Leveraging AI

183 | 15 Mind-Blowing Use Cases for the New ChatGPT Image Generation with Isar Meitis

• Isar Meitis • Season 1 • Episode 183

Share episode

👉 Fill out the listener survey - https://services.multiplai.ai/lai-survey
👉 Learn more about the AI Business Transformation Course starting May 12 — spots are limited - http://multiplai.ai/ai-course/  

AI image generation just got a major glow-up — and if you’re a business leader, it’s time to stop sleeping on it. ChatGPT’s new image generation capabilities aren’t just fun to play with — they can seriously drive results.

In this live session, we’re walking you through 10 specific, mind-blowing business use cases for ChatGPT’s image generation. We’re talking step-by-step breakdowns for how to use it in marketing, product, internal ops, sales, and more.

This isn’t theory. You’ll leave with concrete prompts, smart workflows, and practical tips for getting incredible visuals — without relying on designers, agencies, or stock photo sites.

If you’re leading a team, launching products, or just trying to stay ahead of the curve, this is your shortcut to using AI visuals like a pro. 

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!

GMT20250417-154445_Recording_as_2560x1440:

Hello, and welcome to another live episode of the Leveraging AI Podcast, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business, and advance your career. And we have a really incredible and really fun episode for you today. Today we are going to look at multiple use cases on how to use the newly released image generation capability on chatGPT Now. We named this particular episode in the beginning 10 incredible and amazing ways to use it. And we actually came up with 15. So you are in luck today. We're gonna have 15 different use cases on how you can use this really incredible out of this world capability that Chat gave us just a couple of weeks ago. So let's start with a little bit of background before we dive into the actual, tools and how to use them and all the different use cases. And by the way, those of you who are joining us, live either on LinkedIn or on Zoom, please go ahead and share who you are, where you're from, what are you doing, introduce yourself so you can meet other people as well. And also. If you want, share what you want to get outta this episode, how have you used it so far and things like that. I will read the notes and I'll try to relate to that. And also as we go forward, if you have any questions, please ask them in the chat and I will try to relate to them, in a normal manner, but now into the background. So if you think about what we had until not too long ago, we had Dall-e, which was built into ChatGPT and you could tell it to create images, but it was mediocre the most, and it was very far behind other image generation capabilities. We also had image generational tools, which are incredible, such as, flux and mid journey and stable diffusion and tools like that, which really provide incredible capabilities of image generation. But they are standalone image generators while ChatGPT and Dall-e has the ability to actually have a conversation and understand context. So let's explain. If I'm trying to create a design for a presentation, if I'm trying to create an image for a post that I want to do on LinkedIn, if I'm trying to create anything that I'm trying to create an ad. If I'm doing this on an image generation tool, I need to work very hard to capture in my prompt everything that I need from that image. if I am in a chat, whether it's Gemini or Cha Chippie and so on, I can actually explain and have a conversation about it because it's a chat. I can provide it, the background, the information, the context of what I'm actually doing, and hence it will give me better results, more customized for my particular needs. And so it's a huge benefit. But again, the disadvantage was that the image generation capabilities of both Gemini and ChatGPT were below par. a few weeks ago, Gemini came out with Imagine Three, which is actually really good, and I started using it for almost everything instead of using me Journey and Flux, which were my main go-to tools before. Then ChatGPT came out with their solution, which totally blew my mind. Literally from the day I started using it. And I started using it for more and more things. And now I must admit, I use it for probably 95% of everything that I'm doing, and the other 5% is divided between Mid Journey and Flux and Gemini. Imagine three. So the good news is you now have one unified tool. Chat, PT or Gemini. If you're in the Google universe and you prefer to go that path, that can really understand what you're actually working on. What is the project? Who's the target audience? Do research before you actually like even deep research in all these tools and give it as much information before you actually generate the images and then the images will come out exactly what you want. But the other thing that these tool became very good and cha GPT is really incredible in that is just understanding what you're trying to do. Even when you don't give it all that information, even when you just give it a reference image and one short, two sentence prompt, and you get incredible. Results. So what we're going to dive into today is, as I mentioned, 15 use cases, things that you can do with this capability that will blow your mind if you've never played with it before. And we're gonna start with things that are incredible. We're gonna go to some regular things and we're gonna end with a few things that are really incredible that literally, blew my mind and that I showed it to professional customers of mine that do this for a living, and they would spend hours doing something that this tool can now do in. Minutes, and so let's dive right in. For those of you, by the way, who are listening and not watching, I will try to explain everything that's on the screen, but if you have the opportunity to watch this on our YouTube channel, then in your show notes on the actual device you're on, there is a link to our YouTube channel where you can actually watch this and see all the different examples that we're going to show. But I will do everything within my power that if you are driving or walking your dog or doing your dishes or whatever you're doing when you're listening to this podcast and you cannot watch it on YouTube, then I'll try to explain what we're watching. One last thing before we dive in. this is going to be highly educational and I'm gonna show you the prompts that I'm using and exactly how I created all the images. I'm gonna talk about the good, the bad, the ugly, the different steps, all the magic that I've learned how to do in working with this tool, literally every single day in the past few weeks. But this is just creating images. If you wanna learn how to use this in your business in a broader way, learn how to build strategy, learn how to write. Documents, not how to analyze documents, not how to do data analysis. Both, qualitative and quantitative data analysis, combining data from multiple sources into reports and dashboards. If you wanna know how to actually implement AI in a business wide perspective, how to apply this to different departments, how to train your people, and so on. We have been teaching the AI Business Transformation course for two years. Yes, since April of 2023. We have done this course at least once a month for this entire two years, and hundreds or maybe thousands of business people and business leaders have taken the course and completely transformed their businesses based on the knowledge that they acquired. So everything you're gonna see in this episode today. Is awesome, but it's just image generation and it's going to be very quick if you want more structured training that can literally and dramatically transform your career and your business. Don't miss this course. We teach this course all the time, but most of the time it's privately taught, meaning an organization it consortia a buying group or a specific company will hire us to train just their people. And so we do publicly open courses only once a quarter ish. So the previous course was January and now the next course is in May. And so on May 12th, we're opening another cohort. So if it's something you're interested in, again in your show notes, you can open it right now. Wherever you are, if you're driving, wait for the next stoplight and click on that and you can open it and see all the information about the course and you can sign up right there and then we would love to have you. You if you haven't done anything like this. And even if you haven't, it was theoretical and you're not sure exactly how to apply it, come and join us. Now. Let's dive in into all of our use cases. So I'll start my PowerPoint just to guide us through it, but we'll jump back and forth between the PowerPoint and actual chat. GPT. And again, if you have any questions as I'm going along, you can ask them in the chat. Okay. We are ready to go. So. Product promotion. This is maybe the biggest magic that this thing can do, and it's what we're seeing on the screen right now. Again, for those of you listening on the left, there is a low quality image that I downloaded off the internet of a sunscreen by Neutrogena. It's poor quality and it's has a bite white background, and it's literally just a download from the internet on the right. What you see is something that looks like a professional ad of a girl hand closeup, holding the same kind of product in the background of the beach, like blurry, and she has the colors of the US flag painted on her fingernails, and it says, 4th of July, sale Neutrogena. Buy one, get one free. Now I went from one to the other, from the ugly low quality image on the internet to the really beautiful, amazing looking ad on the right. In four or five. steps of simple prompts, and let's go through these prompts to see how this works. And so the first thing I did is I uploaded the ugly image and then the trick if you want to get the text right, more times than not, and this tool is incredible at creating text, but creating the text accurately. There's a little trick to do this. So what I do in step one is I wrote the following prompt, please provide a line by line text of what is written on the product. And then it literally wrote it down for me, Neutrogena dermatologist, recommended brand, blah, blah, blah, blah, blah, all the different components. And then I went and wrote the actual prompt. Now, I would like you to create a closeup professional product, photography of a female hand holding the product. The background is the ocean and the beach, but it is blurry as the focus is on the hand and the product. And then I gave the information of the camera, Nikon Z seven 50 millimeter lens aperture 2.8. And then I copied and pasted what the product text says, the same thing it wrote for me, and it created the first image. So the first image just shows the hand without all the fancy stuff around it, holding the product. It looks perfect, looks like a professional photography. It's fantastic. And then I went ahead and I wanted to see if I can change the SPF. I wanted to see how much it actually understands what's in the image. Again, a huge benefit of a chat that is a model that actually has logic versus just an image generator. So all I wrote is, please recreate the image with SPF 50 instead of 70. And it did. So now I had an image with SP 50, same everything else. And then I started to have fun with it. I said, please redo the image and change the girl's nails polish to the US flag pattern. And he did a really good job. Now it looks really cool. I'm like, oh, that's cool. So then I went ahead and I asked for the following, extend the image on the bottom. To make it a nine by 16 image and write in a fun, font. 4th of July sale, Neutrogena bogo. So it did that. But what it did, it actually wrote the Neutrogena BOGO in red, which wasn't very obvious on the actual, image. So I asked it to change the font to say, make the Neutrogena BOGO also white with brutal outline, like the text above it. Make sure that all the fingernails are painted because it missed one in the previous one. And that's it. And I had this final ad that I could literally use in a professional setup. It looks really cool and I can use it today in that scenario, that's mind blowing. This would have taken a professional photo shoot, a lot of editing in order to get this picture. And now you can do this in four to five prompts, starting with a poor quality image of a product. Let's move to the next one. So creating. Icons. That was something that, again, you usually had to go to some kind of a website and grab icons, sometimes pay for them if you wanted something to be professional. And if you wanted something unique, something that's only yours, you would have to have somebody created somebody in your design team or pay a third party person that knows how to create high quality icons. But what I did here is I actually took two existing icons from my website and I've uploaded them to ChatGPT, and I created this last icon. So let's see how this was done. So all I did is I uploaded these two images of icons that I have on my website, literally right click copy, and then I put it in there and I said, let's try something different. I've tried 50 different things in this chat, so ignore that, but then attached our images. Of two icons from my website. I would like you to learn the exact style of these icons and create new icons following the styles and the colors. The icons that should be created are blah, blah, blah, blah, blah. And the first one I ask for is the AI podcast icon, and it created this that looks. Absolutely incredible. Again, for those of you who are not seeing it, follows the same exact style of the original icons. This 3D shiny look icons, and it has a professional kinda like podcast microphone with headphones around it and it says AI in a speech bubble. It's a perfect icon for a podcast that I'm actually going to use on my website. The other very cool thing that no other professional image generation tool that I know of actually created a transparent background because it understands that this is an icon that I need to use as an icon, meaning it needs to have a transparent background. So it created that on its own as a p and g. When I download this, I can immediately use this wherever I want to use this. Now I wanna touch on something else that has to do with this, and it's kinda like use case number three, which is understanding and applying styles. In addition to the fact that I just created an icon, it actually learned the style, the essence, the colors, the. Type of thing that I'm trying to create. And yes, in this particular case, we've applied it to a. Icon, but you can apply this to anything else. If you're trying to create textures, if you're trying to create a specific style of image, if you're trying to create old looking photographs, if you're trying to create a specific. impression of something, you can upload the original ones and it is very good at understanding and capturing the essence of it and applying it in a new way. And we're going to see more examples of that. So at number four, we have applying known style. So in addition, you giving it the style, you can ask for basically any style that you want. So when this tool came out, everybody started to creating, Ghibli studio style anime images of this. But what I've done in this particular case, I wanted to show that you're not limited to Ghibli. You can use any style that is a known style or artist that is available on the internet. So on the top left is an image of a family. Actually, my family on a trip in Chattanooga that we came back from a day before this capability came out, so it was an inspiration for me. And then I went ahead and asked it to recreate the image in multiple styles. So the first thing is Ghibli. The next one is Legos, which is my favorite out of all of them. So it's actually my family sitting on a rock in Chattanooga, all built out of Legos. It's absolutely insane. and then we have, Dall-e and then Van Gogh, and then, Andy Warhol. And each and every one of these were created with a simple prompt. So let's take a look very quickly. So we have, Very simple and short prompts. So the first one, I just uploaded the image and said, please turn this image into a studio Ghibli anime. And it did the second one. Now let's use the original image and make it into Lego. So what I did initially, it's try to build them from Lego pieces, which is not what I wanted. I actually wanted like mini figures. So I went ahead and changed it again. I said, great, but now make the people as Lego mini figures and the surrounding more Lego style and now it actually looks like it's built out of Lego. And then so on and so forth. I did for all the rest of them, Salvador Dall-e and the other ones. and when I asked it to create Van Gogh, it actually did a good job, but not incredible. So what I did in the end for the image that you've seen, I've actually uploaded an image of Van Gogh and I actually gave it as a sample. I said, make the brush strokes more prominent and more directional, like the attached image. So instead of it coming up with Van Gogh from its information in its background, I actually uploaded an image. I got a much better. Outcome that is aligned with what I was actually looking for. Why is this important? Because you can use this in any expression use that you want, whether you want to create something for fun, whether you want to create something for, holiday seasons, greetings for people. You send this to, whether you do this professionally and you need this for any campaign that you're running with your company. You can use any one of these things. And yes, people are asking, is that okay that they're using, actual people's, references and so on. That's a very big open-ended question. They do have some limitation on what styles it will and will not do from an IP protection perspective. I must admit that sometimes it actually blocks me in really weird situations that do not make any sense. And yet it does allow me to do things where it's things like this, like Van Gogh or Dall-e or Ghibli studio for that matter. So it's very open compared to previous models that existed before and it allows you to do more or less everything that you want. somebody asked Disney characters. Yes, it will do Disney characters. It will do, Simpsons it will do all of these things. Okay? The next use case is following brand guidelines. So now we're taking it to the next level and make it more professional. And I must admit, this absolutely blew my mind. So what we're looking at right now is two images side by side. One is a kinda like Spring Shoe sales for women by Walmart. The other one is from Target and none of them is real. And both of them is a hundred percent ai. And the way I created them is what shows the real power of these tools when it comes to understanding the chat and context and additional information for creating these images. So how did I create these two amazing images? What I did is I started. With a simple prompt that said you are an expert graphic designer. We are working on a partnership with Walmart. As a first step, I would like you to review their brand guidelines, and then I literally gave it a link to the document that has the Walmart detailed brand guidelines. And then I said, visit all the sub pages and learn their style guide in detail. Please create a short bullet point summary of what you found. So then it created a short summary of what is the style guide of Walmart. On the actual chat, and then I said, okay, great. Now I would like you to create an ad for new shoes sale for Spring. Using these guidelines, the ad should show two smiling female friends sitting on a bench with cool sandals. It is also. Professional product photography. The angle is looking upwards with their shoes in the middle of the frame. Intricate sandal details. Bright sunny day, blue sky in the park, Nikon Z seven Aperture, 4.5 50 millimeter lens. It is a Walmart a so use all the guidelines you learn previously and it created this amazing ad, like it's absolutely stunning and it looks as if a Walmart actually created this. All I wanted to do is I wanted them to wear dresses instead of long jeans because I think that will make the sandals stand out even more and it will look more spring like. So I said, okay, good start. Let's try having the girls wear spring dresses and sit with one leg over the other. This way it will show each of the girls, on the ground and one not. giving additional angles, so maybe basically showing the sandals in different angles. So that's what it created, and it looks amazing. Again, it looks like an ad and it looks perfect, and it has the Walmart logo and it follows all their brand guidelines on the type of text and how to add colors and things like that. there's again, another question. Does that violate any policies and so on? I don't think so. I'm just following their brand guidelines, and again, I'm not gonna pose this, but it's just showing it literally read their professionally produced brand guidelines, which are very detailed and learned how to follow it. Then I tried a different angle. I uploaded a PDF of the Target brand book. It's many pages of all their different details and I said, this is great. Now let's copy this ad to target. I attach target brand guidelines, please study them carefully and then recreate the ad by using Target's, brand guidelines, everything else should stay the same. And I got the same ad with the red background and the logo and this different font, with more spacing. Like it literally follows their brand guidelines. And it's just mind blowing to me how easy it is to do. I did not need a camera, I did not need the models. I could change what they're wearing. As you saw. I can change the sandals, I can do all these different things and create, At least inspiration for what the ads needs to be and show it to the relevant people and get approval before we actually get the models and do the actual photo shoot, or eliminate the photo shoot altogether. next one is infographics. So this is the first tool ever that can create long complex text accurately. So the next best thing that we had so far was, ideogram, or ideogram, depending on how you wanna pronounce it, which is a great tool that still knows how to create images with good text in them. But it will not create an infographic. You will not create a full page full of text. It will not create sophisticated diagrams accurately. And ChatGPT now will, now, this use case is actually really interesting, because what I did here is actually a much longer process than actually creating the. infographics that you see on the screen that has two different segments. and it talks about running AI agents safely on a virtual machine. So let's see what happened here. So what happened here is I'm now testing many different agents and to test the agents, I wanted not to run them on my computer because to be honest, I'm not a hundred percent sure what's going to happen. And so I wanted a safe environment to run this. So I did a deep research process on chat. GPT Deep research is an incredible way for you to find information and summaries information from hundreds of websites across the internet and. I did a completely different episode about this a few weeks ago that you can go back and listen. I compared all the different deep research tools and you can go and check it out. But what I said is the following, I'm looking for a safe way to run Manus and other AI agents on my Mac. It needs to be in a separate universe than all my regular applications and everything I use. The best option would be to run it on a remote server. The second best would be a parallel machine on my Mac. I am open to other suggestion and would like to know what are the pros and cons of the different options. how much would it cost, if anything, and what are the technical skills required to set it up? And then he went ahead and did the whole research. And then it gave me multiple different options where the best option after going back and forth multiple times and asking it about different options and so on. And again, those of you're not seeing the screen, I'm scrolling. Like it's a very long conversation that I had with it back and forth. And the best option came to be a. Virtual machine on Google Cloud. Now, I am a geek, but I'm not technical enough to do any of these things. So I literally asked it for step-by-step instructions and I followed its instructions. And in the beginning, I couldn't get it to work, and I went back and forth and eventually I was able to create a virtual machine. The whole process took me about half an hour, and now I have a virtual machine running on a Google Cloud where I can install and run all these agents. And if something goes south and goes terribly wrong, nothing happened to any of my environments. And so that's something worth doing on its own if you want experiment with agents. But what I did in the end of this very long conversation is I literally said, please create a beautiful infographics of this guide. Use the latest version of the conversation using Ubuntu operating system, which is the one I actually managed to get to work. use the attached brand guidelines, my brand guidelines in this particular case as the color scheme for the infographics, and use the multiply logo that is attached as a document as well. Start with, a background of what are agents, why is there a risk in using them and why this solution is even necessary. And then describe the steps that we have taken in order to create the environment. And now I have the ability to test Different agent platforms with zero risk and it created the infographics, which is incredible. It's clearly done. It follows exactly what I said. The text is perfect. It follows my brand guidelines and colors. It created icons for the different steps of the process. It's just absolutely amazing. And so that's unique. You can now create sophisticated infographics based on anything you want. Next inspiration from images. So I was trying to have fun, but I was also trying to have fun in a sophisticated way that will involve text and reproducing images with new text in them. So I found this image, actually, somebody sent me this image of a homeless guy that's holding a carton sign. He's standing in the middle of the street and the sign says, 16 wives, seven hungry dogs, three thin cats, 25 kids, and still horny. Please help with loose change. I find this really hilarious and a really smart guy, and I wanted to do the same thing and come up with other smart and funny things to write on these kind of signs. So I went to check GPT, uploaded the image, and I asked it to come up with new, funny. Things to write on a homeless sign, and then I ask it to apply it and recreate the image with the new thing. And it created this image that says, too ugly to strip, too honest, to steal, too sober for karaoke needs beer and therapy. Spare change. Question mark. Again, I find this to be incredible. if you look at the image, it's almost identical to the original one. It definitely follows the same kind of thing like he's standing in the middle of the road. The road has two sides, one with like stones and one paved. there's an old school BMW behind him. Like it looks very clear that it got the inspiration from the original image. It's not exactly the same, but you can recreate images with things that you wanna change in the image, including text in the image. Think about having the, billboards and Times Square saying what you want them to say. Stuff like that is now possible, which just one prompt. Sean said that he's still waiting to be wowed by AI humor. Overall, I think it's getting better. I think this is actually not bad. but let's continue. So number eight, which is actually a fail for me, but I saw people do really good job with that, which is professional headshots. So what I did is I actually uploaded several images of me from different angles and I asked it to create professional headshots of me. I asked for one that is, with a t-shirt, the same t-shirt that I'm wearing right now. My multiply, t-shirt and then one wearing a suit. And the reason it's a fail, the actual professional headshots looks amazing. It just doesn't look like me, which is the whole point of this. But I saw other people online do this and get much better results. So I don't know if it's my, face that is not easy to reproduce, but it's worth you knowing that this is an option. So let me show you how this is done. So let's go into ChatGPT. And see the process that I did here. so the process started with me uploading several different images, front two sides and back, images of me that I just took with my phone. And then I wrote, you are the world's best headshot photographer. You have 20 years of experience in capturing the essence and glamor of people and making them look amazing in headshots. As a first step, I would like you to look at the different angles of this person and describe him in as much detail as possible. Include things like the aspect ratio of his face, the shape of his nose, the direction of his eyebrows, the color of his eyes, et cetera, et cetera. Try to create as detailed as possible description of this person so you can replicate it later. And you can see this is a recurring theme. What I found is when you ask it to describe things in details, it actually does better afterwards. We've done with the text, and I'm doing this now with. Myself. And then it created a very detailed description including, general structure, facial features, eyes, nose, mouth, ears, skin tone and texture, hair, all of that kind of stuff. it's pretty long and very detailed. And then I uploaded my logo so it can capture it and put it on the shirt more accurately than just grabbing it from the image that it had, and I wrote the following. Now let's try to create the first headshot. Let's start with the same T-shirt that I'm wearing with the same company logo. I'm also attaching the company logo itself for you to copy. and I want it to look like a professional headshot, but wearing the t-shirt I'm wearing in the original image. Try to capture all the details you mentioned above as well. And it created the image. And again, it's a great headshot. It just doesn't look exactly like me. it looks somewhat like me and it has a lot of the features, but it doesn't look like me. And then I ask it to change it to a professional. With a suit and tie and he did that and I replaced the tie and I tried different things. none of them actually came up looking like me, but the clothing change actually works very well. So worth trying. If you need professional headshots, I will say something else, I assume, and it is very likely that if instead of trying twice, I will try 20 times. One of them will actually look like me and then I'm done and it's gonna save me the time and the money of actually going and getting professional headshots. So it's worth trying 20, 30 times. It's still gonna be a lot cheaper and a lot less time than actually getting a professional photo shoot. And because I have uploaded multiple angles of me, I will be able to get like a 45 degree thing. I will be able to get it for my passport if I need to instead of paying$25 at CVS, and all these kind of things. So if you manage to do it, it's actually very helpful. Let's move on. Number nine. This one is really one of my favorites because it really blew my mind, which is combining images. So what I did, and again, I was just experimenting with different ways I can use this in a business context perspective. So what I did is I took an image of a basketball player holding a basketball with a dark background and he has a very serious face on it. And I was starting to think what would be completely out of place to put in his hands instead of the basketball. So I took a very fancy, very kids friendly cake that has lots of sprinkles on it and colorful, candles and so on, and I asked it to combine the two, and I created the image of the basketball player with the dark background, with his really tough face holding the cake. And it looks amazing, and it looks almost exactly like the original cake. So let me show you again. This was literally just one prompt. And so what I did is I've, uploaded the two images, so the image of the basketball player from the internet, the image of the cake from the internet, and I said, please have the basketball player hold the cake instead of the basketball. Try to make the cake as identical to the original image. I attached. And as you can see, if we zoom in a little bit, you can see that it even captured like it's not regular sprinkles that on this cake, like they have these weird shapes. it captured the drip of the chocolate. It captured the colors of the candles, it captured the actual plate color, like it's almost the same exact cake. And it's just amazing that it knows how to combine these two images together because it understands what I'm asking. And again, that's something that doesn't exist in the regular image generators. let's move on. I'm just reading some of the comments. Somebody else says it did work for them. Either like professional headshot. for some people it works. For some people it doesn't. I think again, with a lot of trial and error, you can probably make it work. So product placement, this one is another big one. This is an actual client of mine and they have this product that is called I Port, which allows you to put a. iPad in a stand that can be placed in different places, it can be removed from that. It's detachable. It has a lot of really cool features, but to create images of it in different scenarios so they can sell it to different kinds of client. they need to actually take the product and place it in the place and take pictures. not anymore. What I did is I uploaded several images of the product into ChatGPT, and then I just described the background that I wanted. So let's go and take a look at what I did in ChatGPT. So scrolling up, you're an expert product marketing photographer and designer. We are about to work together on a project, for a product called I Port. You can learn about it here, and I actually gave it a link to the website. I want you to review all the product pages on this site and let me know what you can learn about the product. And I'm doing this again because if it understands what the product is, it will have an easier life of actually generating the outcome that it needs to generate. Again, a huge benefit that just an image generator doesn't have. So it provided all this information. And then I said, okay, great. we're going to focus on mounted iPad product. Here are a few images, that I want you to look at. And I uploaded multiple images. I also attached the logo so it knows how the logo looks like, and then I ask it to, give me a description. Again, I did the description of what it looks like from different angles in different directions and everything. So it came with shape and structure, color and finishes, design details, functionality, usage, angles observed, and a summary. So again, a detailed description of the product. I asked it for some additional information and then I went to create the first image. I would like you to create a promotional product, photography image of an port on a counter at Starbucks. The shot is from the barista side. Looking into the restaurant, the barista fingers are operating, the iPad mounted on the port. There are happy customers in line waiting in order for their drinks. The airport needs to be in high resolution and the focus of the image, and it created the image. And it's amazing. It's exactly everything that I asked for. And creating that image with a camera would've taken. Taking over a Starbucks and having a professional photographer and having actors to be there and stand in line and take all these pictures and then pick one. And here's just one prompt. And then I created all the other images that you can see in this image with any scenario in an office building with a glossy table on the wall, like whatever. I actually want interior or exterior design. This is another amazing use case. And what on the left is an actual backyard. It's real, it's an actual building and you can see that the yard looks nothing exciting. but what we did is we literally ask it to give it some life and suggest new designs for that backyard. And it created these different variations that look really inviting and warm and something I would love to have, myself, but it kept the exact aspect ratio and the size and the wall and the window, everything from the original actual yard in the image, just changing the design of it. And you can do the same thing for interior design as well. So let's see, what are the prompts over here? So again, uploading the image of the backyard. And then I said, recommend a cozy backyard. I want to have one tree in the corner. And then he just recommended all the things that can happen. And then he asked me questions, would you like to, visualize this? but yes, not too much trees. I want, to reduce the amount of maintenance. So it reduced the amount of trees in the description. And then we asked for it to create the photo, and it created the photo, and then we asked for other stuff and created more variations of it. this work was done by Joyce, my amazing assistant for an actual house. so this is incredible. And you can do the same thing for interior design and ask for recommendations or ask it to show the sofa that you considering buying in your living room and stuff like that. And it will do that as well. It's a really amazing use case to get inspiration or to actually do the design that you want to do. Number 12, changing angles. So this is somewhat related to what we did before, but what I wanna show is how amazing this tool's ability to understand what it's actually looking at. So again, different than an image generator that generates an image and that's it. This actually understands what you're creating. So on the left you can see an image of a room. By the way, created with AI on the right is a top down view. So the first image on the left is looking into the room from eye level. The second image is looking top down into the room from like the corner where the wall meets the ceiling and it's looking into the room and you can see how accurately it actually captures all the details. Now it's not a hundred percent, but it's close enough that it could have been used as a game for kids to find the differences because the sofa is the same sofa, the cushions are the same cushions, that chairs are the same chairs. The table is not exactly the same, but it's almost the same. It even captured the two rugs on the floor that are overlaid one on top of the other and the curtains and the lighting and the window and the plants. Like it captured all these details and just created it from a different angle. Why is that helpful?'cause you can use this again when you're doing design and you wanna see how will this look like from a different angle. If you want to think about a product from different angles and use your product and show it in different angles in different situations, you can do that as well. and again, this, by the way, the. very simple prompt to go from one to the other. So I will show you that very quickly. this is the first image, and then the second image literally said, show me the rest of the room from a bird's eye view. That's it. And it gave this incredible outcome of the room from a completely different angle. Next one is user generated content, also known as UGC. And this is another thing that's gonna change an entire industry because brands can now quote unquote fake UGC. Now, previously brand did this anyway, but they actually had to pay people to do this and hire people to do that. And now you don't need to. So what in the image on the left, again, is a low resolution image of a cream that I took off the internet. And on the two images of the right, you see a young girl. Holding the product. I ask it to not to look not professional in one of them, she's just holding the product and smiling as if she's talking about it. On the other hand, she has a little bit of cream on her face. Totally looks like something she took as a selfie with her cell phone. And I did that on purpose in order to make it look like UGC. And I don't have the link for that one. but literally all I did is I followed the same process that I described before I asked it to. Tell me what is the text on the product. So then it shows up accurately when I render it again, and then I ask it to create a user generated content style image of a young girl holding the product as if it's user generated, as if she shot it as a selfie with her phone. And now I can create as many versions of this that I want until there's a few that I like, and then I can use it for whatever I want. By the way, the next step beyond that, which we're not gonna do in this session, but you can definitely do, is you can now use this image. And upload it to a tool that also knows how to create video. And then you can have a video of this girl talking about your product when the girl doesn't exist, and the product in the image exists, but not in an actual image. This is, generated by ai. So you can create user generated content, including videos, including voice, including making it look completely realistic as if a person shot it with their phone. And you can do that in seconds, in multiple people, in multiple places around the world, in any language that you want with every kind of person, all young, female, male, different ethnicities, et cetera. All of that with one simple prompt. Number 14 blew my mind because it combines a lot of the things that we have done before. So let's see what's going on here on number 14, first of all. I've followed the entire design process. Several of my clients are apparel brands, some of them for adults, some of them for babies, with different kinds, with different styles. some of them just do t-shirts of multiple brands and so on because they have the licensing to do that. But so different companies that do different things. And what I tried to do here is I try to follow the entire design process. So I started with a mood board on the left, and then using the mood board, I created graphics that can go on onesies. And then I uploaded, what on top here is a 2D flat image, of a onesie. So it's not an actual image, it's just like the graphic design, which is how designers actually work when they create these designs. And from. Me giving it to it, plus the combination of the first few steps. It created the design on the onesie as a flat graphics, and then I ask it to put it on an actual baby. And it did. Now, I'll show you the prompt in a second, but what I wanna show you that is really incredible here is if I zoom in on the actual onesie that I uploaded, the flat graphics one, you will see how the stitches look like, how the overlay of the shoulders and the neck opening work, so you can slip the baby's head through it. you can see the buttons on the bottom and the stitching on the bottom. On the original image and it captured all of that in the design that it created as the graphics, as well as in the actual product it put on the baby. So all of this is mind blowing. This process takes professional companies weeks to do with multiple people, and now ChatGPT can do it in matter of minutes. So let's see how this process works. So I started with you're an expert clothing designer at Gerber Children's Wear. As a first step, I would like you to do a quick research on the company and its design guidelines. Get back to me with a summary of what you find so we can establish a baseline of what are good designs in Gerber. And then it came back again with core values and product categories and material. Choices and design guidelines, color palettes, pattern graphics, functionality, key takeaways, like all of that, it did just by me asking it to do it. And again, I do this because if it has more context, it is gonna generate better results that are aligned with what I need. And I see now that there's a lot of people writing, so I, I apologize for missing some of the, comments. I will get to it in a second. So then I said, great. I need your assistant in planning the next round of onesies design. As a first step, I would like you to create a mood board, that will connect us from the spring season we're in right now with its beautiful seasons, blue skies, warmer weather, two clothing of babies and household environment. And then it created this description of what it thinks it needs to be, the color palette, the texture materials, the motives and patterns, the design elements, the nursery inspiration, and then it gave me other examples, and then I selected one and it dove into the details of what this one should be. from the three different options that it gave me. And then I said, okay, great. Now let's create the mood board itself. And it created this amazing mood board that has everything that I asked for. It has the color palette, it has some of the designs. It actually looks like a board with two onesies hanging on it, or three in different sizes. And the templates and even the nursery theme that I ask it, there's like a crib and the skies and so on. All looks amazingly professional. And then I said, okay, I really like the board. And also really like the colors you picked. I would like you to create more designs in the styles of the balloons and the rainbows and the sun behind the clouds, which is some of the things that appeared in the mood board. And just create patterns that we can later on use and add on onesies. So it gave me multiple options. And then I uploaded this, right? I uploaded a image from the internet of a. Design diagram of a onesie chose the back and the front in just lines. And then it said, I would like you to use the image I attached as a reference. This is how we create designs. So using 2D variation of a onesie. so please use the exact one I've used. Just change the color of it to a color from the palette, that you created and just apply one of the designs. Remember, this is the front and the back. So the image I uploaded has the front and back of the onesie, but I also need the front in this particular case. So I ask you just to create the front, and I ask it to create one with the sun hiding behind the clouds because I like that pattern. And it created this incredible design that follows everything I requested that can be used professionally right now. And then all I did is say, this is fantastic. Great work. Now let's do the next step. I would like you to create a photorealistic photo shoot style version of this with a baby wearing it as he's smiling and standing in his crib and it created this image. This is mind blowing again. This process would've taken weeks to a professional design team and now takes minutes using cha GPT. Let's go back to the presentation. Number 15 is just for fun. Many of you have seen that, but it still blows me away that this is doable. so you can do a lot of fun things. In this particular case, the big craze after the Ghibli style anime thing was action figures. So again, this, Joyce created this, her son is really, both her kids are actually really into TaeKwonDo. And to surprise him, she took an image of him wearing his TaeKwonDo clothes and created this action figure package for him. And I find this. really fun and mind blowing how accurate it captures her son's details, as well as the whole TaeKwonDo gear and everything. So how is this done? Very simple way. In the similar process, we've done everything else. So if I scroll back, she upload his image, and she said, create image. create a toy of the person in the photo. Let it be an action figure. Next to the figure, there should be the toy's, equipment, each of the individual blisters, a TaeKwonDo helmet, a pair of shift gloves, TaeKwonDo armor, et cetera, et cetera. Describe what needs to be there. And it created this really cool and fun image summary this tool literally changes everything we know about how. You can use AI to create visual aids for anything from PowerPoint presentations to ads including text, infographics, fun stuff, final design, steps in the design, in the professional design process, interior design, exterior design, all the things that we did in minutes. And the biggest benefit is that it understands the context of what you're actually trying to create. And if it doesn't, you can continue the conversation, which again is something you cannot do in just image generation. Tools like Mid Journey and Dall-e and Stable Diffusion. If you haven't played with it, just go ahead and play with it. It takes a while to create each and every one of the images. It takes a minute to two minutes, sometimes five, to create the images. You can ask for different aspect ratios, but start just by having fun and then start thinking about what business use cases you can apply this to. I can guarantee you that if you have any need to do any kind of design when you are in your work, whether this is your actual work, you're a graphic designer, or you're not a graphic designer, but you are now can do this in your work either to get inspiration to give to your design team, and you can very quickly get to a very solid draft that they can then perfect. Instead of explaining to them what they need to create, you can actually show them in seconds or even if you're the CEO of the company or the head of something or somebody in product and you wanna be able to do all these things, you can now do it in minutes in chat, GPT. That's it. I remind you about the course. If you wanna learn more stuff like that across everything that AI can do, come join us on May 12th. You can look for the link in the show notes. For those of you who have joined us live, thank you so much for spending the time with us. There's multiple people on LinkedIn right now, from multiple places and multiple people on the Zoom. I appreciate every single one of you. I know you can do other stuff on Thursday afternoon with your time, and so I really appreciate you being here and joining us. Those of you who haven't join us, you can come join us. We do this every Thursday at noon, going into details like we did today on a specific business related AI use case that you can learn how to implement in your business today. So come join us live. We also do the Friday AI hangouts every Friday at 1:00 PM where it's just open. Ask me anything kind of environment. Everybody participates and bring use cases, and you can come and join us for those as well. That's it for today. Have an awesome rest of your day.

People on this episode

Head Shot

Isar Meitis

Host