The Startup Ideas Podcast - Google's Nano Banana is an INSANE AI Image Editor (FULL Demo)

Episode Date: August 27, 2025

Join me as I chat with Logan Kilpatrick about Google's new Gemini 2.5 Flash Image model (Nano Banana), he showcases its capabilities for image generation and editing. We explore practical applications including creating marketing assets, product placement, and interactive experiences, all accessible through Google's AI Studio platform. The conversation highlights both the technical capabilities and business opportunities for developers or vibe coders to build innovative products with this technology. Timestamps: 00:00 - Intro 02:34 - Nano Banana Overview 04:55 - Demo of AI-generated product ads 10:06 - Demo of Social Assets 11:41 - Demo AI-Generated Mockup Generator 15:05 - How to edit image with prompting 18:45 - Best Practices for Prompting 21:18 - Product placement demonstration 23:04 Three Levels of Using the Model 25:54 - Why you should start using Nano Banana now Try Nano Banana: https://startup-ideas-pod.link/nano-banana Key Points: • Logan Kilpatrick demonstrates Google's new Gemini 2.5 Flash Image model (nicknamed "Nano Banana") • The model excels at fast image generation and editing with impressive quality at low cost (about 4 cents per image) • Multiple product applications are showcased including ad creation, image editing, and interactive experiences • AI Studio provides free access to experiment with the model through chat and pre-built applications • Developers can "vibe code" custom applications using the model's capabilities The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ Boringmarketing - Vibe Marketing for Companies: boringmarketing.com  The Vibe Marketer - Join the Community and Learn: thevibemarketer.com Startup Empire - a membership for builders who want to build cash-flowing businesses https://www.skool.com/startupempire/about FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg  Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND LOGAN ON SOCIAL X/Twitter: https://x.com/OfficialLoganK  Youtube: https://www.youtube.com/@LoganKilpatrickYT  LinkedIn: https://www.linkedin.com/in/logankilpatrick/

I'll say it. Nano banana, Google's new image model, is the best image model to ever exist. It's what we all wanted out of an image model. You can place products, you can keep characters consistent, you can change scenes, you can edit specific parts with full control. It's basically like Photoshop, except you don't need to hire someone to go and edit. You just use plain language. So I brought on Logan Kilpatrick, who works at Google, who's senior at Google on the AI team,

to give us a tutorial with how to get the most out of it. And it's important to me that I brought them on because I think that there's going to be a lot of people who make a lot of money from this specific model. They're going to be able to create content that's scroll stopping from this model. They're going to be able to create ads that convert from this model. They're going to be able to create SaaS startups using nanobanana.

You need to watch this episode. This is an incredible demonstration. of a new technology, and I can't wait to hear what you think. Logan Kilpatrick on the podcast, what are we going to talk about today? Greg, I'm excited. We're talking about nano-banana, aka Gemini 2.5 Flash Image, which is our new Gemini state-of-the-art image generation and specifically image editing model, which folks are loving and no pun intended going bananas for right now.

So I was hoping we could just see a bunch of examples of the model in action. we could actually build some stuff live and like vibe code something and show people like what are the actual product applications, what are the types of companies and things that you could build around this new model. By the end of this episode, what are some tangible things that people are going to get out of it? Yeah. Hopefully you'll see like what are the models capabilities. What does it actually work really well at? And hopefully like what are like five or six different ideas of how you might actually bring this model in and start building a product or integrate into your existing product. build a new product around this model and put it in production. Beautiful. Let's let's go.

Awesome. Maybe I can share a screen really quick and we can just look at some basic examples. Let me pull up a tab of AI Studio and we'll see the model in action. So you can use them all for free. It's on AI Studio. If you haven't used AI Studio before, it's our platform for developers and AI builders to go and try a bunch of things. you'll land in this experience.

You'll see if you're a normal AI Studio user and you've used the product before, we just landed a bunch of other updates. We'll talk about that some other time. The fun thing and the cool thing is we have the sort of two Gemini Native image experiences. One at this top level when you land, you can just do a bunch of prompting.

There's the model drop down to the right hand side here and you can ask the model to do a bunch of silly, goofy stuff. I'll make a quick comment, which is like the speed of this model is something to think about. Like there's a lot of these like editing experiences or these generation experiences that you can't usually build just because like it takes 45 seconds and like our user is really going to sit there and wait while the thing is generating. So there's like there's an interesting like product edge angle that you can have around just how fast this model is. It's also only like I think it's like roughly four cents for an image to be generated too. so it's like, you know, you can let people go wild and you're not going to break the bank, which is really great.

It's like a thousand images is 40 bucks. So this is the basic experience. The cool stuff is in this build tab here, which we don't talk a ton about, but it showcases a bunch of these like demo apps and shows the new model capability, nano banana actually in action and in practice. So we've got options, Greg. you want to look at. We could try this like image filtering use case, which is really, or this like live Gemini, I think it's called like Gem booth or something like that. This could be an interesting

one where you can like take a picture and use, you know, some, a bunch of these different filters and it'll it'll showcase all these things in action. We could try building something live. What are you, where's your head at? We were talking off camera about, yeah, interesting. We were talking off camera about like creating marketing copy and stuff like that is like a is something marketing like imagery is something that could be potentially interesting. So I'm happy to go in whatever direction you think is most fun. Yeah. I mean, I think when new models drop, I'm always interested in, you know, how can this give me

an unfair advantage either from building a product or using this for a marketing asset to get more customers. So on the marketing side, like, you know, Yeah, here we go. AI ads. AI ads are where it's at. So I built this literally as we were sitting here talking off camera about sort of being able to drop in a product picture and then turn it into a bunch of different ad formats.

So here when you upload, I'll go and upload an image and I'll take the new picture of the Google Pixel 10. And then this is completely vibe coded. You can see this is literally one shot as well. You can see my prompt in the top left hand corner. And so we have a bunch of different things now so we can do like a luxury magazine spread or a subway interior. I actually, could we do subway interior ad just because I see like the notion ads all the time and they're showing them in the subways. And I'm always envious of the notion people for doing that. So maybe we could try that one.

Let's do it. Awesome. And let's see. And so this takes the, there's a prompt behind the scenes. It takes the image of the Google Pixel 10 and hopefully we'll see it in a subway. Awesome. I feel like it's reasonable that you might actually see something like this in an actual subway somewhere. This doesn't look that fun of a subway, but the pixel is shining in this example.

So maybe we'll try one more. And then actually, I've got an idea for remixing this, which I think could be really cool. So maybe we'll try. Sam Altman, the co-founder of OpenAI, just said that it is the era of the idea. idea guy and he is not wrong. I think that right now is an incredible time to be building a startup. And if you listen to this podcast, chances are you think so too. Now, I think that you can look at trends to basically figure out what are the startup ideas you should be building. So that's exactly why I built ideabrowser.com. Every single day, you're going to get a free startup idea

in your inbox and it's all backed by high quality data trends. How we do it, people always ask. We use AI agents to go and search, what are people looking for, and what are they screaming for in terms of products that you should be building? And then we hand it on a silver platter for you to go check out. We do have a few paid plans that take it to the next level, give you more ideas, give you more AI agents and more,

almost like a chatGVT for ideas with it. But you can start for free, ideabrowser.com. And if you're listening to this, I highly recommend it. I feel like this is a little bit edgier, but an urban mural ad. I feel like mural ads, I always look at murals

because they don't feel like advertising. So there could be something, there could be something interesting, which I really like. This is actually cool. That's cool. Companies did this. That's really cool.

Yeah. And this is the type of thing that you can put on social. Like if you're not Google and you're a team of 20 people or even less, like you can put this on Google. I'm sorry, you can put this on X or something.

or Instagram and people be like, whoa, like, where's this mural? I love it. And then it actually creates this flywheel where you're like, wait, maybe we should actually do a mural in real life. Like, this is kind of sick. So what I like about this is just like how well the model like fuses this onto an actual like real world setting. I think the thing that's missing is in this example, like I have a picture of my product

that I want to generate ads for. and in this case it's the Google Pixel 10. But it's missing like the, I know it's the pixel because there was just some event that happened and I watched it, but someone walking by this might not actually know. So you're kind of missing the like marketing tagline or like some additional context.

So I'm actually going to ask the model to like add that in as part of it and we'll use the model's native capability to like embed that text into the actual ad that it's creating itself. So I'll try to come up with a, coherent prompt for this on the fly, which is something like, okay, this is great. However, I want to add in a marketing, and this is maybe a bad example. You probably don't want like a marketing slogan, but we'll say you want to add a marketing slogan to the image itself in text. So that when people see the ad,

they don't just see the product. They also see the marketing slogan to make it so I can manually add this UI or optionally let the model make one up for me. Even better. Yeah, I'm like, I don't want to come up with marketing slogans. Let the AI do the work for me. That's what I'm paying tokens for. So maybe while we look at that one, I'll show just like another example that I was messing around earlier today and was inspired by a show on X and was seeing their like social assets that they're putting out. And this example that I did was I took a social asset that another that TBPN had created.

And I basically vibe coded an app in a single prompt to say like, hey, based on this asset, make me, you know, be inspired by this theme and this style to like help me make assets that are something like that. So this was inspired by the Taylor Swift engaged one. If anyone saw that on X today that the folks at TBPN put out. But so I'll do Logan Kilpatrick shipped, uh, nano banana. And we'll generate this. And this will make me a couple of like cool social assets in the theme of the TBPN. So you could go in and change this theme with whatever. Like Greg, I don't know if you have like a bespoke social asset character that you really like. But literally all of this is 100% vibe coded. This is using the model behind the scenes.

And it's actually like generating these assets and like dramatically makes it easier. If you have like a consistent style as a brand or as a company and you're producing these types of social assets, you can get lots of like cool content remix by using this model and like building your own generator to do this as well. Yeah, and I think, you know, why this is interesting and what to me at least is, you know, social content is about scroll stopping content. And yes, you can put that image of you, which is a beautiful image. You look great. Thank you. But, you know, there's there's something about that extra layer of wrapping it in a story that gets you more awareness within the algorithms, gets you more likes, gets you more replies,

which helps ultimately get more customers to whatever it is you're doing, get more brand awareness. So I think that in the past, what did you have to do to do this? You had to hire someone who understood Photoshop maybe, right? You know, now you could just do yourself. Yeah. And I think there's another layer of this. And I think about this a lot, which is like, what has, happens when you as the person who, like, has a story to tell or like some idea, you have to,

like, put it through this translation layer, especially when the translation layer is sometimes like a, you know, a bunch of people or something like that. You lose a little bit of the fidelity of the story. And that's why this like whole AI assisted tools to help you is great, because like I get to iterate on this idea and make sure that the tool that I'm using is like actually telling the same story that I'm telling from a fidelity standpoint. So I love this example. I'm curious to see the other vibe-coded, the mocks, where we are with the mocks. So I'll go back and I'll put in this pixel and we'll see. Okay, so I'll let it come up with the slogan and hopefully it's not horrible. Hopefully it's not horrible. And maybe

there are ads and co-working spaces, maybe apparently cafe product placement. Curious. Any of these stand out to you as interesting places. I mean, luxury. magazine spread to me is actually the most interesting. Let's try it. Let's try it. I don't know if there's any luxury magazines out there that people still buy, but we'll find out what it looks like when the pixel with ideally an AI slogan shows up. Um, let's say. Okay, created, crafted for tomorrow, inspired by you. I like that. That's pretty good. That's actually, that's actually pretty, like, subversive and it's actually good. Like, it says nothing, but says a lot at the same time, which is kind of what you want. Yeah, that is great. Hold on. I want to try one more just because I'm sort of inspired by

what slogans we're going to come up with. Any of these other ones seem interesting. I kind of like the vibe of the rainy bus stop ad, but I don't know how effective bus stop ads are. Yeah, I don't know. I don't know. We'll try it. Let's see. Yeah, let's try. I also wonder if it's like taking the context of the bus stop ad to then come up with the slogan. Like, are you going to, is it going to give us like a water resistance story or something like that. No slogan, but we did get an AI generated Google logo, which I guess that's the slogan in and of itself is it's Google. We're selling a pixel. Well, I wonder how intentional the model was about that effort. It's just missing the point. Either way, I love this example. I think there's definitely something here to

push on and it showcases the model's capability in action, which is awesome. What if you like, Okay, so let's just say you wanted to edit this image. Like, how do you actually edit it from here with natural language? Yeah, that's a great example. So in this experience that we're in right now, I think it's kind of hard. But let me actually just like take the image out of here and then we'll go into another example. So you could either, you have two choices. We could either just like go back to the main chat UI.

And I could dump the image in and start doing a bunch of stuff. So we could try that first actually. and we'll see, so maybe I say, make me a slogan, or let's do, add the slogan, pixel, the phone for AI nerds. I don't know. I'm sure the pixel people won't appreciate it, but add the slogan pixel, the phone for AI nerds under the image of the pixel. And let's see what it comes up with. So this is the most lightweight version of this where you could come and do this. I do think there's something for like you want to have a little bit more like product scaffolding around this to kind of help you if you wanted to like, you know, have a paintbrush to like highlight something or circle an area. Like none of that exists in this default experience, but you can build all those things bespoke in that build tab that we were in before.

You just need to like prompt and say like now add a bunch of like creative tools. And we actually have an example of this as well. But if we look at this, pixel, the phone for AI nerds, it looks great. I feel like that's like a reasonable outcome. 100%. Yeah, I'll show you this other example, too. We can see what it would have been like. We can go to this Pixshop photo editor example.

So I'll upload. Actually, I'm going to upload the picture of, yes, this one. And then so we have a bunch of different options here. So we could try filters. This is, again, this is like a vibe-coded pre-built set of different filters or like tools that you might want. So you can like retouch, click and area of the image to make a precise edit. So I could say, let me see if that actually works. I can say remove the Google logo from here.

Let's see if it works. This is vibe coded. So, you know, batteries included, but also sometimes the batteries are in the wrong position. So we need to not. Okay, awesome. It actually works. And it did hallucinate a little bit and end up removing the logo from the middle of the phone. But I think generally gets out like you get these like creative tools out of the box, which is pretty cool.

That's awesome. Yeah, I want to try a filter as well. And again, we could change this to say, like, hey, here are the 10 filters I want or come up with 10 filters or come up with, you know, a way to like add a text box to it or something like that. So there's like all this like infinite content customization. And I will make another note that all of this experience that we've looked at so far is completely free. So you can do all this like, you know, ideally you build a great product with this and you end up using the Gemini API and all that stuff. But like you don't, you don't necessarily need to. The experience is free.

there's no gotcha. You can come in and play around with all this stuff and vibe code at all and try out the models and it doesn't cost anything, which is awesome. Is there any best practices in terms of prompting to get the most out of the product? Yeah, it's a great question. I think there's, and I don't know if I'll just

throw another example up on the board or on the screen as we talk through this. I think some of the limitations are around, the complexity of what happens when you do like multi-turn, when you ask for lots of edits in a single turn. I think the best way to do this is to be like very precise single-turn edits. The model is capable of like doing multiple things in a single turn if you're, if you give precise enough instructions.

But I think it oftentimes like kind of loses the gist of what you were trying to say if you like layer multiple instructions together. it is it is also like it's worth noting this model is powered by the the same Gemini 2.5 flash model that like we released earlier this year so it does have a lot of world knowledge so you you should assume it is like a smart creative partner in many ways but just like any other if anyone's ever done like uh worked with like a random you know sort of creative uh contractor on the internet like you oftentimes don't get i just went through this recently where i like wanted someone to design a bunch of teaching shirts for me. And I had sent them a bunch of stuff and I got the, I got the results back. And I was like, yeah, this isn't what I wanted. And then I went back and looked at what I said. And it was like, oh, yeah, it's very clear that I gave bad instructions, which is why I'm not happy with what the outcome was. So I do think that the same story applies to this, which is like be precise about what you want. Try to block these into like small, as small like multi-step

edits as possible. The model doesn't like the image quality doesn't get. worse as you like do a multi-turn edit. So like you don't need to get everything right on the first edit. So all that's possible. And this example that I just pulled up is like another really cool one, which is like AI home design. I think is this like huge ecosystem. I just was helping my girlfriend decide what colorblind she wanted inside of her office. And it was like a great, we were like, I don't know. Like is there a app that's going to do this? I was like, I don't know. We'll just make one right now. And it literally took 30 seconds. And then we took in an image. And then she literally scrolled through all 37 different flavors of the color green for what her blinds might or her curtains

might look like. And she was like, that's the one I want, straight on to, you know, onto Amazon to go and buy those curtains. So it was so much possible with this. Can we see how this works? Yeah, this is a great example. So if we upload the, if we upload a scene and I need to go and like find a good one. Let me see. So this is a picture of Demis and I talking. and I will upload a product now. And we'll do this. This is kind of a contrived example because I don't have a bunch of good. I don't have a bunch of good examples nearby.

But let's see what happens. So the product, this is actually a really good example of, assuming it works. This is a great example of like the models world knowledge coming into play. So we have the scene on the right, which is Demis and I sitting in some chairs in the library in London. The product on the left is actually the. ad that we generated before using AI. And the interesting thing is there's, like, other stuff visible in this image. So there's, you know, a car and a bunch of people and umbrellas and a bus stop.

So, like, the model has to make some assumptions about, like, what is the actual product that the user is asking for? So if we go and drag this over, let's see what happens. hopefully it does something reasonable with this. And I actually also realize that I'm supposed to draw the, oh, that's actually great. So I drag this image over and it took the screenshot or didn't. That's amazing. Yeah, it took the image and it, like set it on this little table that was sitting between Demis and I.

And now there's like a little product placement for the pixel 10 that was pulled out of this broader image that we had just created. That's crazy, dude. Yeah. I mean, there's so much possible of what you can do with this stuff. I think, and that's, I mean, just to opine on this point of like why we have this experience that, like, lets you interactively see. Because it's like seeing is believing. Like, I think you can like, the like chat experience is cool. But like sometimes it like gets my gears turning in a different way to like see the experience like come to life in this way of like interactively interfacing with the models.

beyond just chatting with them, I think lands the point of just how capable the models are in a bunch of these different contexts. Yeah, to me, what I'm hearing from you, and correct me if I'm wrong, is there's almost like three levels of playing with the models. One is just to use chat. That's like level one, the simplest way. Anyone can get started. Chat, understand how it works. Level two is going in the build tab and seeing some pre-created vibe coded apps that you can go and use and create some value with. And then, you know, once you get a little, uh, used to that, then it's like, okay, I understand what this, maybe the home canvas thing does, but there's some limitations for whatever my use case is. Therefore, I want to create some, you know,

personal software based on my needs. And then that's probably where most, in my opinion, that's where most of the unlock for the people listening to this show, founders, business builders, are going to get building their own vibe coded apps using some of these models. Yeah, 100%. And then like when you, the, you know, you have all the controls that you need. When you go and like do your vibe coded app, like if you want to just like go and deploy it and share it with a bunch of people or move it over to GitHub or download the code and like move it to a cursor and like keep vibe coding with it or like whatever your flow is,

you should be able to like continue on with that experience. It doesn't need to stop in AI Studio. Like we've designed it so that it shouldn't stop an AI studio. as you do. You should be able to go and use whatever tools you want, build in whatever ecosystem you want. But we want to help you get started. And I think this is, hopefully this is helpful. We're also, I was talking to our team earlier today. Like, we're very early in this story. So as much grace as you can give us in this experience, there will be rough edges, send us the feedback. We've got a ton of stuff coming in the next few months. And also a ton more coming on like models like

Nano Banana, which is exciting. So hopefully, hopefully we'll see more progress. And if there's examples that don't work well and there's like things you wish the model could do for your use case, like please my emails on the internet, go and send me an email. Like those are the best emails of like, I'm trying to build this crazy product. It's not possible today. It doesn't work. I wish the model could do X, Y, and Z thing. Like we'd love to help make the model work for whatever products people are trying to build. And before we sign off, you know, why should someone play with Nano Banana today and not in six, you know, not the next model in three, six months?

Like why log into Google AI Studio today and start playing with it? Yeah, I think there's this, there's this competitive advantage piece, which is like there's, you know, the number of people who know that this model exists and are building things with it is rather limited. So if you're sort of early to the wave of creating the product experiences around this, I think like my broad take is there's a huge amount of consumer interest in this type of use case. And if you look at like what products are available to actually like serve customers who are interested in this, it's like pretty limited.

It's probably like a handful of products that actually exist. So if you build something and are thoughtful about it and get into the hands of people, I think you're going to have this like holy crap experience from a lot of your users that they just haven't experienced something like this before. If you show the average person on the street that this is possible, it's going to blow their mind. So I think there's some urgency to build that experience because lots of folks are going to try. All right. I believe it. Logan, thanks for coming on the show. We're going to have to have you back when new stuff comes out, which seems like you guys are shipping like crazy. So I bet that sooner than later.

Please, please comment if you'd like Logan to come back. and if you enjoyed this episode and like this video, if you want more of this in your feed, I'll include links to follow Logan on his social, you know, on social, and we'll include a link to get going on Google AI Studio. AI.studio slash banana. You can try the model out AI.com.

Studio slash apps if you want to go and build and see all the stuff that we've built. So hopefully the links may get super simple for folks to get started. Super simple. Thanks, man. I appreciate you. I love it. See ya.