# NEW Nano Banana + N8N is INSANE (FREE Template) 🍌

## Метаданные

- **Канал:** Julian Goldie SEO
- **YouTube:** https://www.youtube.com/watch?v=7wsgCRpGq1k
- **Дата:** 30.08.2025
- **Длительность:** 31:11
- **Просмотры:** 5,912
- **Источник:** https://ekstraktznaniy.ru/video/5870

## Описание

Want to get more customers, make more profit & save 100s of hours with AI? https://go.juliangoldie.com/ai-profit-boardroom

Get a FREE AI Course + Community +1,000 AI Agents 👉 https://www.skool.com/ai-seo-with-julian-goldie-1553/about

🤖 Need AI Automation Services? Book a FREE AI Discovery Session Here: https://juliangoldieaiautomation.com/
Mastering Google Nano Banana for Free Image and Video Generation | Step-by-Step Guide

In this tutorial, learn how to utilize Google’s Nano Banana and NA 10 for free image and video generation. Get two free templates: one for generating images and another for generating videos from images. Follow a detailed walkthrough on setting up and using the model, acquiring a free API key, and integrating it into your workflows. Discover how to edit and create better-quality prompts with custom tools, generate animated videos using Gemini’s built-in features, and explore other powerful tools such as Open Router and AI Studio. Also, get insights into how to co

## Транскрипт

### Introduction and Giveaway Announcement []

How to use NA10 with Nano Banana. I'm going to be giving away two different templates today for free. One of them being a NA10 Nano Banana template that actually generates images for free and then the other one actually generates videos from images. We'll come on to that in a minute. So, let me walk you through exactly how it works. This is

### Overview of Nano Banana and Its Capabilities [0:19]

the basic workflow right here. And essentially, if you're not familiar with Nano Banana, it's a new update from Google where you can generate really nice images, right? So it's a brand new image editing model. I would honestly say from my tests that it is much better than chatb from what I've seen so far. As an example of this, right? So you can for example edit images actually create a thumbnail with it which is pretty nice. And essentially how you can use this is you can use it inside the chat here as an AI agent. Right? So this is a chat message and then from there you can then use open routters API and they have a free version actually for using nano banana the free version right then once you've done that you are going to run a request that turns the image to a video.

### Step-by-Step Guide to Using Nano Banana [1:10]

So let me show you exactly how this works step by step. If we go inside here and we type in for example banana. All right. So, you can see it's now generating the outputs here. So, we've typed in, for example, like monkey in the chat. It's going to edit that and then turn it into a file. Really quick process. We basically put in a chat whatever image you want to generate. For example, like monkey. That's going to send a chat completion over to open router. from open router. We're going to edit the fields and take the JSON which I'll come on to in a minute and then convert that into a file so that we've got the output over here of a monkey right and so we're using Nano Banana for all of this and it's really easy to use. Now, if you want to use the API for free

### Using Open Router API for Free Image Generation [1:55]

on open router, you can go over to open router over here and then you can go to models, right? So, you get your model and then the one that you're going to be using is Google flash 2. 5 image preview free, right? So, this is the free API that you can use to generate images for free inside N. Now, if you actually host locally on NAS as well, then this is completely free too. So, who we got on here? We got MD just

### Live Demonstration and User Interaction [2:23]

joined. Morning from Portsouth. Good to see you. Jesse Jiitsu, let's go. P says, "Yo. " Spice says, "Let's go. " And Mavan says, "Hello from New Zealand. " Yeah. So, essentially, this is how you use it step by step. Right? If you want to get the API key, let me show you exactly how this works. So, if we pull this up full screen, let me pull this up. Right? So, we're using the model in Gemini 2. 5 Flash image preview. Now, if you want to use the free one, all you would do is you copy this. And the reason that I'm not using the free one on this example is just because sometimes, you know, when it's just been released, and this is brand new stuff, right? When you're using the new stuff, it can fail on you a little bit. But let's try this out. So, we're using the free version of Google Gemini 2. 5 flash image with open router and it's generated the image. Beautiful. That is beautiful. Right. Word first time on a live stream. Wow. I love that. All right. So, Sum says, "Could you send the template? " So, the way you're going to get access to this, you go to and it's inside the free group, right? So, it's the AI money lab link in the comments description. Then, you're going to go to classroom, new AI automations, Google Nano Banana free. And then you've got the images and the image to video example. Right. So, if we want to generate just images on their own, click download. Go over to NA10, import from file, upload the JSON file. Boom. Shakalaka. There you guys. Ready to go. One thing I'm actually just going to do is I am going to save this as we're free, right? Because this is actually using the free API and it actually works on the live stream. So, I'm going to just download that and then we'll go back to the money lab. add that template in for you right there. Right. So then if you want to use the free API, you can just use a free API version. All right, just use that one instead. And so that's basically how you can turn this N into a free image generation tool that's really powerful that can just generate images for you on command. Now bear in mind if you using Chatch's image generation API, it would be crazy expensive. if it's going to be super slow, etc. and super annoying, right? Whereas you can use the free version with open router. You just plug in your details. Now, let

### Setting Up API and HTTP Requests [4:52]

me talk you through exactly how to set this up, right? So, if you wanted to set this up from scratch, if you want to build it from scratch. So, first thing that you're going to do is you would set up a new chat trigger like you can see add node and you would add a chat trigger. So, I've already added one so I can't add a new one. Then you're going to set up a HTTP request and this is going to change this to post right to post. So what this does essentially it goes over to open router laying this post request we're using this API right so it's open router um API chat completions predefined credential type is open router and then inside the credential type right you go to edit and you plug in your API key here now if you don't know how to get your API key here's what you're going to do you're going to go over to openi then to keys inside keys create API key And you just go and you plug that in directly here. You just paste your API key in. Right? So we've done that. Then what you can see here is we are sending the body. Right? So we're sending this body JSON type. Right? So you click send body. Let me just refresh the page. Send body JSON using JSON. And then if you want to know what the code is that we're using here. So essentially we've got the model as flash image preview 3 messages ro user blah blah and you can just copy and paste that right or just use the template that I've given you. But essentially the most important thing to note here is that inside the text input here we are inputting our text so that we can tell the image generator what we want. And so just to be clear here we've got a chat message that goes to post https request over to open router. From there we are going to edit the fields. Now, you might be wondering, okay, why would you edit the fields? What's the point of this? Right? And so, this edit fields section here allows you to map manually the different parts of the JSON code, right? So, you can see here we've got the data string. Um, and if I show you an example live, so if we type in, I don't know, cat eating banana. If we do that example right here, so that's going to run the HTTPS request using the open router. And then it's going to edit the fields. So, if we open this up, it's now taken all of the data, all of this messy data and just organized it into a nice stream, right? But the main thing to note here is that what it's actually going to do is it's going to take all of this base data and then it's going to turn it into an image, right, that you can download. So, if we go over to convert to file, what this is doing is it's taking that image data and then if we click on show data, it's taking that field mapping over here. We're going to click operation move base 64 string file base image as the output. And that basically turns this into a downloadable image. Okay. If we go to view over here, we can see our cat eating a banana. And it's pretty realistic, right? Pretty good. I'm actually going to show you some interesting ways to prompt this in a second that blew my mind earlier today. But essentially, inside the edit field section, you can create that image and then if you want to view it, you can. If you want to go back to the list and then download it, you can. And then you can see this image over here. Boom. Shakalaka. All right. Really cool stuff. So that's essentially how you can do it. Now that's a really basic workflow, but it works beautifully. And also if you don't want to go through the whole process again, if you want to tweak stuff, what you can do is pin each of the f modules here. Right? So if you click save here, this is all pinned information. And then if you want to get the JSON file, like I said, go to the AI money lab, go to classroom, new automations, new Google Nano Banano. It's right at the bottom. We do add a lot of stuff inside here for this free course. If you just want to get the JSON files, they're down here. Right, there you go. Resources. Boom. Okay, so that's basically it. Damicious says, what time is it there? It's 4 p. m., my friend. And then from here, we've got this ready to go. Now, what

### Generating Videos from Images [8:57]

I'm going to show you is how to generate the video. So, if you want to generate the video, you just go to this JSON file that I've attached inside the module. And it's again, it's completely free. Don't need to pay for it. This is free stuff. And then what you're going to do here is you're going to see an example like this, right? And so, essentially what you can use is something called Runway, right? And with runway, you can actually generate images to videos. So let me pull up an example. This is a super rough example, but I just want to show you the power of this. We're just going to close Alama. So this is a video that we've generated from an image, right? And so if you have images from Gemini, then you can actually turn those into videos inside as well. And again, using the free API, you can generate images. Then you can send those images over to runway and then you can generate the video from the image. Boom. All right. So let's go to how this works step by step. So again we're starting this with a new chat trigger. So we're taking the chat input for example like whatever we want to create the image about. So for example like banana. Then from here we've got the HTTP request which again is just creating that image. Nothing has changed there right? Nothing has changed there. So that's what it does. And then from here what you can do is you can actually take the image that you have and generate a video out of it. All right, pretty simple and easy. So if we go back to for example basic banana image, right, we've got that image like so. Then you can generate videos with it. And you can see this is using just a sample URL inside the automation. But you can see how easy it is to do this, right? So you're basically just taking a PNG file and then you plugging it into the process. Now, if you're wondering, okay, how do you set up Runway to use this? So you can set up a HTTP request one, right? Then you're going to go to post. You set up the URL, which is this one. This is runway MLS's setup. And if you want to create like an API key and everything like that, just go to dev. runway. This is the developer portal. And inside the developer portal, you can actually get an API key, right? So don't use the main version of Runway. Go to the developer portal at dev. runway. ml. com. Click on new API key. You can generate a new API key that you're then going to plug into a generic credential type header off runway ml. And inside the runway ML section here, you can put authorization right as a name. Then you're going to put bearer. And the way that you type this out is it's a capital B. Let me I'll put this inside the notes just so you can steal this from me. So it's bearer space API key, right? And so you have to add that space in here and you have to put bearer first in the credentials and then that's how you can validate this. Right? It's important because otherwise you won't be able to generate responses. You also have to make sure that if you're creating videos that you've got your balance topped top on runway. So you can see here we've added credits and that allows us to generate responses like you can see over here. Right? So you can see that we've been generating responses using this process. Really simple and easy. You see all the different models that they have here as well. So it's quite easy to turn a image to a video. You got a lot of different options right there. And essentially that's how it goes. Mother man says it's 9:00 p. m. here and click stango. Stanganger says, "Yay, Julian master. Appreciate it. Thanks for watching, tuning in. " All right, gener credential type header off runway ML send headers and I'm using the X runway version and we just add this value in. And then on the JSON here, we send body JSON using JSON. And then if we open this up, you can see how we've plugged this together, right? And again, you would just replace that URL with an openly public URL where your PNG file is hosted, right? Really important to note that. So that's essentially how you can do this. And then you can generate videos like I was showing you a second ago inside here. Right? So this sends this module here. It sends the image to become a video using runway. And then this section right here gets the image from runway. Right? So you can see it's using that JSON ID over here which is pulled in from the last module. We're using a generic credential type header off runway ML send headers same model as before. Boom shakalaka. All right. And that's basically how you can turn an image into a video using NA10 and this workflow. So you can basically replace any sort of previous modules that you had and switch them over to something like this. Right now, as an example of that, if you pull up a previous module that I've created, this is shorts automation. Right? And inside this shorts automation, what we've done is we've created an idea, then that's generated a prompt, then that's going to plug in an image over to foul, right? And so this section here, instead of generating the images using Flux now, you could actually create the video using Oh, sorry. You can get the image using Gemini image and then generate the video using VO3, right? So you can use something like this. So lots of cool stuff that you can do there. Lot of optimizations and automations you can make with that. And if you want both of the templates for doing this, we've got the image to video example, the JSON for generating images, and then finally the free API version for generate basic images. The other cool thing that you can do over here, if we go back, right? So if we go to overview then we go to banana basic n to n you can actually make this public right. So for example if we click on this make chat publicly available then we're going to make that workflow active. All right and then you can actually create a open chatbot that generates images directly inside the chat here. Right. So if you want to use this you can. And then you would just go through it as normal. All right. So that's basically how it works step by step, how to use it, etc. Now, there's a couple other things I want to show you here that I think are really cool. So

### Advanced Image Prompting Techniques [15:30]

using the custom GPT that I've built. So actually got this custom, this is inside the AR profit boardroom. If you want to use this custom GPT that I've built, essentially what this does is it's an image prompter for banana nano, right? For banana nano. So if you want to get like better quality prompts, you can go inside here. This is custom prompted on Google's guidelines for generating responses with nano banana. And then from here you can start generating responses. So for example we could say right okay give me an image of a cat playing basketball with a gang of dogs. Something like that. Right. And basically using this image prompter it's going to give us the subject the composition the action the location. And that's a much better quality prompt for generating responses. For example, if we take this, it's going to have all the details of the context, the style, the editing instructions, and then it's going to have a final prompt over here. So, if we take this information, like then we're going to go over to Google Gemini, plug this in right here, enter, um, we'll get a much better output than using just a oneword prompt. And so it depends on the quality of the prompts that you want. But you could easily add this into your workflow and then generate better quality prompts as you're going along. So let's wait for this to load. Here we go. That's the image generated. And that was super cool and it's super easy and it's simple to generate. We've got a cat playing against all these gangster dogs. Whole crowd in the background looking at stuff and some squirrels at the top. like the attention to detail is pretty cool too, but it's much better and much faster than using something like, for example, chat GBT. The other benefit of using Gemini Nano Banana is that when you're actually using this, you can edit the background and that sort of thing. So, for example, if we wanted to say, okay, make the cat look way more ghetto and gangster. then we can actually just edit like different parts of the image like a AI version of Photoshop if that makes sense. Now, if we use exactly the same prompt inside chat GBT, right? So, we're going

### Comparing Nano Banana with Chat GPT [17:47]

to take this prompt like and we use chat GBT which I mean honestly it's like super slow, right? So, if we go inside chat GBT, I'm actually dreading using this right now. So, I'm going to say okay, create an image of this and then if we go to Gemini, right, and we'll compare these side by side. So, I'm going to pull up chat GBT and we're going to compare this versus Gemini. So, we're going to plug this in over here and we're going to use chat GBT to generate a response as well. And so, let's see who wins. Now, I know for almost a fact that Gemini Flash images is going to generate a much quicker and better response than using Chat GBT, but let's see what we get back here. So, you can see we've already got the image back, which looks pretty good. If we have a look at the image from chat GBT, it's just getting started, right? It literally takes 10 times longer. If you have this in your workflows, then your productivity is going to get absolutely smashed. And the reason for that is because you're waiting like 10 times longer, if not maybe 50 times longer, for the same image to be generated at a lower quality, let alone if you have any image edits that you need to change on the image. So, for example, if we're using this, well, I can quickly, whilst it's still generating, I can say, okay, make the cat the green alien. And whilst chat GBT is still messing around generating, I think we can even make edits quicker with Gemini. But let's see. We'll see which one comes back first. We've actually generated two images with edits in the space of time it took to get the image back from Chat GPT. It's just ridiculous. It's just absolutely ridiculous. Darren says, "What if we take old technology and build a bridge to connect it to new technology that is a lot cheaper and easier for government mined transport and banking to adopt? " Probably a little bit off topic there, mate. But yeah, I see what you're saying. I think it is a bridge to be fair. If we have a look at these images as well, side by side, this one is more photorealistic, but it just looks a lot weirder, right? like what's going on with that dog's arm over here. Whereas, for example, if we look at this image, there's a lot more detail. Like I was saying, it looks a lot cooler. It's a lot more interesting. I would say this one is going to capture attention more. Andrew says, "Julian, you are awesome. You're an absolute legend. " Andrew, I appreciate it, man. Thanks very much. It's really that makes it worth everything that I do to get good feedback and stuff. So, I appreciate that. Thank you very much. But if we have a look here, so if we've got the gangster cat, we've got the cat over here, we've got the alien, you know, so like you can build really cool stuff with Gemini Banana and it's way faster and way easier. Andrew says, "What's your main chosen model? " So for using images, like I was saying, I use Nano Banana. I think it's way better than Chat GBT image creator. The other thing that I'd be tempted to do, and I've not tested this out yet, but one thing that I would like to try is actually building an app using the API from Google image as well. Maybe we can test that out in a second. But essentially, before we do that, I want to show you something else and this is absolutely amazing. I've actually linked to Machina inside the free module, the AI success lab, but this blew me away, right? So essentially what you can use inside Gemini if you're creating better prompts and you can put this inside your NA10 workflow if you want to is you can take these prompts and use them as presets for like logos ads that sort of thing. And there's 20 different JSON templates inside here. So I'm actually going to put this inside the description of the video from today as well. So that's on YouTube too, just in case you want to check it out. But if you want to, for example, generate like a really cool output here, let me show you some examples. Right? So if you wanted to generate let's say like a game style image like you can see right here. Shout out to Mino again for doing this. You can actually take this JSON prompt and you can plug that into the into Gemini Nano Banana when you're creating the outputs. Right? So, for example, if we take this over here, we're going to copy that JSON. We're going to plug it into Gemini. Going to switch tools to images. And then we're going to say, okay, create a zombie apocalypse image, something like that, right? And then that's going to start generating the image, but it's going to be using the JSON that we're filtering it through, which means that we get much better responses from the image because it's stylized to that custom code we've plugged in, right? And that means you got a custom preset if you want consistent outputs. So you see how this has created an image right here like in a game style, right? It looks way more interesting. And so you can generate beautiful images using these presets and they look really cool. Sporter says, "If you want to impress us, have a gangster cat rap while balling. " All right, let's try this out. So I'm going to change this to Let's see what styles we got on the list here. So we got the game one is really cool. This is kind of like a comic book style one. This is photo realistic, which I really like as well. So, we'll try this one for the image. So, I want to take the JSON over here. We're going to plug this in to a new chat, right? Tools, images, go up. And then what I'm going to do is I'm going to go back to the image prompter like, and I'm going to say, okay, give me an image of a cat playing basketball cat with a gang of dogs. wrapping whilst balling, right? And we'll get that image prompt generated first and then we'll use that to generate the outputs, right? So, we're going to take this text like so, go back to Gemini, plug this in at the top, right? Hit enter. And now we can start generating better responses. And that should use the custom prompts from chat GPT along with the photorealistic JSON from Mulina. And then if we go over here, we have the image. And there we go. So you can see how easy that is to do. Super simple and it really didn't take long to generate at all. All you have to do is just run those prompts step by step using the process I've given you. Works really well. You actually get much cooler, better outputs. I would say that looks more interesting than the original one that we generated and less cartoonish as well. And then also here's the other thing. So if we download that full size this is something that chat GBT can't do as well. So if we download that and click Strango says top results appreciate you. Sporter says a thanks very much sir. And then for M4 log says hi Julian thanks so much. Your video pushed me forward with NA10. That's what I'm talking about man. Let's progress humanity with NA10 automations. All right. So now we're going to take the image over here that we just generated. Right? So this is the one of the gangster cat wrapping whilst balling. And here's where we're going to take it to another level. Right? So we're going to add in that photo of the image from Gemini. And then we're going to say animate this. Right? And so we're using Bayer 3, which is the builtin automation from NSM. And we're going to use that to generate a video. Right? So you can see here it's now generating that video using Gemini. Not only does Gemini have the fastest image prompter in the world, it also has a built-in video generator that you can't get inside Chat GBT. And then we're generating the video over here. So that's going to take a couple of minutes. But yeah, you see how it works. Final thing that I haven't tested out, but I want to know whether you can do it or not. Probably there's some

### Creating Custom Tools and Final Thoughts [25:45]

people watching who can do this. But essentially, I think inside Bolt, you could for example use the nano banana image API to generate a image tool. Right? So essentially what we're going to try and do here is create an image tool using the image API from Google. So that for example you could generate like images or thumbnails whatever you want directly here. All right. So if you've never used it before it's kind of like app builder and it can build websites too and it is very simple because you're just using plain language to describe what you want and so using that we can then create the tools that we have in mind. Right? So if you always had a tool that you wanted to create, let's say for example, you want to create a image tool using the Nana banana API, I'm pretty sure you could do it using this process. It would just take a lot of back and forth. Actually did something similar with the chat GBT image previewer, but yeah, you get the point. So you can build those sort of tools directly inside BN new as well, which will be really cool. Final thing I want to show you, if you go over to AI Studio, this is another way you can use it for free and you can get a free API key from here. I know a lot of people think that you have to pay for API keys. You don't if you're using up or studio on Google. So if we go to AR studio. google. com then we are going to go down to chat. Inside chat you can select nana banana and you can start using this directly here as well. Right? So you can start generating responses directly inside the chat here. And it's free up to a certain limit. Right? Obviously if you're going crazy with it then that's not going to work. But if you want to just quickly play around with it for free, then you can use AI Studio as well. It seems to be a little bit slow. So, it took 9 seconds to generate that. But again, like how much faster is that than using something like chat GPT? And good luck if you need to create some edits as well. Andrew says, "Bolt is amazing. I'm trying to use Bolt and NA10 together. " Yeah, I think that would be really cool, too. But yeah, essentially that's how it works. If you love like NA10 automations like this, feel free to get the AI profit boardroom link in the comments description as well. If you type in NA10 here, go to classroom, then go down to NA10 templates and workflows, you can check out all of our NA10 workflows here, and we have attached JSON files for each workflow, right? So, if you want to learn how to build with this stuff, you can. If you've never used it before, but you're curious about learning it, you can start with the six week AI automation master class and we'll literally show you how to create your first AI agent in five minutes. It's crazy. Anyone can learn this stuff from scratch. And then also we do daily coaching sessions. We have five a week. And inside the community here, we have a very active community of people who just want to learn and grow together inside the AI profit boardroom. Like I said, the free automations from today are inside the AI on lab. before anyone comments like this is not free blah blah you can get them inside the resources here import them into NA10 you can actually host NA10 locally if you want to use NA10 for free as well so all of this stuff is free and you can get a free API key from open router so no need to comment that it's not free because it definitely is 44 log says or analog says I managed to make a huge right program in Google studio imported vs studio to change the integrated services vm it's massive work yeah I would agree like it's justing amazing what Google AI can do and it's clearly dominated, right? I think actually Chat GP makes the most revenue from what I've heard when it comes to it AI, but Google absolutely crushes when it comes to its outputs, right? This is generated like a an example AI image generator. But the thing is you want to actually have an option to plug in your API key here. So I would just plug it in all the information about API guidelines for coding with Nano Banano. And you can just plug those in the chat. Create a tool with it. Boom. Shackleaka. You're living the dream. All right. So

### Conclusion and Community Engagement [29:51]

thanks very much for watching. Hope to see you inside the AI profit boardroom. Link in the comments in description. And yeah, we've got loads of good stuff going on in there. And then also, if you want to book in a free AI automation session with us where we can basically look at your business, look at where you're spending the most time and then help you figure out how to automate it, you can book in a automation session right here. We'll basically on that call look at the time audit build out the systems for you and then do the hands-free stuff here as well. Final thing I want to show you was the video that actually got generated by B3. So let's have a look at this. This will have sound as well, but I'm not going to play sound because it won't sound on the live stream. But essentially, you can see how we've generated that video using VR3. Thank you for the reminder. I appreciate you. Yeah. So let's have a look at that. It looks really cool, right? And that was all generated from this image with Nano Banana. And then you can even do that inside N10 like I showed you earlier today. Boom. All right. So, thanks so much for watching. I will see you on the next one. Cheers everyone who tuned in. Appreciate all the comments. Support us. You're an absolute legend. Click Stanganger. Andrew, you're a legend. And I'll see you on the next ones. Cheers. Bye-bye.