching
the advance setting, we get this beautiful portrait. On the top right
corner of the image, you see the share
and download baron. Tab on download to
download the image. As you see, the format
is VP with 73 kilobytes, which is very low. And this is the
main issue that we have here because
it's totally free. We can use so many images
here without paying anything, but the quality is very
low. How to fix that. Just simply go to Hugin
face.com slash space, or you just click here in the search spaces
type Face scale. The first one is Night Ferry, the creator of this free model is the one that
we're going to use. Just tab on it, and
here you are in mage scaling and
Restoration model, which is specifically
works on face. Just drag and drop
your mage Here, make sure is on version
1.4 and put the re scaling factor on ten to get the best quality
image of it and submit. In less than 30 seconds, we get this large upscale
image with the best quality. And as you see, is 2.4 megabyte, and just simply
download the image. And this is how we
fix this problem. Let's come back to Flux
Laura the Explorer, and at the bottom, you'll see the advanced setting, Tabans little icon here. Here, we have CFG a scale, steps with and height. Before I explain CFG and steps, let's put the highest
amount that we have here. Here, we have 15 36,
which is the highest. But I will show you a track. You can put any number
here, and it works. Let's test it with 15 36
heights and generate it again, and we get something like
this, which is beautiful. Let's download it.
Again, Dragon drop here, number ten, submit, and we
get the highest quality. Let's come back to
advanced setting again. This time, let's
talk about the CFG. And what's going to
happen if I put it on 20. CFG scale is a parameter that controls the flux
model and how strict, it should follow the prompt
input in ma generation. So basically, the
higher the number, the more actual generation is going to be look like prompt. But based on my experience, the 3.5 is the best
for this model. But you can test it out if I put it on 20 and generate it again, as you see, I will get
a more realistic image. Again, we can do the
process of upscaling that. This time, I'm just
going to put the CFG on 3.5 and steps on 50.
What is the steps? The flux is the parameter
is a parameter that controls the number of etration in the
generation of images. Atration refers to the
repetitive cycle starting from generating random noises
based on the text input. When an image is generated
with a flux model, it will go through many steps, typically about 20
to 30. That's why. I I put it on 50, it's just going to
take more time. And GPU to produce an image. But the result is going
to be more realistic. Now, what if the CGF scale
is on 20 and steps or 50, let's try out with
the same pront. And here it is, the result is absolutely very realistic
image. And how cool is that? So by controlling the settings, you can get exactly what
you're looking for. But for us, most of the time, we put a CFG scale on
3.5 and steps on 28. The left one is CFG 20 and the right one is CFG
3.5 and steps on 50. And I believe both
of them are perfect. So now you know how to control the advanced setting
and flux Laura model. I have generated more
than 200 images here, and I got this error, and I have to wait
for 29 seconds. To let me generate
the next image. The simple solution
for that is log out and log in with
another g mail. And I can run this again for a week without
even any problem. And after that, I can go
back to my previous e mail. And this way, it's just
going to work forever. And let me show you a track. Here in Advanced setting, you can put your desired
heights, for example, here, 1920, and you can generate your image to get
exactly the same size. And how cool is that? All right. Now you know how
to work with flux, Laura, and Hugging Face.
3. Mastering Prompt Formatting and Formulas: Understand the importance of well written prompt for
generating high quality images. At the end, I'm
just going to give you my prompt formatting. The first is the subject
like a woman walking. Then is the film type. If you like, you
can put it here. If you don't, don't put
it like Corak gold 400. If you're looking for
a specific film type. The next is camera angle. If you want your model or image, be at eye level shots or low angle shot or
high angle shot, extreme low angle,
Vb cama style, underwater shots,
underwater close up. Like we have so many
style and angles here. The next number
four is lighting. Are you looking
for natural like, like sunny day, snowy,
overcast, foggy, hazy, Sunrise, golden hour, or studio like like catch light, split lighting, loop lighting. The number five is
ambient or styling, like dark and moody image, bright and vibrant,
Fantasy,torical. The next is location. You can put like New York, Central Park, Egypt,
Eiffel Tower. The next. If you're looking
for a specific style or photographer, put
photographer's name? Like in a style of Steve McCury, Ansel Adams, Mario Testino. The next is cameras and lenses. You can put taken
with a R Alexa, LF camera with Ri
signature prime lens, 12 millimeter, 1.8 aperture
or red ranger monster. And at the end, you can put some fine tuning,
like cinematic, photo realistic,
atmospheric, filmic, hyper realistic, Bok, elegant. So on. And here is an example. A woman, fi type can be ora
gold for 100 camerngle, eye level shot, lighting, in natural lighting,
in a street style, in New York, photography
by Annie Le Bovez, shot by Aria Alexa, realistic, supernatural,
and you're good to go. Now, let's put the
prompt like this. Extreme close up of a single neon girl eye,
direct fronted view, detail iris and pupil, sharp focus on eye
texture and color, natural lighting to capture authentic eye shine and depth. The word love is
painted over it in big white brush strokes
with visible texture. If we put this on this
prompt section and we generate We'll get
exactly something like this, and we don't change
the advanced setting. This is a very well
prompt format. But most of the time, you don't know what you want. You don't know exactly how
to put these words together. The best way to do that is with this full
prompt formatting. First, let's understand
the prompt formula. This is what I put in GPT
or perplexity or clot. Any time is started with prompt, create a prompt if the
word count limit of 500 words for the AI based text to image program using
the following parameter, one, two, three, four,
five, 6789 parameter. The first param number one, should be replaced with
a user supplied concept, and two should be concise descriptive
summary of a subject. Ensure that description
is detailed, uses descriptive
adjectives and verbs, a diverse vocabulary,
and sensory language. Number three should be concise summary of
sense of environment, number four, mood of the scene. Number five, atmosphere, number six, lighting,
number seven, realistic photography
style, Number eight, camera on lenses, number nine, cinematic, eight K realistic. It's important to remember that the description is the prompt
should be written together, separated only by commas and spaces and should not contain
any line brakes or columns, brackets, and their contents
should not be included. And this is the general
idea of our prompt. Now, let's go to CGPT, sign in, create a U tab, Here, I'm just going to
copy this prompt formula. Put it on GPT, Inter. You're just going to
give me an example. After that, going
to be 500 words. Let's go back here. I'm just going to copy this prompt prompt
column, and our prompt. Okay. Now, I'm just
going to copy this part, Control C, make sure the flux realism is selected
here and generated. If we do that, we're going
to get something like this. What is this link? The file dot AR. If you tab on it, to go to
file.ai and the sign up part, if you tab on sign up, it's just going to ask you
to continue with G Up. It means before
that, you have to go to get Up website github.com, and log in, put your e mail and create a
passport and you're log in. Then, come back to file.ai
and continue with GitHub. I'm just going to authorize
the filed AI right done. At first, the Filt AI, just going to give
you some credit. So I've used my credit
for this e mail, and with those credit, you can create around 50 images. Then you have to log in with another e mail or
e mail account. Now I'm just going to log
in with another e mail, so you just going to
give me more credit so I can run easily
without any problem. So basically, you
have to log into filet AI models file AI flux D. This is also free
to use right now. Put your prompt here. A close off of a single I. Make sure you're signing in. After signing in,
you can run it. You have also
additional access here, and you can also control
the portray the size. This is much easier or
simpler than hugging face. But the cool thing about
hugging face it's free, and probably the file AI in future is just going
to be paid version. As you see, your
request will cost 0.0 25 bucks per megapixel. For $1, you can get 40 images. And as you see, the
result is perfect. If I do this in hugging face, the same thing, I will
get something like this. Again, I can upscale
it and get a 2.6 megabyte image with the
highest quality. All right. Now let's try another prompt, a beautiful blonde girl
with lovely wedding dress. All right. Now let's go
to Cha GPT type prompt. And here I'm just going to type a beautiful blonde girl
with lovely wedding dress. I'm just going to copy this. You can put it on flux, the portrait one, and
also run it here. Make sure the Laura is
selected unless you get this. Error, I'm just going
to generate it again. Make sure the flux realism is
selected, paste, generate. Let's see what we
get. All right. This is what we
got with fall.ai, which is the same model, but this is the development version, and it's a stunning. You can download it. The
cool thing about this. And as you see here, it's
already a high quality image. You don't need to upscale it. But as I said, probably in future, just going to cost you money if you
use it from this side. Most of the time
on Hugging Face, wow, let me get a totally different format
and image of this. I'm just going to try this
again, the same thing, probably, I'm just going
to make it a portrait. We is going to
generate this again, this is Flux Laura model. But this one is just Flux
0.1 development model. You can use both to see which
one is better in your case. If I just put a beautiful
blonde girl with lovely dying dress
in flux Laura model, I will get something like this. But if I put the same
thing on Ca GPT, the Chad GPT based on
the full prompt formula, it's just going to give me this or the portra vision,
which is this one. I can also put this on fool.ai. As you see, they are
beautiful and stunning. The cool thing about fall.ai
advanced setting is you can change the image size easily and don't
change anything else. Just run the image and you
will get the perfect results. For now, most of the time,
I'm using the Fat AI. The images are more
look like the mean. All right. Look at this one. The blond fashion model, the Cora gold 400, i level shot, natural lighting. I put this in Cha jpti prompt. I said prompt, this
one, and I got this. These two beautiful images. I changed the photographer
name to Mario vanco, and I got this kind of style. Course, after I put the Cha
GD prompt into fall.ai. All right. Let's test this
out. I'm just going to copy this Cha GPT, prompt. All right. Let's copy that. Go
to fil.ai model. I'm just going to make
sure it's portray, Control V, run it. Wow. This is so cool,
and it's beautiful. If you don't like it,
you can run it again. And again, I love it, and I'm just going to
download this one. Right. Now you know how to use Falt AI or Hugging Face
Flux Laura D Explorer.
4. Professional Prompt Structures for Objects and Portraits: Now, what is the second
and third prompt formula? The second prompt formula
is the simple one. Create an image of specific object or
character in setting or environment with
additional details or elements in the style
of art style or medium. You have to fill the gap, and here are some examples. Let's break down the formula. What is specific
object or character? This is the main
focus of the image, such as a person,
animal, or object. For example, a young girl
with long curly hair, a majestic unicor a
vintage typewriter. What is setting or environment? This is the location or background where the object
or character will be placed. For example, a sh
enchanted forest, what is additional
details or elements? These are extra
details that a depth, mood, or context to the image. For example, surrounded
by glowing fireflies, wearing a long flowing dress. The last one is art
style on medium. This specifies the
desired artistic style on medium for the image. For example, in the style
of impressionist painting, using vibrant neon color. Here are a few examples of
the formular in action. Create an image of a curious cat in a
sunny kitchen sitting on the counter and looking out the window in the style
of a watercolor painting. And this is the
third and the best prompt formula I'm
going to give you. Create a portrait of
subject description, varying a specific dress style. Example, Floy Maxi
dress, Taylor blazer, vintage cocktail dress, in fill the gap, setting
or background, accessorized with
specific accessories, a statement necklace, elegant heels, a cheek handbag, captured in the style of
photography style or technique. Here's an example of subject descriptions that can be used in portrait photography. A young woman with
curly hair and bright blue eyes wearing
a flowy sundress. Here are two examples
for subject description. The next is specific
dress style, which I put casual
dress example, floral Maxie sundress,
cotton a line sundress. They have the explanation. So you can read them
all out and try them to see which one is
more interested to you. The next is two example for
sittings or background, like Urban Street, beach at
Sunset, lush garden, So. The next is to example
of specific accessories, also to example of photography
style or technique, like low key photography, high key photography, Ling
exposure, photography, and so, and also to example of using the formula for
creating a portrait. Create a portrait of a young
woman with curly hair, wearing a floby maxi dress in a lush garden accessorized
with a statement, necklace, and strappy sandals captured in the style of natural
light photography. You can say a young blond woman with Kelly hair, and
let's see what to get. Run again, a stunning.
Can download it. Let's try the same prompt
on Flux Lora the Explorer. Let's choose the flux realism
and paste the prompt, and let's see what to get here. It takes longer than fold AI. All right, and also this is absolutely gorgeous,
and it's beautiful. I love them both. Let's
see them side by side. I love both of them. They are amazing. Look
at the depth of field. So both website are generating amazing images based on
Flux model. I love them. Perfect. These
images are really, really close to meet
journey, and it's free. Just type photography
by Tommy Ton, and you will get something
like this. A coal miner. If I change the number
of steps like 50, I will get more realistic image. Also the same 28 is also
very realistic image. It doesn't really
make a difference. Number ten, it's
very low quality. Most of the time, put it on 28, which is going to be perfect. This is our prompt. This
is what Chad GPT gave us and what I put on fold AI, and I got something like this.
5. Inserting Yourself into Any Scene Update: Now it's time to train your
face into the new AI model, and you're going to love it. Replicate is a platform
designed for running and fine tuning open source
machine learning models, allowing users to deploy custom models at a scale
with minimum effort. This platform is
very, very low cost. You can train your face
or any model and get 100 images for less
than ten bucks. Trust me, it's worth it. You will get amazing
and beautiful images that you always wanted in your life. Alright,
let's get into it. Let's go to replicate.com
and log in to the website. Search for Luka Taco. Scroll down and Enter. Now tab on Luka Taco profile
name. So we are here. Or just simply go to
replicate.com slash Luka Taco. Scroll down and look
for AI Toolkit. Here is where we are
going to train our model. Click on Train tab now, select the T destination, tap on, create a new model. Here, choose a unique
name like My Dash Love. Then you need to upload at least 12 images and
put it on a zip file. The better your photos are, the better our model
is going to be. So don't just put a camera
and take some selfie. If you don't know how to get professional photography with just your phone,
watch this course. IPhone portrait
photography, master class. There are so many
videos in each video, you will learn how to capture professional photos in less
than three to 4 minutes. Again, make sure these 12 or
20 photos are really good, and the photos
should be PNG files. My photos are JPEG. To fix the problem, I'm just going to go
to jpeg to png.com, drag all the JPEG files here
and download the PNG files. Now, we have to rename it. I'm just going to right
click and rename One Photos. I'm just going to call
it a photo of my love. And my love is capital. And here, I'm just going
to have 12 photos. I'm just going to right
click and zip them. Drag and Drop the zip file here. Images file. And here, HF token stands
for Hugging face. Et's go to Hugging Face website. Click on your image
Tail and setting. Make sure tab on access
token, create new token. I'm just going to put
Mylove Laura flux. I'm just going to give
it some permission. Repositories, interface, web hook collections,
and that's all. And at the bottom, you
will see create token, copy this and don't let anyone see this. I'm
just going to copy this. Come back to replicate
and paste it here. Don't change anything else. Just here at the bottom. Repo ID is very important. To create a po ID, come back to Hugging face, click on your profile picture, tab a new model. It is going to be Sully
art slash Milos flux. I'm just going to copy this
let's go back to replicate and solartJ going to
paste it in Mylove flux, make sure it's public and create a model. The
model is created. Let's go back to replicate
and create training. Here, you have to wait for
around 20 to 25 minutes. Alright, this is a update. If the previous Loko toca
training doesn't work, we are going to use Asteris. This is the new training model
that it works perfectly. So if you go to this link, put it on file projects and
you can have access to it. Just go to replicate AsterisFlxv Laura Trainer slash Train. And it's the same process. You can click on New model. I'm just going to put this,
for example, my model. Input image is the same process. The trigger word,
just put a trigger, put a trigger word that
you don't use so much. So like W girl, something like that, something that is not really in the text. The next is, this is the
hugging face por ID, which is the same, and
also hugging face token, put these two here, and
dress is totally the same. So just create training and
it's going to work perfectly. Now it's done. You'll see
the status is successful. It took 38 minutes and the repo ID is Sol art Mylove. I'm
just going to copy it. And in Hugging phase, I have the Solart Mylove
flux created as well. And if I go to
files and versions, you will see all the
models are copied here. Now again, come back
to replicate.com, Locar Taco, and
I'm just going to click on flux Dev Laura. Here, you can put your prompt and spec ratio is
going to be here, the number of outputs. I'm just going to change
aspec ratio to 16 by nine. I don't change anything. Here, the output should
be on JPEC and here, the hugging fake Laura
I'm just going to paste the solar dash
my love dash flux. I'm just going to say my love, which is a trigger for
my trained images, then close up portray. And run. And I'm going to get this
beautiful portrait of my wife. And, trust me, it's 99% hair. I showed her these
images without even tell her. I
trained this model. She told me, when
did you take them? These are amazing. And let's see the
real four of my wife. These are the real images. And let's see the
result. It's absolutely stunning. Now let's
try this one. My love close up portrait of a pretty girl with
Golden Hour lighting. And I'm just going to
change the ratio to nine by 16 to be portrait. I don't change anything else. I'm just gonna run it. Wow.
This is absolutely stunning. Now, let's go to ChaGPT. I'm just going to
put the prompt here. And I'm just going to
paste the prompt and let's see the chai Bit result
based on our formula. I'm just going to copy
this.'s come back here and I'm just
gonna keep the M love. Or most of the time, you don't even need the my love. Because this has been
trained based on our model phase,
so let's try this. So this is the test without even put the M
love as a trigger. And let's see what's
gonna happen. Wow. This is
absolutely stunning. I'm just going to download it. I'm just gonna copy this. Alright, let's see
the portrait here, and this is the result. If I put it on landscape, I'm just going to get
something like this. It's absolutely stunning. 16 by nine just gonna give
us something like this. So I changed the prompt
to a girl wearing wedding dress in a
beautiful garden with golden hour lighting. I put this prompt in
ajipit and I got this. I put the my love
as a trigger first, and I got this beautiful image. As you see here, this is
the output and result. Another one close up portrait
of a pretty girl, lovely. So my love as a trigger, and this is the
Chang GPT result. And I got this beautiful
image. I love them. I love all of them. Look at
the quality of the image. Guys, the next one
is super cool. You have access to
the prompt here. And here's a prompt that
I got from Cha JPT that my wife is riding a bicycle with golden hour lighting in
the street from the back. So it's amazing. And there's another
one, another one. And we are getting to
really cool photography. Trust me, a beautiful woman
on the train looking outside. I put this in ChaGPT
and I got this. And after I put
this on replicate, I got these beautiful images, and these are really,
really amazing guys. And it's totally hair. I showed her these photos, and she was amazed how beautiful and realistic
and looked like hair. It's exactly hair. And
look at these images. They are absolutely gorgeous. This is another one, my
love dancing in the rain, looking directly at the camera with a joyful, radiant smile. This is another one lady, professional wearing
a tailored suit, sitting at a modern office desk. And just take a
look at this one. My prom in Cha JBT was a beautiful woman on the
train looking outside. And just take a
look at this one. It's absolutely my wife. I put the trigger, my love, high quality, and what
I got from ha JBT, I put it in replicate,
and I got this. Just take a look at this one. It's absolutely amazing, guys. And trust me, you tried. You're gonna be amazed by this. My love, high quality
photo of a woman sitting gracefully on a train chair.
And these are the setting. I put the output quality on
100 and I got better results. And the aspect ratio is nine
by 16 black and white photo, which was this one, and just
take a look at this one. You have access to
these prompts, guys. My love dancing in the rain, looking at a camera,
happy, joyful. And this is the conference one. Chasmatic speaker is captured
me speech. I got this. This one, and also this one, this is absolutely amazing. Chasmatic singer is
captured met performance. He long hair flowing grazly
and a beautiful smile. It's amazing. I love it. Even my wife loves it. One of the cool thing about flux is you can put any
words or text. I said around her
neck with a badge that reads Suli Art and just take a look
at this one, Suli Art. It's amazing. Even me
Jenny can't do this. And this is the fun one. A powerful and
chasmatic Wonder Woman is captured mid flight. And she's my wife. And this is the prompt. You can use and this is the normal prom. She's a chasmatic speaker
is captured me speech, pointing to the left. Surprisingly, you can use this for YouTube or Instagram
or TikTok Tinails. Point yourself
somewhere, and trust me, you go change your
life. I love them. Another one I tried
surprise close up face, pretty girl with long
hair floating to the and I said something
else like close up face, pretty girl with long
hair, floating there, showing a sign with words, I am AI, and it's done that. I can't imagine how
you guys can use this for anything on your website or page
or YouTube channel. And this is another one. Im AI. I love it. So make sure you use this text and prompts to get everything
you're looking for. And my love driving
a new black car. And how amazing
is that? This one
6. Creating Cinematic AI Scenes: Age pit to write ten
storytelling scene. Each scene is about
a beautiful girl in red dress in
different location. I got ten different
scenarios. I use them here. I got so many scenarios here in different location,
different places. Just put the prom here, and get the story that you
want based on your picture. Take a look. Then I ask the Cage P
Give me some prompts that the face is always
looking at a camera, and I got something like this. These are the scenarios. And my friend, the sky is limited. Take a
look at this one. As the sun sets over
the city escape, casting an orange glow, and this is the scenario,
and this is my love. Take a look at this one.
It's absolutely stunning. Look at this one. These
are different scenarios, different location,
but the dress is red. How cool and cinematic is that. Now I ask a GPT to give me ten different fashion
style outfit and closing, and this is what I got. Take a look at this one. Just put the prompt based on what you want to wear, and
you're going to wear it. Take a look at this one.
It's absolutely stunning. Wow. Take a look at this one. It's gorgeous. Stylish,
my love in red. Gorgeous. Here's the problem. When I
say my love at the beginning, you just to think I need
the word my love somewhere, and you're just going to add it. That's why most of the time, I don't put my
love as a trigger, it's just going to work because it has been trained just
with my wife photos. You don't need to put the
my love at the beginning. So the photos are amazing. I just ask aji to put my wife or a girl in different
location in party in Dubai, top of the mountain,
It's like a couple. It's the breathtaking,
high resolution image of a bride and groom in a
romantic food body portrait, and you will get
something like this. It's absolutely stunning.
Just take a look at this one. You have access to the prompts. With curly hair, so cool, a real photo close up of a beautiful Instagram
influencer taking a selfie. And the selfie part,
it works the best. Another selfie, I put this
prompt to chat JT I got this, and then just going
to gave me this one, taking a selfie in the airplane. Bungee jumping, it's like
Self in a K two Himala. Again, I got this prom
from a GPT, also this one, a French girl model, wearing a soft summer
clothes by JogR Money. I'm just going to
give you this one and replicate, which is my wife. If you put the same
prop on Flux Laura, the Explorer, you're just
going to give you this one. This is you. This
is another model. You have two choices. Train your model or use
another model for your outfit. For your assignment,
try to recreate all of these photos
just with your model. And just send it back to
me for more feedback. All right, go for it
and create your model.
7. Designing AI Social Media Thumbnails: Creating time nails for social media has never
been easier than this. All right. Just
copy this prompt. It's here. I'm going to
copy this go to GPT. Well, let's create a new one. So it's going to work.
I don't need this one, copy this and paste it. So basically, just going to ask me to type the prompt, right? I'm just going to say prompt, column, and that's it. What is the topic?
What is the title? The topic is going to be
consistent character. Shift inter, going to the
next line for the topic. My topic which is flux AI. I'm just going to type
this and list the result. Is the full prompt.
Let's understand this. You are my assistant here. When I typed input, prompt, ask me, what is the
topic? What is the title? When I provide the
topic, for example, World of AI, and
title, for example, flux tutorial, give me the final text prompt for creating the time
nail like this. Just based on the topic,
change the expression. A portrait of a person with
this kind of expression, which is going to be
changed based on the topic, and this is going to be the expression that the
CAG PT is giving me. And this is going to
be related to topic, like a technology, futuristic
background, and et cetera. And at the end,
display the title, which is going to
be flux tutorial, large and bold. All
right. Let's try this. Now I'm just going to copy this. I've tested this before
and it works like a charm. I'm just going to paste
it here. And can run it. All right. What do
you think, guys? Isn't it amazing with just
your face and the title, you can have this like
less than 30 seconds. So you don't need to
spend a lot of time or money for creating time nails for your social media account. If you don't like it, change some wording, change some text, and run it again. Going
to download this one. Run again. L et's try again. Awesome. It doesn't
mention the flux AI. So let's try it again. I'm just going to download it is cool. Maybe the person needs an AR sunglasses or something
with futuristic sunglass. Let's see what's happened. Wow. This is super cool, but it didn't mention
the Fux AI display. Let's run it again. I wish I could have downloaded. So make sure you download it always, so you don't miss it. Let's try this, guys. Put just make sure to display the title flux AI
permanently in large bolt text. Let's try this. I just added the make sure to
display. That's all. All right. So it works. Basically, this is how
I added the Flux AIO. Let me change this
to Flux tutorial. Let's try this. I doesn't work. Sometimes works
sometimes doesn't. Flux Tutorial. Instead of title, the
word printed large text. That's it. Let's try
this. I love it. I love the image. That's cool. T. So, try it multiple times
until you get the result, and it's just going
to take 1 minute. Imagine if you wanted to
take these kind of photos and create a time nail or paying someone
to do it for you. So how long that's
going to take? Sometimes hours, sometimes days. So how cool is that? You can create
yourself easily, guys. So just put make sure to display the words printed in large
bold text and the image. So I'm just going to copy this, and I'm going to
fix this as well. So I guys know how to do this. Let's copy this again. It's going to create a new one. Paste it here, paste.
Let's try this. Prompt. The topic maybe AI is the future shift inter
to go to the next line. I just love flux. Let's
see what's happened. Inter. It says, make sure
to display the words flux, printed in large word or a. Let me see. Let's paste
it here. And run it. All right. This is
super cool, guys. I love it, but it doesn't
mention the love flocks. So I'm just going to re run it. So I just tried two
times and it works. So basically, this
is how it works. Try to change some wordings
if it doesn't work, and trust me, it's going
to work like this. And there is no ultimate
formula for this. You have to play around with it. You have to learn to
educate yourself and change some wordings to get
exactly something like this. I'm just going to download
it. I don't want to lose it. Maybe I say, and also I add it with
futuristic sunglasses. Let's see what's
going to happen. Absolutely lovely.
And we got it. I want to clap myself, and I love it. Don't you guys? You guys can create any kind of time nail
with this trick, and you're going to thank me
for this forever. All right. For your assignment, try to
use the Cap formula pasted in Chagp put your topic title
copied here in replicate. And get the result easily, and all the process, is just going to take
less than 1 minute and how cool is that. Alright, Happy creating,
and don't forget to upload your images
for my feedback.
8. Assignment: For your assignment, create your own AI generated
scene and time nail. By the end of this course, you will create a
unique project that showcases your ability to use flux AI to insert yourself into a scene and design an eye catch and social
media time nail. This project will demonstrate
the skills you have acquired and allow you to
express your creativity. These are the project steps. Select a theme, choose a theme
or concept for your scene, for example, adventure, fantasy, travel, or a personal hobby. Think about the message or
mood you want to convey. Number two, prepare your photo. Take or select a high
quality photos of yourself that you want to integrate into
your chosen scene. Ensure the lighting
and angles are comparable with your scene
for a seamless integration. Number three,
generate your scene. Use flux AI in
replicate to generate an AI generated scene that
agns with your theme. Experiment with
different prompts to achieve the desired
background or setting. Insert yourself into the scene. Combine your photo with
a generated scene, ensure your character maintains consistency and looks natural
within the environment. If it doesn't, re run the
project again, and replicate. Finally, design your
social media time. Using the integrated Image, create a professional looking
social media time mail. Incorporate bold text that reflects your theme and includes any relevant information like your project title
or a catchy tagline. Make sure to use my prompt
structure and formula. And make sure to submit your project as a
single mage file. Happy creating
Soli Art, Content Creator | Digital Artist
