Leveraging AI

181 | How to Ideate, Generate, and Animate Scroll Stopping Images and Videos with Arminas Valunas

• Isar Meitis, Arminas Valunas • Season 1 • Episode 181

Share episode

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

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!

Isar Meitis:

Hello and welcome to another live episode of the Leveraging AI Podcast, the podcast that shares practical, ethical ways to improve efficiency, grow your business, and advance your career. This Isar Metis, your host, and we have a really exciting show for you today. As you know, creating visuals that gets people's attention has been a key component of everything that we do. Whether you're in marketing or you just like to share content online or build networks, being able to capture people's attention by generating the right images of the right videos has been something that. Companies has been born and grown on. And if you know how to do this right, you can grow your business. Whether you are a part of a big machine like running your role in a marketing department or a sales department or something, whether you're a solopreneur or a consultant, a content creator, all of the above. You need to know how to create visuals that attract people's attention and connect with the people that you're trying to connect to. And it needs to be aligned with your 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 do it right now. Used to be a lot of work, especially when you go to the video side of things. You needed to actually have a good story and a good idea, and you need to be able to create the right process with videographers and camera people and audio and visuals and lighting and actors in a studio and like all these things to actually get these things done. And the good news is now you don't have to, you can create incredible visuals without having a camera and without knowing anything about design. Now, obviously if you know about design, you can do a lot more in a better, we're gonna talk about this in a minute, but you don't have to, and you can actually use AI tools to do this. Now, another good piece of news is now there's a few tools that aggregate a lot of these capabilities into one tool where you can do Most of the steps of the process in one place without leaving the tool. And this tool brings into it multiple other tools and AI resources that otherwise you would need to jump back and forth, in order to create the output. So today we are going to learn how to create amazing visuals that will be thumb stoppers on social or will grab people's attention if it's an ad somewhere or on your website and how to do this for both images and video. And we are very lucky because we have arming, Unas with us, and Armen has been doing this for a very long time. He's been in design as well as running a company that does branding and design for other businesses for many, many years. So he both understands the visual 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 been posting these incredible things on LinkedIn. That's how I found him. And he's teaching courses on how to do that. So he really brings to the table everything you want. As a guest of this podcast, he has the professional background, he has the business background. He's been running his own business for the past six years, and he knows AI very, very well, and he knows how to teach it because he's been teaching courses. So if you wanna learn how to create incredible visuals with ai, don't go anywhere in the next 45 minutes to an hour. Or if you're driving, stay put. this is gonna be absolutely fantastic. I'm very, very excited to have you, Armin. Welcome to leveraging ai.

Arminas Valunas:

thanks, Isar. thank you so much for having me. And, yeah, I think that will be a great, workshop and I have prepared a lot of for you guys. I want to mention that, of course, the experience in advertising industry is so important and I have been working with the, the biggest brands like IKEA and, sweat Bank and others. But at the same time, I want to encourage you, like Isar mentioned, like these tools, AI empowers 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 right into this, right Isar?

Isar Meitis:

Awesome. Yeah. Before we jump in, just for those of you who are joining us live, either on LinkedIn or on zoom. Thank you for joining us. I know you can do other things on Thursdays, on noontime Eastern. but I know a lot of you have been joining us every single week, so I appreciate every single one of you. I also really, really want to, thank you for, participating. So if you have questions, then ask them in the chat again, whether you're on LinkedIn, you can just say it in the chat. If you are on Zoom, you can say it in the chat as well. For now, just go ahead and introduce yourselves. this is one of the reasons you joined these lives, so you can network and get to know other people. So tell people where you are, where you're from, what you're doing, what you're looking to get out of this. But like I said, if you have any questions, please ask them. So that's if you're here with us live. If you're not here with us live, the question is why we do this every single Thursday with amazing people like Armen that are gonna share. Very practical use cases with ai. And then you can ask them questions if you are around. And if you're not, you can still listen and benefit from it, but you can participate and you can engage. and you don't get to experience that when you're just listening, but there's a lot of chat happening in the chat as well, so you can join that conversation if you join us live. I'll say one last thing before, we dive into today's topic. Today's show is brought to you by the AI Business Transformation Course. It's a course I've been teaching personally for the last two years, at least once a month. So we've taught hundreds or maybe thousands of business professionals on how to implement AI in your business. The course is four sessions of two hours over four weeks, and it takes you from whatever your level 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-on experimentation across multiple aspects of the business. And we end with business strategy, an actual blueprint on how to implement AI successfully in your business. If you haven't done anything like this, anything structured on how to implement AI successfully, you owe this to yourself. You owe this to your business and you owe this to your career. And so if for being a listener of this podcast, you can come and join us with a promo code. Then the promo code is leveraging AI 100 or uppercase. There's gonna be a link in the show notes, and we're gonna share a link in the chat right now for those of you who are with us live, and you can come and join us for the session. The next session starts on May 12th. So if we do these courses, like I said, every month, but most of them are private courses. We teach them to companies and organizations who, Book us to do just for them. And we open a public course once a quarter. The previous one was January and February and now we're opening one in May. So if you need that, and if you haven't done it, you need that, come and join us on May 12th. That's it. Now to our session with Arm and Armin, the stage is yours. show us your magic.

Arminas Valunas:

Oh yeah. Thank you Isar. Thanks so much. So I think, I will start from sharing the screen and, yeah, we will go through, let's say, let's check the last version of video that I've done, and we will try to recreate this as, as fast as we can.

Isar Meitis:

That would be fantastic. For those of you who are not watching, by the way, if you're driving your car and so on, that's perfectly fine. We will explain everything that's on the screen, but if you can, there is a YouTube version of this. If you're watching this after the fact and in your show notes, you can just open it and click and go and watch the YouTube video. And then you can see,the visuals as well.

Arminas Valunas:

Okay, so let's this for now.

Isar Meitis:

Wax London, ethically crafted pieces designed not just for seasons, but for life stories. The foundation of lasting style lies in superior fiber Wax, London Clovis with character. So for those of you who can't watch, this was incredible and I still can't believe this is AI generated. So it's different images and not images, like videos of a fashion show and then actual people in different scenarios like. Driving a boat and walking in a beautiful old city in Europe, wearing nice fashion clothes and, bracelets and so on. And I'm blown away that this is all ai. So I'm personally really excited to see how this was done.

Arminas Valunas:

yeah. And it was so much fun, creating this. So I think, I will go to, to the whole, process and we will see how to do this. So at first, really big thanks for, 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 page and I just, downloaded these photos like you see, and I trained Laura. Then I trained the second Laura for character, for my appearance, but I didn't use this in the video. And I generated all these first like static images and from them, like videos and then created the whole, show reel. So let's dive deep, into the whole production process. So I chose the Freepik and it actually gave me like really high quality and at the same time I think it's, really like user friendly and really easy to produce these images. And later on, all the videos. So here we are. In the homepage of Freepik. And from here, if we wanna create the images we are going to create. from here, we want to train the object, the garment. So from here we are choosing object. And you just have to press plus button. But, actually I already trained. So let's go through the process. So here we say the name, let's see wax, then, shirt, the type. And here we, upload all the images. I will upload. These images.

Isar Meitis:

So while you're doing this, for those of you who are not watching, Freepik is one of those aggregators of tools that brings you a lot of different other tools into them and make it very user friendly to use. And what we're doing right now, when Armand says Laura, Laura is just a way to train a visual model on a specific person or style or object, you can train it or different things. And when you train it, it can then knows how to regenerate new images of the thing. In this particular case, a high-end fashion shirt. so what Armen did is he basically just opened and said, okay, let's create a new training, uploaded multiple images that he, when I say multiple, it's seven, like it's not 50. And he has seven images that he downloaded from the website and he is basically gonna create a new model that knows how to create this shirt in any scenario, on any person with any background because it learns how to create the shirt.

Arminas Valunas:

This is exactly what I have done. And actually, to be honest, you need to upload, and, my, kind of recommendation would be all the time, follow all these tips and, it says 12 to 25 images. So for this, if you don't have 12 at least, because if you have o only seven, it'll not allow you to train the lara. But then what I did, I, basically changed the composition of the images and flipped the images horizontally. And I had 12 images and I was able to train this Laura. And yeah, actually it's so on point. I wanna interrupt myself a bit and, maybe. To explain how I understand Lauras there are so many technical, terms about, Lauras, but in general, it's, low rank adaptation and, let's say, this is our like flux. And by the way, we are training on flux. So let's say this is, all the flux model and all the whole data is in here. So we are training, like just one little piece, like this is, our like train Laura. And it, shows the model like, if it's only, object or like character, it shows how we wanna, 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 be waiting, pretty, long time. Actually it's quite fast, but maybe still takes 15, 20 minutes. So we don't want to do this. So I created Laura already.

Isar Meitis:

we'll do the cooking show thing, right? We're pulling out of the oven And for those of you who don't know what flux is, so there are several different leading visual image generating models in the world today. probably the best open source one is flux. So it's just a name of an open source, model that works very well. because it's open source, there's a very easy, process on 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:

I think most adaptable and if I can say this, like trainable, models out there.'cause it's open source and you can do whatever you want with flux and it gives you such a high quality. So definitely I recommend, if it's, for training objects, characters or styles, just, use, flux. You can do this, by the way, on like older ones, like SDXL or SD 1.5, but Flux is, the best at this point. we have already our train object in this case, this V London shirt. And by, by the way, there are like many, pre-trained objects in, Freepik that you can just, choose and maybe test if you don't want to, let's say train your own law.'cause it costs a lot of credits. So at first it's a good idea to, play around with a pre-trained object. So when you have this trained object, in this case our garment, we just select this one and at Lido X, it's my, train Laura name, and it appeared in this field, in this box. And here, if it's, active, it will, generate in this train Laura product. here, I can, start typing and creating prompt, but actually I already have a lot of prompts prepared for us. So I will not be doing, creating from scratch. let's dive deeper a bit into my thinking. So I have a product and I was, exploring, two cases, like consistent character and, different characters. And, yeah. Let's talk a bit, before I start January, let's talk about, the process and the thinking. I divide, or at least I am working in three stages. So the first stage is pre-production, where like creative ideas are born, where I'm creating like mood work where I find, the tone of, not tone of voice in this case, but, color palette and, the whole widen mood. And then I am usually drawing some 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 the best results. And also, of course, nowadays, helps, like AI tools and LLMs in 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 case chat g pt. But, also I'm exploring other tools, as well. So I think it really, depends on you and your style, but, nowadays it's just the leveraging your creative capabilities and you don't have to. let, the AI kind of drive your creative ideas and your creativity, but you should empower and leverage, your creativity with ai. So the second stage production itself, where I am, generating images, videos, making some selection from all the material that I have editing, combining music, voiceover and everything falls in into place. And last touches also, this is really important. I think this is where magic happens, is, post-production. And it's really important, because retouching and color grading and, it's just, lifts you into that. This like pro quality that you are reaching.

Isar Meitis:

Yeah, so quick summary, three steps. one is, pre-production where you get the ideas basically and more zoom in and what exactly you're trying to create. And as Armina said, if you're very creative, use your own creative ideas. If you're not, you can use large language models to help you through the creative process. And think of an idea that will work for your target audience that is aligned with what you're trying to do. Literally just have a conversation with it. Explain what you're trying to do and it can help you. creating mood boards, rough ideas on how the video, so the video that we've seen had, like somebody, it started with somebody walking in a fashion show and then people walking the street and then somebody in a boat, and then a closeup. there's all these components that in your head you need to know that you need in order to actually show them afterwards in the results. So this is more in the creative process, and then you create all these components and then you put them together. So now let's go to the steps of actually how to do it.

Arminas Valunas:

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 be messy and, it's even like before ai all the time, we are using this kind of, process. let's say we already have trained object, garment at in this case, and let's say I'm just, create like some simple, prompt and then I will compare how 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 four variations, but the first one is maybe the most accurate. that's why I'm more into other tools 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's mystic, it igram, imagine three, but it works only with the flux. because we train Laura on flux, we can't train, on like other models. yeah, so

Isar Meitis:

again, for those of you who are not watching in Freepik and similar tools as well, like Korea, you can choose many of the image generation models. But now, because we trained flux, we gotta use flex. But if you're just generating images, not on a trained model, you can use all of them.

Arminas Valunas:

Exactly. I'm using a bit more advanced prompts and, this is also deep topic it is an art of itself and when I'm using more advanced. Prompts it gives, well, for me at least, it is much better quality and much more interesting.

Isar Meitis:

let's read the section of this prompt just to tell people the understanding. So they understand what you mean by a more advanced prompt. So let's just read some of it.

Arminas Valunas:

Yeah. So, the prompt, mid-length fashion, runway, short subject focus, male model, walking, wearing white shirt, subject details, fit, male model, white swept back brown hair, we point, more accurate, details to everything, to characteristics to character, what he's wearing. and when you prompting with ELOs, in this case, you shouldn't be confusing the model, let's say if I, would try it. Like red t-shirt or something totally different. It would be, confused and, won't give you like good results, but this is also, maybe I wanna show you, a bit, where you can start, like, how can you, learn how to prompt? So I think the best start is, just, let's say download this one and just, to upload, the image into the chat, GPT and just ask, describe the photo. And I'm in the camp where like people are saying like, but you are copying, you are doing this or that, and this is bad. But actually it's not like you are just trying to figure this out. What model, because vision model itself, it gives you the answer how it interprets this photo, and you just, borrow these, key phrases, but you are making your own prompt. it's really good base. yeah, again, to

Isar Meitis:

explain, for those of you who are listening, you can take an image that you wanna mimic the style of, or the concept, or in this case it's a model on a runway how. To start prompting better, you can just drop an image that is your inspiration and say, I wanna write a prompt that will generate a similar image in an image generation model. I want you to write a very detailed prompt that will mimic everything in this image, including the style, what he's wearing, the background, and so on, the lighting. And it will give you a very long, detailed image that then you can use as your baseline to make changes and massage to whatever you need. One more thing with regards to prompting, pre-trained models with Laura is I'll say more extreme than what you said. It's not just don't confuse it, but tell it what it is. if you would say a buttoned up, stylish white shirt, describe the thing that you trained it on, it makes it even better and it will give you more consistent results. So don't just trust the training of it to be perfect, but also describe it in your prompt and you will get more consistent results, than if you don't. So let's continue with the process. So now you have the images of the guy in the fashion show. I assume you do the same exact thing for all the other characters, right? The guy in the boat, the guy in the street. I'm actually very curious about the closeup one because one of them was very different, right? Most of them were like full body, relatively, kinda like style was similar. One of them, you literally specifically asked for closeups of the fabric and closeups of the person,

Arminas Valunas:

tip centric. And I will, reveal all the secrets. Okay. Awesome. Maybe let's, dive deeper and, maybe let's go with the like generating video and then I will go to this micro shot. let's say we, really love this shot. then, what usually I'm doing, actually you can go like straight to the great video, but, actually I'm, upscaling and really good at, Freepik has the magnifi upscale, which is, the best upscale, I would say. Yeah. So I am editing I'm pressing like edit button, and then I am upscaling and it's basically the same parameters that in native Magnifi on its own, but, yeah, everything is the same. I have a few presets when I don't want to change the character appearance, I tend to, lower all the creativity stuff. Parameters or, like portrait soft is really good. So let's say, I will upscale and it'll take some time, but, not that much. during this time while we waiting, I can, reveal my secret. So actually, it's not about generating, especially when we are working with the real products, right? And garments and clothing, it's not all the time just, generate for the sake of generate, at least in my thinking. So I actually just took this photo. it's the same photo, but I took this and, actually I generated using. runway. runway is, really cool especially like junk four. And they released this latest model, I think two weeks ago. So it's really new runway

Isar Meitis:

version four. so that's a good trick again for people. for those of you again, who are listening, what he's done to get the really extreme closeups is actually use. Actual closeup photos from the website and then animated them with tools. In this particular case, runway version four is really good with consistency. which is very important when you're trying to do stuff like that and actually have the shirt look like the shirt. so now you have the standalone components, you upscale them And then you animate straight from there.

Arminas Valunas:

Yeah, actually from upscale photo, But, when we upscaled, we can't, generate video directly from here. So we have to go back to migrations 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 you see the section. the first stage images, and second section would be videos. And it automatically gave me a prom, but, in this case, actually it's quite good. a male model confidently walks down a minimalist runway. So actually in this case, I will use this, but, I can, give away another secret. what I'm doing, I created my own Armada, video prompter, and usually I'm just, Using this, it just 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 really detailed, prompt, and even two prompts actually where it describes like what is, the composition, the, wide angle shot. how the model looks like and all these things helps to generate like much more accurate, videos and actually it made my videos much better. I just wanna

Isar Meitis:

pause you again to explain. For those of you who are not great prompters, and especially when you're moving, even if you are a great prompter on an LLM and now you need to prompt a video model, it's a little different. And the best way to do this is to have some kind of a framework. And if you don't have one, then this particular case Armen created a custom GPT that does it, and all he does is He uploads the image that he is already created into the custom GPT and tells it a general idea of what it is, and it creates a very detailed prompt. Now, if you don't know what to put in a video prompt, you can ask. Cha pt say, I wanna build a video prompt What component needs to be in it? And it's gonna tell you it needs the composition and the lighting and the motion of the camera, and the motion of the character and the feeling you want to get and stuff like that. and then more details and different characteristics of the person and what's happening in the shop. And so it will tell you all the different components and then you can ask it to build like a prompt generator for you based on that. If you fit it an image, and then it will do the work for you. So it sounds really fancy, but you can start very quickly and get probably not the same level of results that arming got because he's been doing this for x number of years. So he knows what he's looking for, but he will get you from knowing nothing about it to 75% there, which is way ahead of most of the people in the population.

Arminas Valunas:

Yeah, definitely. And I wanna share some, thinking behind this. So actually you can do this perfect. custom gpt on your own. Just, let's say, this is a great example. I created also, custom GPT for generating, describing pictures. So you just, go to the page of the. model itself. let's say this is frames by runway, this is like prompting guide. So the best thing is not to try to guess how to create, custom GPT, these, developers, the, giving you all the information how to prompt. just copy this, all the info with the example and, feed to the knowledge base. And you have perfect, Custom gt. Great idea. Yeah. yeah, let's, continue. I decided, my own prompt with my custom GPT is better, so I copy paste here. And, let's check a bit, about the video models itself. so now it says, CL 1.6 Raw, but you can press here and, you can choose all different models. so I think, in my experience it's still Ling 1.6 is the model that I am going, most often with, 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 to video.'cause actually from image to video, it is, just in my experience, like ling. Delivers better, better results.

Isar Meitis:

Yeah. And again, for all of you, the, one of the beauties of tools like Freepik is that it gives you access to all of these tools, right? So you can pick and choose whether you want to use, this image generator or this video generator. And the cool thing is you can try it with three different ones. And yes, you're gonna pay tokens for all of them, so it's gonna cost you a little bit of money. But if you're doing this for a business purpose and not just for fun, then it's still gonna be significantly less money than you spend ever on creating a professional video for anything. yes, you're gonna run this on VO and Cling and Sora and Runway and all four videos are gonna cost you.$10. it's still nothing compared to what it would've cost you to even just get the actor for 30 seconds would've cost you more money than that. And so it's worth sometimes because what you are trying to do might be different than what ARM is trying to do. And the only way to know whether the style and the thing you're looking for works better. The other thing is you may listen to this episode two weeks after we recording it, which may have something completely different on one of these models. So it's always worth trying to do this and just trying different models and see how it comes out. And once you've done a few and you consistently like, like Armen is saying, he already knows that for the stuff that he's doing, cling works best. And I'm sure that a month and a half from now when a new model's gonna be out, he's gonna try the other model as well and see what is actually working better. But you gotta experiment yourself in your style and the thing you're trying to do in order to see what's gonna work for you.

Arminas Valunas:

Yeah, so great. wow. definitely. I agree 100%. And, it's changing daily. Like maybe tomorrow it'll be different in case. Yeah. let's choose then cl 1.6 and sometimes I mess this part. So it's really important to choose like different, aspect radio. So you have ability to choose from these three, in this case, in, when using three pick, in others, like you can choose, other aspect radios too, but here, like three aspect radios, so we are choosing social story'cause it is vertical. Yeah. And then click generate. So while it is generating, of course I will be showing other things, but, basically it's the same process for all the shots that we have, right? Yeah. This is the first one. We will not be able to generate all these shots, during this workshop, but you get the idea. And then I am combining, I'm compositing everything. in After Effects. I'm using After Effects, I was diving deep into, character, LL Laura training for characters, and I was testing with my appearance. So actually not that many people know that you can combine Laura's, in three pick as well. while generating, let's go back and, it's the same process. you can generate, train Lauras on style, on characters and objects. You select the gender. you upload the images. and then, actually I didn't mention, but, if you wanna even like better quality, you should, choose ultra and then again, create your character and you have your character here. it appears in this panel, and you can just press the arm and we have, okay, it appears at the end of the prompt, So we have two, character and object as well. So let's try generate with a tool r. Yeah. So

Isar Meitis:

again, for those of you who are listening, what Armen is showing right now is actually very powerful because you can train the model on a character. This could be basically your model. And this could be yourself, it could be somebody else. you need obviously permission of that, somebody, but it could be somebody that's made up, meaning you can create a model with an image generator that doesn't exist, and then train on that and create more and more images of that person. And the interesting thing is that then you can dress up that model with whatever object in this particular case, a shirt that you trained in a different training set. So now you can combine the person and the object into a single image and then create videos. from that. And the same thing for style. Like you can train on style and that could be the style of your company or just the theme you want for that particular, shot or video, and you can do that as well. And the output, we now see images of arm with a lot of hair. No, no driving, driving a boat, but wearing the shirt that we were creating previously, which is really cool.

Arminas Valunas:

Yeah. I think I, have to read the prompt, but I created the, like previously and you see it's cool, yeah,

Isar Meitis:

great

Arminas Valunas:

shots and of course it's, we are giving away a bit quality wise, when combining two ours. And, it's not, not that accurate maybe, but here it's good. It's not bad. It's not bad. if, you are not like, getting the best, result, you can lower the strength. Like you can, choose the parameters of the strengths so I can lower the strength of my, character and then, try again. But at the same time, I will lose a bit of likeliness. But, like we see, it's pretty great results actually, and a combined two lowers. And, from here I can generate more

Isar Meitis:

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 where we are till now, and then I want you to say, what are the following steps. So step number one is getting an idea. You can do this with AI and brainstorm back and forth in defining what you're doing with it. Step number two is getting your resources. So in this particular case it was images of you, so the model or images of a general model and images of the actual product. In this particular case, it was a shirt and we had multiple views, including closeups of the product. And then we trained a LoRa, which basically means training an AI model. In this particular case, the model was flux. And you do this, it sounds really fancy, but you do this literally by following the process on a tool like Freepik. You upload a bunch of images and you train the model, and now you can use that train model to generate images of that object or that person, or like we saw the combination of them again and again. So this way you create the images, which will become the different shots in your video. Then you upscale each and every one of them. So within, still within the same tool, you upscale the images to get a higher resolution. By the way, that's true in all these tools. Every single image generation tool you're going to use, the initial output is a relatively low quality. And if you want to use it for anything professional, you probably wanna upscale that. If you need just for social media, you probably could do it what it is. But if you need anything more than that, you wanna upscale it. Once it's upscaled, there's literally a button. Once you're looking at the image to create a video, then you can prompt it again to define what the video. And as Armen mentioned, you can use a custom GPT that you can build on your own very easily to help you write these prompts, to get better at prompting the video output of the tool. And in the end, you just edit them all together in an editing tool. That could be a professional tool or just a basic tool. You can go as basic as Canva or as advanced as. After effects and Premier and tools like that and anything in between. But it will allow you to put all these short videos together, cut them and do the transitions as you need, add text on top of them, and so on. Anything else that you add in addition to get to the final product?

Arminas Valunas:

Yeah, maybe, first of all, you so good at, summarizing and putting all the dots in, into places, connecting all the dots, so I think, I don't know if you, if you heard the sound of this video while I show Oh yeah,

Isar Meitis:

there was a nice music in the background

Arminas Valunas:

and voiceover,

Isar Meitis:

Did pieces designed not just for season.

Arminas Valunas:

so yeah, the last step, I think of course, like music and you can generate music, if you want to. AI generated music, the best tools are, soon on and Audio. And, both of them, by

Isar Meitis:

the way, are free. So you can generate any music you want as many times as you want for completely free, which is mind blowing. So again, the tools are, SUNO and UIO are two very solid competitors and they keep on improving all the time. But you can create any style with voice, with singing, without singing, and until you land on the one you really like.

Arminas Valunas:

Yeah. and, the last component, in this case it was, generating voiceover. So I just, created some, copyright, some text generated wax, London ethically

Isar Meitis:

crafted pieces.

Arminas Valunas:

This is not the best, but, you get the point. you can go to text to speech 11 labs. It's, the best at generating voices at this moment. And you can choose from like library desk that has, I don't know, like thousands and thousands, voices. And also what is really cool about this, you can, train your own voice and use it, even, I dunno, for many cases.

Isar Meitis:

so one more thing about 11 labs and the voices, yes, it comes with all these voices, which are, again, endless, but even within each voice, you can control how fast it speaks and how soft it speaks, and how much emotion it's gonna have, and how much consistency it's gonna have. So once you find a voice, you can still control that voice for that particular sentence. And then you can run it again and say, okay, Next second sentence faster or whatever you want. So you have a lot of control on, even within a specific voice, how it's gonna sound, so you can make it even more realistic between your different scenes.

Arminas Valunas:

Yeah. and this, how it's called character voice acting. So 11 labs released, like few weeks ago. I think the voice acting, you can upload your own recorded video with your own intonations and, drive the video, apply let's say the voice of this, Johnny Boy, and get your own style. Style and

Isar Meitis:

intonation and, yeah.

Arminas Valunas:

Yeah. Yeah. Yeah. So it's, it's definitely so powerful and, I think it's also the whole another topic, to dive deep into 11 labs. So I think we don't have, so much time, but, yeah, I think, this is, the whole process and let's check a bit, behind the scenes. So I am using. like I mentioned, the after effects and these are all the different, generated voiceovers. This is soundtrack and, it's not that kind of complicated, I just, edited the video maybe. sometimes slow down Ah, one more thing. let's say, post-production. didn't mention this, but, all the time I'm using top as video ai. So now I will turn this on. it's the best, video op scaler. it's just like next level, in terms of quality.'cause usually you also are getting not the best quality in terms of, resolution. of course, some, video models like, let's say the last, gen four, it, gives you ability to upscale to 4K. I already upscaled this one. So you can also upscale natively in the runway if you are using one, but if you are using other models, welcoming, so it gives you full hd. But, usually I'm upscaling to 4K at least.

Isar Meitis:

okay, so I'll put the final step together that you mentioned, creating music. You can do with uio or with Suno you can create the voiceover with 11 labs, which is definitely 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 for upscaling, Magee is probably the best image upscale are out there today. And, Topaz for video. Both of them are really good. Both of them are really expensive. So there are other options that are not as expensive, that are good enough probably for most, use cases. There's even some open source tools that are completely free that you can use, but definitely if you want the best, then topaz for video and Magnifi. Four images are the best ways to do up scalers. And if you're doing this professionally, Armin does, then it makes perfect sense. Armin, this was very powerful. Like literally anybody who wants to create these kind of videos, or images or a combination of them, this was a great session for them to learn. If people want to learn more from you, follow you, see your work, work with you, what are the best ways to do that?

Arminas Valunas:

So follow me on LinkedIn. I'm most active there at this moment, and I'm thinking of, launching a wait list and just, to get, know the kind of position of people, whether they want, learn and, to, collaborate together. and, then we will decide if I will be doing some kind of, workshops or online courses.

Isar Meitis:

Awesome. Cool. one last thing that I wanna say. we touched a little bit about Freepik and so on there, there are multiple ways to do what we did because in, at the end of the day, there's multiple tools behind them. The easiest way to get started because it puts everything in one simple user interface with clear things to click and so on, is either Freepik or choa. Both of them do similar things. I must admit I'm not a pro on any of them. I played with both of them just enough to be dangerous. but both of them do the same thing. They bring in multiple visual. Tools into one tool, and you can pick and choose what you wanna do. And in most cases, they still give you the flexibility of the parameters in each of the native tools. So whether you're using an image generator and the parameters in it, or whether you're using, LoRa and training capabilities, or whether you're generating videos and you have controls, that comes with that. So if you want to get started and you don't want to get a license to six or seven or eight different tools, the easiest ways to get started is to get a license and buy x number of credits in one of these tools, either Korea or Freepik. And you may have a better, ideal on which one will probably work better. once you have that play around and if you do say, okay, yes, this is too expensive for me, I just 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 simple user interface that brings together a lot of other tools that you would otherwise have to get individually.

Arminas Valunas:

definitely. I think, you can, explore, maybe separately, let's say, image generators, like Mid Journey and others. and then to combine also, buy subscription like natively, CL or Minimax or, runway, but it'll be much more expensive. So all in one platforms, I would go with a Freepik or Korea at this moment. Yeah.

Isar Meitis:

Yep. Fantastic. I just wanna say thank you for everybody who is, who are joining us live again, we had people today again, just to tell you, we have Patrick from India. We have. Paul from the Netherlands. We have, Asai from, he didn't say where he is from, but based on the name, he's, probably from India as well. We have, Rahil from Pakistan. We have obviously multiple people from the us and so really people from all around the world. This is ah, Berlin. So we have Marta from Berlin. And so really great to see everybody 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 the eyes of people. Some people, wrote in the chat like, okay, that's obvious that you need design skills to do this. and the answer is it helps a lot, right? But it's definitely not necessary. So I have zero design skills and I do stuff like that as well, and I don't do it as frequently as Armen does, but I'm getting pretty good results. So all you need is to experiment. Like literally go and try yourself, get yourself a license to Freepik or choa and just to give yourself a test project and just play with it. Try different models, try different, prompting skills. Use AI, whether Chachi pt or Claude or Gemini, it doesn't matter, to help you prompt and play around. And I think you'll be really surprised with how good your outputs are going to be based on what you think your skills are, and then you can move forward from there and get better and better results. Thanks again, Armin. Thanks everybody. Have an awesome rest of your day, and I will see you next Thursday. Bye everyone.

People on this episode

Head Shot

Isar Meitis

Host