68 | AI As Your Creative Co-Pilot: Transforming Creative Ideas Into Reality with Sachin Kamath

In an era where creativity meets technology, understanding and leveraging AI tools in the creative process has become imperative for business success. 

This session will walk you through the end-to-end AI creative workflow.

Discover how AI can serve as your ally from ideation to final design, revolutionizing the way concepts come to life. We will navigate through the use of cutting-edge tools at various stages - starting with brainstorming, moving on to conceptualizing, and ending in the creation of final, Ideation -> Draft -> Image generation -> video generation.

Our special guest, Sachin Kamath, a visionary in the realm of AI and creativity, will share his expertise. Sachin's groundbreaking work, including the development of the consistent character GPT, exemplifies the potential of AI in generating innovative and cohesive designs. 

His journey from a senior technical lead to an educator and influencer in the AI space, coupled with his hands-on approach to AI workflows, makes this webinar a must-attend event for forward-thinking leaders.

This session is not just about understanding the capabilities of AI; it's about envisioning its application in your strategic initiatives. Whether you're looking to enhance your brand, streamline your design process, or inspire your team with cutting-edge technology, this webinar will provide you with the knowledge and inspiration you need.

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/
• Free AI Consultation: https://multiplai.ai/book-a-call/

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!

Transcript

Isar Meitis: 0:00

Hello, and welcome to a live episode Of Leveraging ai, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business, and advance your career. This is Isar Metis, your host, and I have a fantastic show for you today. There is a big debate in the world right now whether AI is gonna positively or negatively impact human creativity. Some people are saying that because AI can create all these things, then it will harm human creativity. Because, what's the point? I'm actually on the other group that's saying that AI is gonna boost human creativity. Why do I say that? Because it allows people who have creative ideas, which do not have the creative. Technical skills of creating images or painting or creating music to actually bring their ideas to life. I'm one of these people, the stuff that I can do with AI today, when I speak on stages, when I teach my courses, when I work with my clients, I can do amazing things that were not possible before, without hiring different kinds of people who are experts in understanding my ideas and then executing those ideas. So it is the ultimate democratization of creativity, and I personally absolutely love it, and it is, but there is still a barrier. And the barrier is you need the knowledge on what is the right process to get your creative ideas into life. And which AI tools to use in each and every one of these steps and how to use them well. I'm really excited that this is exactly what we're going to talk about today and learn from Sachin. Kamath Sachin is our guest today, and he's one of the rare people that have both a strong left side and right side of the brain. He has a master's degree in engineering, but is also a professional artist that is making and selling art. So this unique combination makes him the perfect person to teach people how to use AI in a creative process. And he actually teaches a course that shows people how to do the entire creative process using different AI tools. It's called the AI Accelerator Workshop for Creative Leaders and Teams. And today he's gonna share with us how to create a full storyboard process, beginning to end. What are the tools, what are the prompts in order to. Create a storyboard for anything you want in your business. This is, as I mentioned, an amazing opportunity for us to learn from somebody who does this professionally and for a living, and so I'm really excited to welcome Sachin to the show. Sachin, welcome to Leveraging ai.

Sachin Kamath: 3:28

Thank you so much, Azhar. for the wonderful introduction as well, so yeah, very happy to be here and, yeah, I'm ready to dive in and share the process that I usually walk through as well. Before

Isar Meitis: 3:42

we start, I want to ask you a quick question. This process is obviously something you've been working on for a very long time. Yeah. If people are not that advanced, can they just take the process and start, or are there prerequisites for people to learn or experiment before they jump right into what we're gonna show

Sachin Kamath: 4:02

us? I think no, this particular process is, super beginner-friendly as well. So even for non-designers who do not have any design background can totally use it, and get started with it. But if you have a design background, you have these, UX UI design or any kind of graphic design background, it's definitely going to be helpful and it just supercharges your creative process. Okay. Fantastic.

Isar Meitis: 4:28

Before we start, I'll say one thing. We do these live sessions almost every Thursday at noon Eastern time. If you haven't joined us, come join us. You can either join us on LinkedIn Live or you can join us on Zoom and sign up for the Zoom, and then you can actually ask questions and participate while we're doing the thing. so feel free to do that. We would love to have you, but for now, let's get started. So just walk us through the process. I'll ask questions if I have any, and, let's learn this together.

Sachin Kamath: 4:57

Absolutely. I do have a deck that I have created and I think I can walk through the step-by-step process. So let me go ahead and share my screen. Isar? Perfect,

Isar Meitis: 5:07

By the way, for those of you who are listening on the podcast, I'm gonna let you know that we're gonna share with you and tell you everything that we're seeing on the screen, but you can also watch this on our YouTube channel. It's called Multiply AI YouTube Channel, and we spell multiply with AI in the end instead of Y. So Multiply ai, you can go and check the full details over there. I assume right now if you're listening to the podcast, you're probably either driving, walking your dog, doing your dishes. working the yard. So you probably cannot watch the screen, but you can definitely go and check out the YouTube channel afterwards. So path

Sachin Kamath: 5:40

to use Achieve. Alright, you're looking at my slide deck, right? It's on the full screen right now, just to make sure we're all Oh, yeah. Okay. Awesome. Awesome. So let's go ahead. So I'm the co-founder of AI Lemon Academy, and we help you unlock the full potential of AI in your creative process, right? So that's what, I'm every day looking forward to. Every day I wake up and I'm thinking, Hey, what is the AI workflow? What is this new AI tool or AI model that I can really use and implement in a particular use case that, that I'm looking into? So as part of that, we all know over here that the future is definitely the human and AI collaboration. So your role as we see going into the future will be creative direction and curation of inputs and outputs. And of course, in between all of this, you need to get better at AI applications and knowing when to use them for the right purposes and the right workflows. we have up until now provided, like a ton of workshops, free workshops. We do this as part of our learning programs, and we have been providing trainings and boot camps as well. And as part of this, a quick background about myself, I'm an artist and a designer at heart, and I love painting and drawing in my free time. The images that you see over here are not AI generated. These are actual photographs. Of my hyper-realistic drawings, and I'm very curious about the intersection of art and technology. And over one year ago, I had co-founded AI Lemon Academy and started helping top creative agencies and education, education creatives on how to use these AI tools really effectively in their creative process. Because I saw that there was a lot of gap between who were really adopting this and a lot of people were actually getting left behind in the real potential of using these workflows. So today I'm going to, take you from how you can go from an idea to storyboard in minutes with ai, and especially if you are a creative director in a marketing or advertising agency. This workflow is going to be super useful if you want to streamline your storyboarding process. Now this will save you really valuable time while ensuring you can effectively communicate your ideas with your team and, and also through, with the client throughout the project, right? And that's the key over here so that you are able to very eloquently, tell your ideas to the other people. And visuals are a very important part of this. Now, take for example, I have to develop an ad campaign for Tesla, right? And the panel one is, for example, the dawn of new era Panel two is the drive and panel three is the destination. So let's say that these are the three concepts that have broken down into, and we'll take a look at, hey, how you can break it down into these, these three concepts. But I already have a concept and I know that in each of these panels, I want this particular image to be shown as part of a narrative. What am I going to do at this point, right? At this point, I can quickly put together this storyboard with the help of ai just going from this concept to the final visuals, and then connect them into a wonderful pitch deck, and tell a story and you can apply it to your commercials, short films, documentaries, corporate videos, social media, mood boards, et cetera, right? So there are a lot of other applications around, around this particular workflow, but I think, this step-by-step approach, when applied is super useful for creating storyboards to bring your concepts to life. Now, what exactly is a storyboard? And this is what, a traditional storyboard and storyboarding process looks like. So you have an idea in your head and based on the client's briefing or requirements, whatever the client has shared with you. You want to put it down on a piece of paper or document so that you can communicate your ideas to your crew, and in the end pitch to your client. So what you're going to do is either going to make rough sketches if if you like sketching, or many of the times this does not even happen just because the lack of resources around us. But this is a traditional storyboarding process, trying to put down your ideas and concepts, in a way that you can visually communicate to somebody else. Now let's take this example from this movie called The Edge of Tomorrow. If you don't know it, it's actually a sci-fi movie and there is a lot of action scenes that are involved, as you can imagine. and it's made especially dramatic by the choice of camera angles. As you set out to create a film storyboard and like you see over here, and this is what a typical three frame storyboard looks like, that conveys a story. And I think any particular idea, any ad commercial, for example, two minute ad commercial, three minute ad commercial or any short scene or a film can be conveyed in these three, storyboarding process. Like these three panels, right? You can think of, it as if you're familiar with these, terms, it is an, it is for example an establishing shot. it's a point of view shot and in the end there is a shoot that shows how all of these are connected together and you really get an idea of the entire story. So any story can be broken down into three frames. Alright, so now the question is how can we all use AI to help us reach that particular stage? how can we make this process much more easier? Now many of you will be familiar with what I'm going to talk over here, and you might have faced the same, problems or hurdles, on your way from concepting to final pitching. You probably have often found yourself stuck in the brainstorming phase and not able to find that create to direction to go to the next step. You have a rough idea for an ad and you, but you still don't know what to do with the next, step to turn it into a story and create a high quality visual. Or, for example, you might have a full script planned out and you want to turn them into a professional shortlist for storyboards, right? These are typically the two use cases where you probably have a vague idea, rough idea, or you might have a full script, but the next step is definitely trying to break them down and trying to put those visuals to together.

Isar Meitis: 12:20

I wanna pause you for just one second and generalize this for a lot of people in the audience. So the process you're talking about is like a creative agency, but the same kind of needs exist in any company. If you think about most marketing campaigns, they will have some visuals that are gonna be attached to them, right? Those visuals could be static visuals could be video, visuals, could be, a combination of them depending on what the campaign actually needs to achieve. some industries you need those visuals to actually sell something. So if you're selling any design services, not just graphic design, but you're selling interior design, you're selling lighting solutions, you're selling carpets, you're selling, your Ikea and you're selling, furniture like there is right? In many industries, the design process is a very big part of not just marketing, but actually selling the product that you're trying to sell. And if you generalize this when you're talking to clients, if you can create visualizations that are appealing to the client, they don't have to be your product, but they convey why they should use your product. And my favorite example that I always like to use is people sell grills never show a an image of a grill in their ads. They show a backyard party, right? Because that's what you're selling. You're selling that fun atmosphere of people around the grill, having beers. These are the things you can have in your head when we're continuing with Sachin through this process of oh, I'm not a marketing agency. I, I know, but there's place for this process in literally every company across multiple use cases.

Sachin Kamath: 13:54

No, absolutely. so I think, any product that you wanna sell, any, story that you want to tell might not be directly related to, that particular visual, right? So you can always build a story that emotionally connects to that particular need. So I think even while creating a pitch deck, this is super useful to then tell a story. And I think, there are a lot of other indirect use cases you can take from here with what the, the steps that I'm going to show you, especially, in the image generation process, right? but you are totally right. I think there are so many other, directions You, and use cases you can go from here. and what I wanted to point out is, especially within the storyboarding process itself, it's a very manual and time-consuming process and many cannot afford going through that particular process. Now, the demand for visual content and storytelling is also so high that this quickly becomes a bottleneck and many just override this process altogether, which leads to loss of information when you are, when, if, even if you're a marketing team and communicating what you really want to, convey in your visuals to your final client or to your team members, there's a lot of loss of information because you're just using words to convey them. Plus, there is not so much of innovation that is happening in this space, and that's exactly why it's a perfect use case for AI to help you in your creative process now, integrating AI into your creative process. Makes advertising pre-production, very inef, very efficient and easy because it is so much cheaper and faster. Plus, you will be able to control and still keep the highest quality in your images. And I believe every creative professional now needs to leverage this to that advantage. just like we discussed, we have had a couple of calls earlier as well. We talked back and forth about this. I think, non-designers can definitely, benefit a ton from this, but really professionals, creative professionals can supercharge that process, that creative process because they can just take it up a whole, to a whole new level. And the entire barrier to creativity, can be raised, The bar to creativity can be raised right, With this. Now, of course there is a learning curve, but once you integrate this within your creative process and train your teams to collaborate with ai, you will quickly see the benefits. The process is actually very enjoyable. It enhances your creative output and you will be able to scale your creative process, or your creative agency. You will be able to seamlessly transition from a rough idea to a professional shortlist for storyboard or for your pitch deck and send this out to your clients the same day. There are examples like this. This is already happening and we have seen a lot of our bootcamp participants telling us about the efficiency increases and the cost savings that they have add while creating any of this. Now here is what I'm really talking about. Now, this entire screenshot looks pretty overwhelming. but don't worry about it. I will break it down step by step, and I will show you what is involved in step one, step to step three, to go from concept to the final visuals, right? And that's what, we will cover. So the step one is, definitely to generate these unique concepts for your advertising campaigns. Now, many of you might already have these ideas in your head as soon as you read through your client brief. if you have this rough idea of the campaign story that you want to tell, then it's absolutely great. You can start there. But if you don't, you can always generate some pretty unique ideas with GPT-4. So for this particular step. GPT-4 is the best that is out there for creative concepting and the most accessible as well. So let's imagine that you have already come up with this concept because it's pretty much starting with, asking GPT-4. Hey, here is my idea. ask it to be a character that you want to, want to be as part of taking this road. Take for example, you can ask GPT-4 to become your, the c seasoned creative professional, or a seasoned graphic designer. First, you have to give it a character. And I think a lot of the, a lot of your listeners, your audience, are already familiar with this. First, you need to give GPT-4 a character. In this particular case, I'm going to tell it, Hey, you are a seasoned creative director for, for marketing campaigns of some top brands that are out there. Now, this is my brief. Can you generate me some. Three concepts that will work really well for this particular industry sector. So that's one way to get started. frankly, to get started, there are so many different ways, and I think it depends on our own unique style as well. but getting started is the most straightforward step in here, and for that it's GPT for now, the next step, I'm gonna

Isar Meitis: 18:50

pause you for just one second. Again, just generalizing it for something that I do that is very similar, but it's for a very different purpose, a very similar process. I do a lot of presentations, I do presentations. When I teach courses, I do presentations on stages. I do presentations to clients to or to prospects to become clients and so on. I love including relevant graphics in my presentations. And I follow a very similar process where I would sometimes even use ChatGPT to help me develop the outline of the presentation. But once I have the outline, I know what's gonna be on the slide. I literally go back to check, ChatGPT and say, okay, here's the presentation that I'm doing. Your role is, let's say in this case, an expert graphic designer that is an expert on conveying, complex ideas with simple graphics. And I will then give it the general flow of the presentation. Sometimes if I have it already done, I will upload the actual text, the actual PowerPoint presentation into ChatGPT as a resource and say, okay, what would you suggest three suggestions for graphics for slide number one? And it will give me three suggestions. So instead of starting with a blank sheet of paper, I now have ideas I can start playing with. And sometimes I won't pick one of them, but it's a good start for brainstorming either myself or back and forth with

Sachin Kamath: 20:08

ChatGPT. That makes a whole lot of sense. And I think, we have to give a lot of context for GPT-IV to come up with really specific ideas. The way I usually start over here is. I just need a starting point because I might have some of my own ideas, but I wanna see, hey, can it gimme a creative spark to go in a new direction? And usually I'm not, and I'm not just talking about GPT-IV prompting, I'm also talking about image prompting. a lot of people think that to create images, you need to provide a very specific, huge pa paragraph of prompts to get the specific results. Yes, you do. But when you first get started, you have to actually start very simple. You just need to specify your subject, followed by some kind of aesthetics that you might have on your mind, right? and that's the really the starting point because when you start adding additional things, especially in your image generation, you really want to have control over your next steps over your image generation, right? And you might have found that when you're using, take for example, I think a lot of people use mid-gen, you might have found that it's not really listening to you and you don't really know where things are going wrong. And this is exactly why, to keep the control of your image generation, you need to be very simple, very straightforward in your first prompts, and take it from there. and of course you can build complexity from then on. And I really think of it as a creative process rather than putting all the keywords right away in there, and then knowing that you're not getting the images, you try the same thing three, four times with other keywords. You don't get the images and people get frustrated. So I think the real key over here is to start very simple in step one and then start adding complexities, step by step, right? So that's one tip I would, give out. And the same thing is what I do with GPT-4. I start very simple, straightforward, and I wanna see, do I get a new creative spark from there. Now, once I have that in the step to the next step, I'm going to break down the concepts for each of this frame, right? because I need, I want to create a three-panel storyboard. For this particular example, I wanna break down the concepts. What is the first frame? What is the second frame? What is the third frame? And here is an example prompt, that I used. So I went ahead and prompted GPT-4 to break down my concept into three different frames. Now this is just an example prompt, which I used for this Tesla ad storyboard, which I wanted to create. Now, the tip here is your three pictures could be sequential with direct connection from frame to frame, or the relationship could be even more loose, right? So it can be a little bit of indirect connection, or it can just tell a story from point A to point B to point C. So I think you can leverage different ways to tell a story. And here is an example of, example prompt for creating a three-piece storyboard so that the GPT-4 gives you a what the panel one, or the frame one looks like, what the frame two looks like, and what the frame three is going to be. And, as you see over here in, in the brackets, this is where you can, oh,

Isar Meitis: 23:20

I'm gonna pause you for a second. Just for our listeners, if you can read this thing beginning to end and then comment on the last section that you're talking about, because some people are not gonna be able to watch the

Sachin Kamath: 23:28

screen. No problem. So I'm saying, I'm just going to read what I have here in the prompt. I'm telling it you are a seasoned, creative and art director, and you have created some top award-winning marketing and advertising campaigns for top brands. You have a new challenge, create a compelling three-page storyboard that will impress your client, right? And here are further details. Now, this is where you can get really specific or you can be a little more, open to GPT-4 giving you, taking you in new direction. So I'm asking over here, your task is to create a three-page storyboard, one large composite consisting of three pictures and a title. Your three pictures could be sequential, could be parts of a panel, or the relationship could be even more loose. However, there should be something that unites them all as well as the title. So I'm setting up the context, overall context of what each of those, breakdowns should look like. And now here I'm going to input what the brief is. it's saying, let's conceptualize a storyboard for Tesla, a brand at the forefront of innovation in electric vehicles and renewable, energy technologies. That storyboard will focus on a future product that embodies Tesla's commitment to sustainability, cutting-edge technology, and the vision of a world powered by clean energy. We will introduce the Tesla solar car. Again, it's a hypothetical one, which I'm using as an example, A revolutionary electric vehicle powered by advanced solar technology, capable of self-charging under sunlight, right? So that's my brief. It's a very short brief. Of course, you will get, much more detailed, brief from your clients, and you can include that over here. usually I start with something very simple. Like I said, I like to go in new directions. Now, the, my last sentence in the prompt is design this three-panel storyboard and, impress them for the next big advertising campaign. Go. That's it. That's my, example prompt, which I'm using for this one. Fantastic. I

Isar Meitis: 25:28

wanna a quick. Like behind the scenes, why this is a good prompt. the prompt starts with, and every prompt that you want good results needs to have the same thing. The prompt starts with telling you what role it's doing. In this case, a seasoned creative director. It continues with what the goal needs to be. So it defines clearly what the goal is. It defines the format of the output, right? So you could ask for a tweet, you can ask for an image, you can ask for a whole 20 page document, like you can ask for many different things. It very clearly defines what the format of the output, and then it provides as much context as possible for it to create the best outcome for you, which makes it a very good prompt. a great way to start. What's the outcome of this and how do we continue

Sachin Kamath: 26:16

from here? Yeah, absolutely. Thank you, Isar. And, I'm, I. I would also love to know any advice from you over here to take this to the next level. and we can have a chat about that. but here is something that I start using to just get, again, a starting point into what will my results look like. and, again, I mean in this particular slide, what I want to highlight is iteration is the key, right? So based on the prompt, and my specific request, I get this three-panel description and breakdown of what should be in the each, in each of those panels. So I have a screenshot over here, of what ChatJPT has replied to me. Now, here is the most important part. You will need to iterate and take it in your own creative direction, right? So this is why it is human and AI collaboration. If you just take these inputs and directly proceed, then the results will be suboptimal. I would always suggest that try to push the boundaries of creativity right in this particular step, because you will not always get, sometimes what you specifically want. But also if you get something that is close to what you're looking for, why not try to go a little bit beyond and push the boundaries and see if you can come up with something unique and make it your own, right? So this is the step where you iterate. Alright, so let's moving. moving ahead. We have step three, which is creating sketches for each frame with ai, using the prompt crafting and image control techniques. And this is exact, this is actually the most exciting part of this. I'm a visual guy. I love creating images, animation, paintings, sketches, right? Like I showed you. And especially for me, this is the most exciting part of it. Here again, I have a screenshot of, what GPD has provided me. So let me, let me just walk you through it. Now, there are multiple ways and tools to approach this, and here is the simplest way, right within GPT-4. jp, I always use GPT-4 because it is powered with Dall-e. And all you need to do is in the next prompt ask you to generate a sketch for that particular frame. You have already received these breakdown, like panel one, panel two, panel three from your previous step. Now just, just ask in the next step, GPT-4 to create a sketch out of that particular panel. Yeah, and this is exactly what I've done over here. As you see, that Dall-e generated this beautiful sketch for me, and it is very good at listening to my image prompts. In fact, it is the best at prompt adherence, even the, even better than, MidJourney vSix in most of the cases, however. So I

Isar Meitis: 28:56

wanna pause you for just one second to talk a little bit about the two biggest differences between Dall-e and MidJourney, which are the two tools I use the most as well. I use a bunch of others. I use stable diffusion a little bit. I use, Ideogram every time I need some text, but mostly I use MidJourney in Dall-e, which is part of ChatGPT 4, and there's two very distinct benefits, one on each side. The benefit of MidJourney is that if you looking for high-end realistic outcomes, nothing beats MidJourney.

Sachin Kamath: 29:28

Absolutely. Yeah,

Isar Meitis: 29:30

absolutely. However, it's harder to get those results. If you look, the biggest benefit of ChatGPT is that it's a part of a chat. It understands the context of what you're trying to do. In this case, it's been a part of the whole conversation, right? Beginning to end like this is what we're trying to do. Let's ideate, let's come up with the ideas. It understands what we're trying to do, and hence the chances that the image is going to represent what you want it to represent is in less steps and less pain. Significantly higher. So I will say that if you're looking for the ultimate image, MidJourney is the way to go. It will be more work. If you're looking for something that's gonna be good enough, it's gonna save you a lot of time. And some, in many cases that's good enough is, guess what? Good enough then you don't need to go, further than this. So there's a huge benefit in doing what Sachin just described, which is to, I'm having this chat, and then from within this chat, I'm starting to generate the images because it understands what is it trying to do.

Sachin Kamath: 30:36

Yeah, absolutely. by the way, mid Journey is my favorite, image generator that is out there. Every morning I wake up if I have any idea, the first thing I do is I go to Mid Journey and I type it out and I see what kind of visuals I get. Yeah. Now I'm using, I'm showing GPT-IV over here because this is the easiest way, the simplest way to get it done right within, within what we are, the storyboarding, what we are talking about, because we have the concept right there. And you don't need to prompt engineer, engineer it to creating very high quality images because there is a kind of learning curve involved to taking it from ChatGPT to then prompting it in mid journey. But by the way, mid journey, you can do a whole lot of techniques. It's not just prompting and creating images. There is a ton of things that you can do. In fact, I deep dive into mid journey a whole lot, in, in, in the bootcamp itself. but also I love using, stable diffusion, comfy UI. All the open source AI models, and there are a lot of things that you cannot do it with MidJourney, and I will show you some of the examples. Take for example, you want to get that exact pose of the person with the exact face all in the same image and create a hundred different variations. You cannot do that with MidJourney. You cannot create the exact consistent character with Midjourney, right? there is a bit of trick and kind of workflow, which probably takes a lot of time and will not give you a hundred percent of the result, every time. But, and, but it's great for high quality photorealistic images. Yeah. and right over here, what is the sketch, A beautiful sketch which, Dall-e generated for me, right within GPT-4. I just told it. This is panel one, right? Create a sketch for me. create a detailed storyboard style black and white outline, sketch for this image. Usually the storyboard images are sketches. That's good enough. and why did it generate just a black and white sketch? It is exactly because Dall-e is very good at listening to our prompts, but it's not very good with aesthetics and photorealism. And this is exactly where we need to go into the next step. What I'm going to show you. So step four is turning these sketches to final illustrations and quickly iterating to land on your final concept visuals. Now, in theory, you can just as well at this particular step stop, right? You have the sketch and you have the storyboard description. You have the story to tell. You can stop, but we can also go one step further and get those A aesthetics in the final image and turn them into finished visuals. And this is exactly what we will quickly take a look at. And this is what I'm talking about. What on the screen here right now is on the left side you have the sketch, which we generated with GPT-IV, and on the right side you have the exact same sketch turned into a photorealistic visual, which is not possible with MidJourney. It's impossible with MidJourney, even if you use image references, even if you use image weights, it's not gonna listen to you. It's not going to stick to that particular outlines, to that particular reference image that I've used. And this is exactly why we need to turn to, another tool, which is, you can use the open source models like ControlNet and StableDiffusion. In fact, I use it a whole lot with, my own ComfyUI or focus, as I call it. focus, Automatic-Eleven-Eleven, and ComfyUI. These are the three, interfaces for using StableDiffusion on your laptop. But that is an easier solution that is out there. So there is this web app. Called Leonardo ai, which is built on top of this open source technology and helps me get these images exactly based on my storyboard sketches. And it is powered with stable diffusion. And I can use the control net extension all within it. So just like you see over here, I have given it my sketch as a reference image. I have also,

Isar Meitis: 34:34

so I wanna pause it just for one second. For the people, again, who are listening, what we're looking at right now is Leonardo.ai. It's a great tool. It's free, it's a really powerful, image generation and manipulation tool that, that everybody has access to and what Sachin has done, he's using that. The first thing he did is he uploaded the sketch that was created by Dall-e inside ChatGPT at the previous step as the initial starting point for the process that we're gonna do in Leonardo.

Sachin Kamath: 35:03

Exactly. by the way, I think Leonardo is an amazing tool. it's powered with stable diffusion. And as you see over here, you can select different fine-tuned models. This is where it's super powerful. You can pick from different kind of styles and aesthetics right there. and it's free, right? You get the credits, but I'm not sure if you will be able to build this workflow because, you need to use this extension called ControlNet. And I'm using over here the Edge-to-image model. within that and, the image guidance, which is, you have text-to-image, and then you have image-to-image. And here I'm using the image-to-image along with the ControlNet extension. I think you have to pay for this, but I think you can give it a try, right? as you log into, Leonardo ai, you can select this. And over here I have input my reference image and I have written down my prompt. Which again, you can engineer this prompt within Leonardo by using the prompt generation guidance. everything can be done within Leonardo ai. So the

Isar Meitis: 36:03

prompt is, I wanna pause you just for one second. there's a personal LinkedIn Live that is asking can we use Playground to achieve the same effect in what you're doing in Leonardo right now? And I don't know if you know what he means.

Sachin Kamath: 36:14

I think, if you're talking about Playground AI powered by Stability ai, I'm not sure if it's powered with Stability ai. It might be, but you need to really look for, if they have this image to image along with the control net extension. If they don't, you'll probably not be able to do this. Okay. it's the same thing as like when you use MidJourney, I can still use this as a reference image as a sketch. But it'll not gimme the result like exactly the sketches. It'll,

Isar Meitis: 36:43

Yeah. It's gonna be, it's gonna be its own interpretation versus a rep a, a high resolution image replica of the

Sachin Kamath: 36:50

sketch. Yeah. But you can also use open source models on replicate that is a control net model. You can do this within it. iPhone Leonardo is one of the best ways, for everybody to access it and to start doing this. Alright, here I just use my reference sketch, and, like I just showed you with the extension and there you go. I have turned the sketch into a photorealistic image, Within Leonardo ai. And that's the power of using, these AI tools and thinking, thinking all of this as an AI workflow, right? I think the real power is building AI workflows. Prompting is a small piece of the puzzle. really, this is what I think because prompting is going to become more and more natural. natural language power, just like Dall-e is very good at it. MidJourney will get there very soon. and prompting, even though very important right now is going to be a small piece of the puzzle. And the real power is in building AI workflows for your particular use cases like model, photo shoot, right? Where you wanna have particular posts, particular, you have, you want that particular consistent character in every single image. You want that specific pose, or you want to change the pose very easily and it's listening to your prompts. That's what you are, that's what you're looking for. And you can build these kind of workflows and you can follow these steps for each of these panels, each of these frames of your storyboard, each of these panels. and there you go. You have, these three panels, storyboard ready, right? you have the script. You have each of those panels what it should be. You have the sketches for the panels, and you have finally the images, the photorealistic images.

Isar Meitis: 38:26

So I wanna pause you for a second. First of all, I think it's brilliant. I think it's absolutely amazing. Again, for those of you who don't see the screen. We have three columns on the page. On the left, we have the digital description. In the middle we have the 2D, black and white sketch. And on the right we have a high-end rendering, realistic view of the same exact sketch. Like it looks as if somebody, as if it was a coloring book that somebody who's really good at coloring colored it to make it, fully realistic. Like it's literally the same image, just in 3D reflections, lighting and everything. Can you go back for a second for Leonardo, because I want to go a step more detailed into the actual step in Leonardo, because I think it's the most Technical one we've done so far. So the steps are this, right? You said you uploaded, you upload the image. That's easy, right? You download the image from Dall-e, you upload the image. You said you write a prompt does the prompt, what does the prompt describe? Can you read the prompt that you use to create, go from the 2D sketch into the 3D beautiful image.

Sachin Kamath: 39:28

Yeah. So here, as well, is where the prompt crafting skills come into picture, right? Because you can change this. You need a prompt, which will define your final vision as well. Just a reference image is not enough. If you really want to get that final aesthetic and have that aesthetic consistent across the different frames you wanna have, to engineer your prompt. So my prompt here is the pearl white Tesla solar car. So I'm defining the color right, and I have the subject in there with its sleek and aerodynamic form. Cuts through the stillness of the deserted highway at sunrise, a stunning display of harmony between technology and nature. First slide of dawn sun rising in the background. I have pretty much described the subject, what the subject is and what it's looking and I've described what the surrounding, is. Right? And then I'm hoping Leonardo fills in some of the creative gaps for me, or you can get a little more, specific in there. But also keep in mind when you, when your prompt becomes very big, it starts to ignore some of those details. Yeah. But of course, we can deep dive into, the prompt crafting funnel. The technique, that I work with is, is definitely a lot more, than this. And it's very important that you get your prompts to get your final aesthetics, to have them consistent across frames.

Isar Meitis: 40:48

So I want to ask you specifically about this, because I, when I do stuff like that in MidJourney, I use the describe function. So those of you don't know in MidJourney, you can upload an image and ask MidJourney to describe it. So instead of doing forward slash Imagine, you can do forward slash describe, and then it gives you three prompts that it thinks will, describe the image. And then what I do when I want to create images that are similar to other images, I pick and choose components from the three, variations of descriptions that MidJourney comes up with on its own. And I craft something that I think is the best description, combining all these components together with the weights that I think, or the order that I think that will get me closest to what I'm looking for. Is this a similar process? is there a mechanism you use to come up with this prompt? Is it just based on the prompt you had in Dall-e or is it just your, experience that teaches you how to

Sachin Kamath: 41:44

do these prompts? I'm just trying to look for the basic ingredients. When I'm prompting, am I describing my subject? can I, can the machine know what I'm talking about? and I'm trying to make it easier that way, but I'm also trying to leave some gaps for some of the creativity to flow into it, right? Because I don't wanna control every single thing. Finally, this is a storyboard and it's a pre-production step. I can get much more detailed in the next steps, right? I am only looking to get those aesthetics that can tell a story from my vision, my, from my point of view. so I have things here take for example, your, you have your subject, then you have your color themes. I. Anything that describes the mood and feel of the overall scene. That's what I want to have over here. Anything that describes the background, like I envision it, I'm gonna have it over here. and, I think having that ambience and that mood along with lighting will just take it to the next level. And I think those ingredients are something that's good enough to, to start your journey, to start, your prompting and of course then you can do image manipulation and a whole lot of things, with the AI workflows as well.

Isar Meitis: 42:53

Fantastic. I, now I think it's a lot clearer. So you're basically trying to describe the vision you have in your head of what this would look like if this was a realistic image, but leaving enough room for it to come up with different ideas.

Sachin Kamath: 43:10

Exactly. Yep. I think when you are using AI image generators, any AI tool, even for copywriting, you have to be able to let go of that control, that ultimate control you will get. you can find many, you will find many different ways, right? You can build AI workflows. In fact, if I need, like I said, if I want a specific pose of a person, if I want that specific outfit, if I want the specific face of the person, I will not work with some of the tools. I'll not work with MidJourney because I know it'll not work for me. I will use the open source models and build my own workflows to get that done. So I think it's key to realize, and I think that's the skill that everyone, needs to learn over the next two to three years, which is really curation of inputs and outputs because the AI models that you choose. It's going to depend on what inputs do you have and what output you're looking for. And that's when you will choose what AI model or a, what AI workflow to build, which you can then use multiple times for very similar projects. And I think that's the, that's, that, that's the secret to scaling any part of your creative process. And that's, that's what I look into. that's, that's what I'm passionate about and I always look for these AI workflows that can really fill a gap between a creative process.

Isar Meitis: 44:28

Fantastic. there's a question on LinkedIn Live. can you adjust the aspect ratios of the images? I assume that applies both for the sketch created on, Dall-e as well as, okay, now I'm in step four in Yep. Leonardo, can you still change the aspect ratio? I.

Sachin Kamath: 44:47

I think you can change the, aspect ratio, like you can make it 16, by nine. in Dall-e you can tell it here is this is the aspect ratio and it'll do it for you. And then you can take that image in here. And as you see over here, there is also, how do I call this? There's also a button for, aspect ratio and you can choose different, dimensions. one tip is if you want to use AI image generators, like especially stable diffusion, your output, needs to have the same aspect ratio as your input for image to image. Otherwise, you might find, that there you, there might be discrepancies and you'll not get that high quality result. Alright. good. So let's move to the next step. okay. And we just saw this, we just saw this one. And yeah, we have the storyboard from here. So with this AI workflow, now you can clearly pitch and sell your idea or your vision to your client. So you don't have to use words like, imagine this scene or that person. You can just show them these images and sell them the creative idea that, or the creative campaign that they're, that you want to design for them. And you can do this all within twenty-four hours and take that brief and tell them, Hey, this is the idea that you have. Do we sign off? Do we have an approval? And of course there is a ton of things that you can do, afterwards, right? I'm only talking about pre-production, where your images are good enough for that particular step. And then a whole lot of AI workflows that you can also build afterwards. Alright. I would love to know, if you do you all find this workflow useful? And yeah, if you do, I would love to hear your thoughts in the comments or any questions you have. You can, shoot out a message for me and yeah. I would also like to show, whatever we looked over here is just. Scratching the surface. I would like to give you some more ideas on what is really possible when we deep dive into the AI workflows, right? we are always looking to see how we can push the creative boundaries. What if we can add animation and here is what it looks like.

Isar Meitis: 46:58

So again, those of you who don't see the screen on three panels, again, on the left there is a kind of like a pencil sketch of a high-end performance, futuristic race car. In the middle, there is a variation of it that is like colored, but still looks like an image. And on the right, there's an actual video of the race car driving. And I assume you've done this either with Pica or with, Runway, right?

Sachin Kamath: 47:25

Yeah. This is with Pica Labs. and you can do this with Runway as well, or stable video diffusion. So it's like always thinking what you can do as the next step, right? Instead of just showing the images, can you turn it into a animation? And there are a lot of ways, to control the animation as well, right? You can do camera controls, you can tell your story in a little bit, take it one step further, tell it in a more compelling manner. And videos always work. So it's always about figuring what really works for you as part of your creative process. And that's, one thing I wanted to show. Take for example, if you want to generate some wonderful, unique concepts for your campaigns. That is possible as well. This is when you have to push the boundaries and start using the right tools because, for example, MidJourney will not give you these kind of results. You, you'll probably have to work really hard, and even in the end, you might not be able to create these kind of images. This was created with Dall-e, by the way, right? So you need to really understand what are the tools that work for you? What is your input? What is your output? And what would you like to use, as to, to go through that process. Now, here, is an example where you can take control of your image generation and tell compelling stories, right? As part of your storyboard. What if one of the panels is not working for you and you're trying to control and trying to change things? You can, of course, craft your prompts and do a lot of image manipulation techniques, to really get control over your images while you tell your stories. What if you want to explore some specific style and aesthetics and create on brand images, right? This is what, this is what is super useful when you have a specific mood board and you want to capture those aesthetics and set settings, and you want to apply that for multiple images that you want to create for that particular campaign.

Isar Meitis: 49:16

So again, to pause here and explain to people what we're seeing. There's a panel with three images on the image. On the left has a close-up of an astronaut in his flight suit. In the middle, there's a girl in a dress in a field, and the combination of these, so the subject is the astronaut, the style is the girl in the field with blue skies, and the combination of this has an astronaut placed in a field with blue skies around it, which is like. Combines the subject and the style and settings of the two images into one really unique and interesting and innovative thing. Because you don't expect to see an astronaut in the middle of a field.

Sachin Kamath: 49:55

Yeah, exactly. So if you have some unique creative concept and you have certain inspiration to start with, you can get those done. It's only about figuring out the right, process, for you. Of course you can explore, as you already know, like different compositions, camera angles, lighting, all of this. Start adding to the look of, look and feel of your images to get the final output. And of course, you can also create consistent characters. I want to close this with, I designed this consistent character GPT, and this is, top five on the GPT Dall-e store. I'm super grateful and happy for this one, because a lot of people were reaching out to me and telling me they cannot create consistent characters. take for example, for the comic books, right? They want to create comic books, tell a story, and they cannot create consistent characters within, MidJourney. And this is exactly why I designed this consistent character GPT. And I would love for you to give it a try. it's on the, if you just go on the GPT store and look for con just search for Consistent Character GPT, you will find it. And I would love to hear, what is your experience with it? What do you come up with it? yeah, thank you. And, if you have any questions, you can reach out to me or you can reach out to my co-founder. My partner, Diana Zdibble. You can find me Sachin Kamath on, on LinkedIn as well. I'm very active on LinkedIn and, yeah. last thing, we have a creative AI Bootcamp coming up with starts on March 11th. And if you want to deep dive into this AI-powered creative world, and you think this is the right, the right upscale for you and for your work and your projects, or your creative agency, then this is the right fit for you as well. So you can reach out to me on LinkedIn if you have any questions about this. Isar. Thank you so much. and I, I really enjoyed walking through this entire workflow and yeah. what really

Isar Meitis: 51:45

this, yeah, this was fantastic. Sachin, before we end, we have a few minutes. There's one more question from the audience, and I'll just read it word to word. it's from Manalo Torres. He's asking. What would you tell all the people who are not able to run stable diffusion on their computers?'cause they don't have enough GPU power? Is there an alternative to SD plus ControlNet or SD plus Comfy? UI, SD for those who don't dunno, is Stable Diffusion. So SD and Comfy UI, like the example of Leonardo powered with ControlNet. So are there other options for online capabilities?

Sachin Kamath: 52:18

yes. in fact, a lot of times when I have to run very heavy, when I have to do quick and experiments, I would run. Stable diffusion on the cloud, and you can find multiple ways to do that. For example, you can rent a GPU on the cloud and in and go through the Git installation process. you can take those repositories and a upload it. And that's a quick process when you're running it on the cloud. So I do run it on the cloud where I can rent out a GPU or you can look for other platforms. I think there are a couple of other stable diffusion, automatic 1111 especially to run stable diffusion. You can, I think it's called run diffusion or something like that. do look at it and you don't have to go through any installation process on your computer and it'll not use your GPU performance. it's gonna use the GPU on the cloud. Of course, you have to pay, but it's the amount you pay is very low. I think you'll have to pay less than a dollar, like 50 cents per hour. When you're renting out, on the cloud server. yeah. there are ways to do this and I use that often as well.

Isar Meitis: 53:23

Fantastic. Another question is, how often do you use weird or chaos parameters when you create these things? probably, I assume earlier in the process.

Sachin Kamath: 53:34

Yeah. I frankly, I don't use them so much. Okay. because there are so many ways that you can reach the reach and result, weird and chaos parameters, they are weird, right? it's very hard to say that there is a specific use case for it. take for example, I think we parameter will give you a little bit more of. Realism, like you're taken. if you want a person, a person's photograph and it makes it look like not synthetic. Like most of the images that you generate on MidJourney look like, highly amazing, highly photoshopped, highly synthetic, and you want to take out that look. Maybe that's where it's helpful. But I would probably use an AI enhancer to get that done. Kos. If I need more variations, I would probably do that, but not so much because I would rather want to keep something consistent. And then, I'm very heavily into image manipulation of how I can go from point A to the endpoint that I'm looking for, rather than just getting a lot of different variations, which, which I can use. I usually need one thing, and I want that level of control, but I also want certain level of creative spark or creative output. And I think there's a fine balance to strike, but yeah, so frankly, I don't use those parameters. So I, but I know that, they are helpful in, in, in some ways. Yeah.

Isar Meitis: 54:56

So I use chaos pretty frequently, just like you said, especially when I'm ideating and I'm trying to say, oh, what would be cool? Then I use chaos a lot, and then I get a bigger variety, and then I would upscale one image and then use the chaos again to get variations. Like it just helps me more in the. Creative brainstorming process that in the generation of the outcome process. Once you're done with that, then I try to be very specific and then it obviously hurts you. Satin. This was fantastic. Like it's a very well thought after process. you obviously, as I said in the beginning, the engineering side of you is working very well with your creative side to create really magical, process here. Those of you who haven't watched this, we will put the link to this in the show notes, the link to the YouTube channel as well, so you can go and see everything that we're talking about.'cause this one was, beyond seeing the process, there's a lot of visual outcome you probably want to watch. So you can go and do that as well. And as Sachin mentioned, go check him out on LinkedIn. That's how we connected. Go check out if you, if this is what you do for a living or if this is something you aspire to do for a living, absolutely go check out his course. He's the best out there in these kind of things and really developing. AI infused processes for creative outcomes. And so I really appreciate you taking the time. I really appreciate you sharing with us, with your knowledge. And thank you so much.

Sachin Kamath: 56:19

Thank you so much, Isar, and yeah, was a pleasure and yeah. we'll connect again very soon. Thank you everyone.