Nano Banana: We Found the Best Tips & Use Cases

0:00All right, welcome back to the noise. We got a couple of stories jumping to today. A lot of banana banana stuff. nano banana lives it does it's it thrives it thrives it's it's growing it's mutating it's yeah turning into a jumbo banana all right let's get into it

0:18okay so first big story nano banana not to toot our own horn but we were we were like pretty ahead of this game before everyone caught on to nano banana and and google for a minute there if you googled nano banana our video came up first it was in the very top results and some people were messages like hey i was trying to search not a banana and like your video was showing up top so do you know you heard it here first you're on top of this stuff that's right but now it's more the reason to subscribe exactly exactly but now it is out in the wild google confirmed that you know it um it was their model and the official name is uh gemini flash 2.5 2.5 flash i'm glad they are still even externally calling it not a banana yeah it's way cooler way cooler of a name and all the thumbnails on youtube and everywhere is like the banana yeah people are generating a banana yeah turning things into bananas yeah it's great it's fun it's a lot of fun so it's already out we're not going to cover like the details of it but there have been a lot of really awesome use cases of it and i kind of wanted to go through some uh tips best practices things i've seen online interesting use cases uh to kind of just showcase what i've been seeing what you've been seeing yeah i mean the more stuff i see from it the more i'm like damn this is the most powerful image generation model to date yeah this has been my go-to uh for a modification i still have not used it as much for like generating stuff but if i'm like i need to modify an existing image yeah or something that generated or tweak something this has been this has been the go-to yeah like for image likeness if you want to replicate yourself or you know a digital actor this is the go-to if you want to you know throw a prop or a product into somebody's hands this is the go-to uh so let's get into some of these big use cases here before we jump the other use cases i think we should probably just showcase the desk the test i did because that that makes the most sense but uh yeah i did a fun test where i just took a screenshot from this podcast at this exact table yes and then i uh for one test i grabbed an image of an old clamshell uh macbook or they weren't even that ibook yeah before they were macbooks and swapped out our macbooks with those they really depended on finding a good source image and surprisingly there were not a lot of good source images of just the laptop open oh interesting yeah okay they're all like the because they used to product display them like this for whatever weird reason was a thing that it was cool man it was cool yeah but that was like the bulk of the product photo so i had to find a good product photo okay i had to change the camera angle they're phenomenal i'll change the camera angle so like i said make an aerial shot and this thing the thing that's crazy to me about this is like your cup your mug this was like just a sliver of it was showing yeah behind your laptop and it like nailed the complete mug in this aerial shot okay you want to know something really creepy yeah that wood flooring is exactly the color of this wood flooring how does it know that it is and it's also funny because we're on a rug but on top of the wood floor and like there's none of that in the shot i think maybe it's just assumption based on the vibe of the room yeah and it got like as far as likeness goes like the right side of my body or the left side of your body and nailed Yeah, even our arm position matches pretty well.

3:15And then another one for fun, I just put us in front of a live studio audience. Kind of warped my face a bit. Somebody commented, yo, that's Will Smith territory. Can we get into that later? We'll get into that one too. But also what I thought this was funny with this one was it took the image from the shot and put it on TV displays in the audience. You see it like. Oh, wow. That's nuts. Yeah. Did you ask for that? No, I just said, put us in front of a like live audience this was like yeah you know i ran this a couple times reflections of the ibooks on the desk itself maybe it's a little exaggerated but the fact that it's a good call that's crazy too yeah it has like the white reflection yeah wild okay yeah and somebody else pointed out the wood grain on the top view shot is accurate because the table is in four pieces yeah and the wood grain is in four pieces yeah and now yeah the proportions look a little weird but it it yeah figured out that this is in in four sections so good yeah Other use cases that we've seen.

4:11Google had a good roundup of some of the use cases that they've found or some other people have found. So one is you can basically, kind of like we covered in VO3, you can drop annotations on top of an image of like what you want, and it'll honor those changes into the new image. And FreePick actually just released a tool that makes this really easy. You can't add photos to it, but it's an annotation tool. So you can take your image, click of like, hey, change, you know, the headphones to a hat or like various precise notes and it honors it really well. Wow. Yeah. And FreePix where I've been using everything too, just because they have the unlimited credit thing, which really gets you.

4:50Yep. So that's been, that's been super handy. Yeah. FreePix has been great for just jumping across models really quickly. Yeah. It's great for testing. I mean, that's how I discovered Seedance and the other ones because they had them and I'm like, well, I'll try it out. And then these are great. and cost effective yeah what else we got headshots change in angles we covered that one yeah so this is the one i sent um i'm looking at the third one here so the architectural example okay so taking just like a iphone photo of a building it could then generate like a arch archvis like architectural visualization of the building oh yeah the isometric view yeah yes yeah that one's cool yeah that one a photo yeah this photo that they showed is pretty not that great yeah it's not that great and i'm sure it's like filling in a lot of the missing details but at the same time this could be really useful for somebody that's doing city planning urban planning anything like that where they need to stick to a certain type of you know architecture or you know if you're doing world building and media entertainment yeah if you're just trying to build a game or something needs some assets i mean i was thinking this would just kind of be a fun, interesting way to animate because you could, you know, create this isometric model of whatever you're taking a picture of.

6:01And then you can just run this through VO3 and say, hey, make a 360 spin and or some sort of other animation. And you've got like a model of a building of something you took a picture of. Yep. And you could do all sorts of things with that in VO3. The other territory that I don't think we have it here, but I'll just saw some of it online is image restoration. So now we're in like Topaz and Magnifique area. Right. But this one is just on another level like i have yeah this shot too where someone restored the first photograph ever taken isn't that crazy which was on a i believe it was a diaro type right yeah and i didn't even like i didn't even put together i always i mean i've seen this image before and i never really pieced together what right it actually was and then seeing this restored photo uh i was like oh it's rooftops yeah i saw some of like martin luther king and stuff because those were all black and white okay i've seen some too of just like really destroyed uh looking you know torn printed archival photos and just having them restored.

6:53I even saw one today. I think it was from someone that works at FreePick and they gave it like the, it was, um, it was like a mugshot of like an old prisoner and then like a description of like the crime they did. And then it made the photo of the crime with the person. So it like read the context of the photo and then made like kind of did a reenactment of the crime. I used to, well, I still do. I watched the YouTube videos where they take historical figures and turn them into moving characters yeah like they'll take julius caesar and now he's like you know drinking his last wine yeah this will like level this up onto a whole different playing field completely yeah yeah i mean it gets into that territory i was talking about in the netflix ai episodes where it's like the line between the documentaries clarifying that it's like not real archival footage right i mean you know it's sort of like you know you think of kem burns and it's like he did he elevated you know took archival images and elevated them it's like, no, there was not really sound there.

7:46So, it's like in that realm where he's like elevating, bringing history to life. And it's really moving and powerful because you already have historical context when you watch that movie or that TV show. So, for you to like watch a lifelike reproduction of that person at the same time, knowing the historical context really drives that home in your head, I think. Yeah, yeah. And also just making recrees and stuff that might have been shot traditionally, you know, with those history channel specials where it's like the interviews and the people talking and then it's like the World War II reenactments and stuff.

8:19But doing that with Gen AI, that's what Gen AI, that company does. They're kind of specializing on lower budget documentary style recreations. Here, this was the mugshot with description turned into reenactment of the crime. yeah the guy has such a distinct haircut and a look yeah yeah but even if it pulled the context of the like it read this of what he did and then use that as a problem like i think they just gave it this image so that was what criminals used to look like back in the day very nice haircuts yes very posh great fade yeah and then yeah one more this was uh from uh philip schmidt who works at deep mind and he posted a list of best practices for nano banana and i'll just run through a couple that I thought were useful.

9:08One, be hyper-specific. The more detail you provide, the more control you have. Right, in natural language, I'm guessing. Mm-hmm. Yeah. Provide context and intent. Explain the purpose of the image. For example, create a logo for a high-end minimalist skincare brand. Will yield better results than just create a logo. Right. Use semantic negative prompts. This was interesting. So instead of saying no cars, describe the desired scene positively. Quote, an example, deserted street with no signs of traffic. Sometimes those prompting tricks, I've seen this with other models too, where it's like sometimes they don't work well if you say don't do this it works well if you say i want this which is the opposite of what you don't want right i i think google inherently believes in as much positive prompting as possible which negates negative prompting and that's the whole reason why like vo3 doesn't really have negative prompting i think possibly yeah it's like their ethos and their dna no negative yeah no evil no negativity the last one i think this was the most useful because you could you can give it multiple images and it'll you know generate the output but people are having issues with the aspect ratio not being what they wanted yes and i saw that so apparently when editing gemini 2.5 flash aka not a banana generally preserves the input images aspect ratio if you upload multiple images with different aspect ratios the model will adopt the aspect ratio of the last yes provided yeah so whatever if you want your 16 by 9 image yeah upload that last that's a hack to yeah just do a little massaging in photoshop it's not that hard right yeah well no i mean if you're like uploading you have like let's say we had our reference image here but then i'm like i want to give it an image of like a square photo i found of a hat to put on you yeah if i uploaded our image first and then the hat image of a square it's going to give us a square output correct so so just take the hat in photoshop or no i'm just saying no i'm saying just upload the hat first and then upload this image for last because whatever we upload last will be the aspect ratio.

10:59Got it. So you don't have to do Photoshop. Can't you just prompt and just say, give me a 16.9 output? I don't know. I think people are still having issues with that. Okay. Upload it last. Unusually manual. Upload it last. Upload it last. Yes. Okay. Yeah. You see anything else with Comfy? With Nano Banana? I don't know why Comfy is on my mind. I mean, just there's been a, like when flux context came out there was a lot of outputs uh generating likeness of people you know whether it's themselves or somebody or sometimes celebrities and then a banana one ups all of that like what it does i think what it does better than flux context is uh skin detail wrinkles pores um getting the subsurface scattering lighting correct and so i always talk about uncanny valley with digital humans like nano banana is like one notch closer to closing that gap than i think previous ai models yeah i found it where like it really follows prompts well it does not modify other elements outside of what you want to change yeah where with flux sometimes have that issue and moving camera angles different positions has been light years ahead of of anything else Yeah, I will say there is, we covered this on the pod, Enhancer.ai, which is the service that adds skin details, like, you know, whether you have freckles or whatnot.

12:22If something like Enhancer was built into Nano Banana or Flux Context, then that's like one less step you would have to take to make more lifelike humans. Okay. Or, you know, it's probably just like you could build it into a workflow, tool workflow or something like FreePick. Or Involk or Weavey. Yeah. yeah right where it's like okay you do your image and you kind of get what you want and then once you got all your elements locked off then you enhance or modify yeah a lot of the workflows that i'm seeing is like it starts with nano banana then it goes to enhancer if there's a person in it and then it comes back to vo3 and then it goes into some other stuff like it'll go into runway for vfx or whatnot right right one thing other interesting thing uh or useful tool because people have been like hey this is great uh but you know i still live and work in photoshop how do i get this in Photoshop so I don't have to rely on, you know, Firefly.

13:10Yeah. So someone, Rob the Winter, built a Nano Banana and Flux Context AI plugin for Photoshop. Nice. And so, yeah, we got the Gumroad link. It's 10 bucks or suggested 10 bucks. But yeah, this looks, you know, awesome to just bring these tools into the one. For sure. The spot that you live and work in, you know, especially something that's powerful with Photoshop. This is like, takes the next level because you could just modify layers and, you know, create elements that you want, but then still have the fine tune control that you get with Photoshop. This is the last mile thing. Like if somebody closes the last mile, that's where they make the money.

13:43Yeah. I mean, I imagine, cause like Adobe has been rolling out, like bringing in other models. I think that's currently, if you use like the Firefly web app, you can like call up different models and the third party model. Right. I would imagine it's probably only a matter of time before this is just built into photoshop sure but then they could stop gap for now for 10 bucks i was thinking about adobe the other day i was like okay they were the first to drop a commercially safe model firefly and uh last couple of years their entire sort of strong suit was like everybody else's model is dubious ours is commercially safe ready to go and not that they're moving into third-party models like that claim is no longer valid well i think the way they framed it was like it's up to you and what your like legal you know uh tolerance is and so it's more like we're gonna give you the option so it's like yes if you want to create with firefly yeah and keep it all commercially safe like choose firefly but if like your quality yeah arguably well yeah yeah well yeah i mean i don't think i would say that but yes yes that's not not arguably it's like what's more important to you quality or legality right so uh you know they're like we'll give you the option for the model and you know like if you're doing something even if you're following netflix's guidelines and you're doing previous stuff where you don't care what the issue with the model is right uh because you're just doing previs yeah you load up flux or gemini or um black forest labs or whatever okay i'm gonna add one more same model adobe thing yeah i follow some of the adobe folks online on linkedin and stuff and um lately i've been seeing a decline in the number of firefly posts yeah i don't really see the only thing i see firefly more so now is like firefly as a platform platform like it's a web platform that is competing with the likes of like free pick or right flora or i mean they just released a beta of like a mood board generator right where you can call up different models i have not seen that much about the firefly model itself i agree with that right yeah so it's a it's an interesting move and i think a company as successful as adobe could definitely pull it off and figure out how to monetize everybody else's model yeah i will say maybe one argument for this third-party script is being able to use your own api keys and because i think that's also gets more important especially with like client work yeah where it's like sometimes you just want to have a dedicated api key because that may be the client you're doing client work and it's on their account so they're paying for it or you need to keep track of different uses for different projects yep if you're doing this if adobe does roll this out and built into photoshop it's probably going to use their credit system i don't know how their credits convert to dollars of like what the equivalent is but you know sometimes it might be a lot cheaper if you just load up your own api key and you pay the direct fee to google or file or whoever's hosting the model and then run it through there and that might be no that's pretty cost effective so that could be another argument for why even if adobe does build this into photoshop a third-party tool could come in handy i have a billion dollar idea okay if you're watching out there you have a friend in adobe let them know this is for the improvement of the entire ai industry adobe has enough software development expertise enough management expertise to really pull off a comfy UI competitor that's way better than comfy.

16:54I know they have the expertise to do that. They could own the professional market, the AI market in that sense, right? I can't think of anything that Adobe does that is node-based though. Like in the world of like, you know, After Effects versus Fusion versus Nuke, Fusion and Nuke is node-based. After Effects, they've not done node-based. Like they've not done, I can't think of any other software that has gone the node-based route. Yeah, I mean, they could figure it out, right? I'm not saying they can't figure it out. I'm saying, does it fit with Adobe's? But like now that they're backing away from having, being a model company to now more of an integrator company, if you keep backing up, you could become a developer company.

17:35So like the same way Microsoft has GitHub and Copilot and like all the tools that they're making the picks and shovels for the gold rush. Right, right. Adobe should be in that game too. I don't disagree with that. Yeah. I don't know if they would, I don't know if I see them building like a something as going after like the comfy market of like the highly technical. Let me like build out my, you know, super custom workflow. Maybe it's like the technicality could be dialed up and down in the same way in Unreal Engine. If you don't want to use any blueprints, you don't have to. Right. But you can totally open that up and get technical.

18:08You can even do C++ coding in Unreal. Right. I've heard of that. So maybe there's like a dial for how professional you want to get. But I think it's like a segment of the market that really has no clear winner yet. And we talked about Comfy a lot. They're not monetizing. They're not really. I would see Adobe maybe going more after like doing more of like a Flora kind of thing. Yeah, right. So that's like the stepping up and down complexity chain, right? Like at intermediate level, it's Flora. But then if you really want to build your own custom nodes and open up APIs, you just peel back the layer and get down to a Comfy complexity level.

18:46Yeah, I mean, I'm also just, I've never seen Adobe open, have any products that are like that open. Like if I wanted to adapt my fall.ai APIs into nodes, I don't see Adobe letting me do that because they would want me to like run through their credit system. Yeah. I don't know. Yeah, I mean, I was just thinking because of the Photoshop plugin that you mentioned. I was like, wait a minute, they could have plugins for everything, every model. Like they can own that whole. adobe's target is the creator the editor the designer that wants to do the stuff and like once they click buttons and the thing works yeah and knock it into the nitty-gritty of like let me build out my i agree okay yes my node-based workflow yeah like adobe's been more like it should be a tool and a button that works behind the scenes and does the thing that you want they're creator you don't know how and user focused but not yeah they're not microsoft they're not google they're not perplexity i remember seeing a post that was a good argument where it's like why did adobe not turn dreamweaver into like the web flow or something else like the cat to keep up with web development at the time yeah yeah i don't know yeah yeah i remember i remember dreamweaver that was my first web builder but look you don't have to be adobe i'm just saying there's still room for a company to move into the ai developer space and really own that in the same way like google totally dominated the browser game and now chrome is the basis for everything if you're going to do any type of web development i mean i know we have talked about this of like how does comfy ui make money but like even if you're not an active comfy user there are a lot of web portals and platforms where comfy is the back end and like a lot of stuff that you're uploading images and it's just running through a comfy pipeline yeah so it's there i don't know what their future is because i don't as we've talked about we don't know how they make money yeah hey uh comfy anonymous if you want to come on the show mr mr uh comfy bitcoin guy it's the same developer the same creator no this is a real person yeah i sent you a video of him yeah no there's a there's not a secret person yeah what's the bitcoin guy's names satoshi satoshi yes yeah all right we're back and rambling we've got enough nano banana all right if you've found any other use cases though let us know in the comments because um there's just new stuff popping up all the time and i'm messing with some other stuff too i'm trying to blend Nana Banana with Mary from Moon Valley for some workflows.

21:05I'm going to post that soon, but I found some interesting use cases there. It's just so good because it doesn't modify. It doesn't, it can, it'll leave the rest of the image alone and it'll like just modify specific things. The end painting is sharp. Yeah. All right. McMuppets. McMuppets, our favorite. Okay. So McMuppets has a new tutorial. We've talked about in the past, he's posted some of the most impressive, complicated, comfy UI workflows that we've ever seen. And a shout out to him for when When I first started on Comfy UI, I downloaded some of his workflows. And man, I mean, such a game change.

21:36They're a work of art. Yes. Chef's kiss. Thank you, Mick, for your contributions to the AI world. So he has a new tutorial out. But I wanted to run through this one specifically because usually a lot of his stuff has kind of been more in the animation space. Yes. But this one is VFX with live action. and it was one of the most sort of impressive workflows and blending live action with ai generation yep and it's something we've talked about a lot of like how these are going to be the future and like blending these two elements yeah and this is a really good workflow and so i wanted to kind of yeah and it does mimic traditional vfx in the sense that things are layer based and you know you're modifying for example the background without affecting the actor in the foreground and things like that yeah so the the gist of the workflow is basically shot everything live action and would modify either just some elements like modify him in the existing world that they shot or completely change the world and keep him and basically he was like it was sort of like acting with a green screen but there's just no green screen right uh it was just in the real world and we just needed to get the positioning right but everything else we could change with ai yeah and he's doing essentially match move without any camera data any tracking information which actually i'll talk about a sec but that led me to think like oh this would have been this actually would be a really good use case for something like jet set to give track the camera position you should connect the two dots you should i to make yeah i was gonna send elliot this link to he's probably seen it already but i was gonna okay this would be a really good use case for for jet set but yeah so basically shot everything runs it through uh comfy which he built this really complicated elaborate comfy workflow that identifies the subject isolates the subject him um basically for the workflow to work you need a you need your original video you need a rough cut out of the subject he's like it doesn't have to be great because the ai will just generate the rest of the elements right like so it doesn't have to be a super clean mask of the person but you have to have your person masked out you have to have your um uh black white uh matte uh death matte uh i don't even know how to be a depth uh yeah it's a depth just a like a mask to mask out oh no that's just a mask yeah just it was black and white it wasn't yeah yeah and then camera tracking data if you want and so we had a workflow too to like track points and data in the scene he's like or you could just track it in another app and just pull in your uh tracking point um coordinate text file data i that's where i was thinking oh whitecraft jet set would make right a lot of sense because that was like an extra step and you had to like track and maybe possibly like bounce around a bit bring in camera tracking data into comfy it literally text like oh like a json file or something let me show you uh it looks like this and i don't know enough about tracking like coordinates like just x y coordinates like i guess it's json yeah that is tracking information but you know it's so arbitrary there's no time stamp or anything so i guess it doesn't matter he covered it in a previous video he's like we covered this more in like our last tutorial but it was um some way that it works yeah however the data spit out it just kind of schmooches moshages whatever he showed it worked um yeah i mean he had he offered a few different techniques for tracking the camera and getting the data in a comfy there i mean there was also a node that because this was only if you use the external tool there's a node for comfy uh co-tracker point tracking which will try to run your footage and and uh it'll it'll track the footage okay so there there's a pre-existing node that he's using to bring in camera tracking data into Comfy.

25:06I didn't know that. I mean, Comfy has all these nodes. I mean, that's the other advantage of the open source platform is like people can just modify it and build and customize it to do whatever you want. Right. Okay, so you've got all this data and then there are options to basically, you could generate a new scene, a background scene and kind of give it a first frame. You can give it a text prompt of what you want to change. And then basically it is modifying everything else that was not masked out. it's everything in the black and the black generating uh it would be yeah it doesn't matter the non-mask side right whatever you cut out from your subject that was not there you can generate so you can give it an image to help you know feed it or you can just do a text prompt right and then it is generating the background using uh one 2.1 yeah i'm sure because he's been working on this for a while i'd be curious how this improves this one 2.2 probably better i'm sure a lot better yeah and it generates the background and then blends all of the edges with the character sometimes it gets like uh he said he like shrinks himself and he sits on a couch and like the pressure from the couch from his hand even though he's like literally sitting on like a box like there's a depression of his hand yeah and then like a little bit like you see the kind of couch it's like aware of that yeah of what is happening with the subject matter so it for those of you who are following along the video it's essentially like a honey i shrunk the kids type of movie production where mick is tiny into a world that's normal sized.

26:30Yeah. Here, let me run the final movie, which he has like before and after he has like the original clip and the, right. And the final shots. I think in summary, basically what he built is like a runway olive that you could run with comfy way more precise. But the thing with this is it's like he is masking himself out. So like the stuff he films of himself is not changing because the issues I've had with runway is like, you'll say, Oh, modify this, modify that. And sometimes it'll change this, but then it'll also change how the person looks. And so you always kind of get this like hit or miss.

26:57This gives you that precise control of like, keep me, keep the actor the same, do not change them and then change everything else. Yeah. This is more of a pipeline for an entire film where you can throw different shots and each shot would have a different requirement versus runway where it's like a shot by shot generation. Yeah. Hit or miss, hit or miss, hit or miss. These are wild too. Look, because this one, it's like literally he just needed to, like the whole city street is fake the running also phenomenal job with high speed motion because he's running the camera shaking and jittering yeah and the generations and everything are still like sharp and work because even like a lot of times you get issues with like high speed movement and like with uh yeah frame rate's always an issue with video generation yeah but even just a lot of motion blur in the shot with something like if you try to give it to runway like it doesn't always do the best with like uh you know whip pans or super shaky camera for sure and this stuff looks great and it's like he just needs to shoot he's shooting on the street and he just needs to shoot yeah the bus scene is he just needs to get the angle right of himself like everything else doesn't matter yeah the so the bus scene was really interesting how he pulled it off and it's the same way we pull it off in cg he modeled the bus with the people in the bus in blender and then did a camera move uh you know very low angle very small and then there's the couch pull that into comfy as a depth map and then comfy just generated the people and the bus based on that depth map yeah it's really unique yeah oh right now he becomes a giant in the city so yeah i thought this was oh god also you know he's running this entirely on his computer so it's all done right with one and other open source models so this is all done locally one person yeah or i think he's got maybe two people okay you do the camera person and i think he had someone else help him create the workflows but this is such a great workflow yeah that i thought was worth noting because yeah it really blends a lot of the stuff we've talked about this now when you say ai filmmaker this is what i'm thinking this is what you're thinking yeah this is a proper filmmaker and you're just using like that's why the whole you can't just call yourself a filmmaker when you're doing like vo3 text to video but he's not he's a filmmaker he's just augmenting the vfx work with like additional ai stuff yeah so he's a filmmaker right that's what i'm saying oh not an ai filmmaker well i'm saying that right i'm saying saying the ai filmmaker i feel like is is everything is generated.

29:16Yeah, and it's synthetic. It's like off-putting. And then the audio is from 11 Labs and the videos from this. And it's like... For now, yeah. I mean, sure. I'm sure that'll get better. And maybe eventually it'll just be filmmaker. It'll be a while. I think somebody like Mick will get there way faster than quote-unquote AI filmmaker as well. Or does he even... Is that what he's even going for? I would call him a hybrid filmmaker. I think he's just filmmaker. you're you're like a year ahead two years ahead of where yeah he made a short film yeah that you know okay you could have done this a while with how do you even do this pull this off normally after effects and you get to build a virtual environment all of that all of the above yeah yeah uh right it's both the 3d scenes and uh sometimes stuff wouldn't even work because you didn't shoot on green so you'd have to rotoscope manually right yeah yeah which is a pain and yeah yeah i don't know how long it took him to do this once he had the workflow built but i imagine not long yeah you know probably a week or two to like just yeah yeah there's a lot of shot to shot stuff yeah for me like the biggest advantage here is not necessarily the background generation but the fact that he's just shooting himself anywhere he pleases he yeah it's like as long as the no screen stuff he touches yeah and the angle is right yeah that's it that's it that's all he needs yeah he's not really recording camera tracking information that the lighting you know kind of is like yeah but you can relight you can't right that's more where i mean now we're getting back into the fix it in post like issue yeah well it's it's what we joked about a few episodes back like just put the camera in the corner put the camera anywhere just film everything and then you'll just reposition your shot we'll just redo it in post yeah cool i thought it was cool tutorial i think it's cool cool workflow good work make for a filmmaker come on come on the pause all right And then our last grouping, we've got a collection of stories of music and AI and AI in the music world.

31:07Yeah. There's a lot going on there. And traditionally, we don't really cover music all too much. But since there's so much going on, we thought we'd take a peek. I think also the music industry is good to look at because usually what happens there is like a step ahead of our industry. Into ours. Yeah. For sure. All right. So which one do I want to tackle first? because there are a couple of AI music bands making a big kind of stories. Yeah, so the one that fascinates me is there's a British creator called Oliver McCann with no musical background. He was a graphic designer. Graphic designer. And then he discovered, I guess, Suno?

31:43Yeah, he says he uses Suno to make the music and his Suno play had like 3 million plays. And now he has a record deal. Yeah, now he got signed with a record deal with Geffen, like records, right? What would actual musicians have to say about that? I'm sure they're not happy. Well, I mean, also, I mean, part of it was like, wait, this feels like an Onion article. Because it's an ABC News article. And then his quote is, I have no musical talent at all. I can't sing. I can't play instruments. And I have no musical background at all. That's like all of us, except for like 1 % of the population. But yeah, he started messing around with Suno.

32:20And one of his tracks racked up 3 million streams. Damn. and now he's been signed as a ai music creator yeah so this is where the world's going no i'm just joking look i think this is a fluke i think this is this level of success with not having any musical background is not it's like the equivalent of the blair witch project being like a total worldwide phenomena from like a forty thousand dollar short film that somebody shot like these things don't happen all the time and nor will they this feels different ish in the sense of like this feels like a weird fluke in this very specific moment in time yeah that won't really be replicated because it's like why do you need a person to do this if you're going down the ai music route what do you what do you need a person for like behind to make it right but i mean what like what that is an actual person and like you know him as the brand it's like you could just automate generate this oh no i mean the authenticity of that person and the fact that he doesn't know music adds to the lore i will say there was a quote i'm trying to find it because he did say that the suno songs the lyrics are you know bad and that he uh uh here uh quote uh ai lyrics tend to come out quite cliche and quite boring yeah uh and that he often writes his own lyrics and creates up to 100 different versions of a song before satisfaction so look that it does So yeah, he's doing some work.

33:43I mean, going through 100 different versions of a song. Creativity and that's input. And I mean, actually, that is important though because a record label wouldn't sign him if he can't copyright protect the music. Right. And from that copyright guide at the beginning of the year, it was humans need to be involved in part of the process for it to be protectable. It can't just be like generate, spit out, and you're done. So if he's writing the lyrics and then going back and forth with Juno, So the human involvement makes that, as we understand it now, it makes that copyright protectable. This is interesting, you know, that it's like, oh, we're signing him as like a creator.

34:21Whereas, okay, so the other stories, well, there's so many of the other stories, because the other stories are, there are AI music bands that are completely fake. On Spotify. Completely right. We got the one on Spotify. The Velvet Sundown is the band on Spotify that's fully synthetic. Exactly. An indie rock band that appears to be entirely AI generated is making alarming amounts of money on Spotify. uh they've got fake uh first of all images nobody makes money on spotify snoop dog came out and said he never made any money on spotify yeah but yeah they came out as like a quote real band and then it was revealed like oh it's like the photos the characters like the whole thing is like a made-up story and the music's generated i think because it's gimmicky it's successful but if you weigh it against it's a novelty now that's it it's capitalized on the novelty now yeah but yeah Yeah, that's like when when Vine came out and all those Vine TikTokers got big, like there was a first generation of them because like it was a new type of platform, new type of content.

35:20Origin story of the Paul brothers. Yeah. So all those guys, right? Lily Singh. Was she originally Vine? I think so. Like so we're having that moment now with Suno and AI music. but let me put it to you in this perspective would this type of success happen with a filmmaker who just texts to generates a film and then a warner brothers buys it for 10 million not warner brothers but it's like i mean we're sort of seeing this with uh you know the ai shorts or the generated clips like the weird ai stuff that keeps circulating of like the fruit that looks like a baby and the baby fruit is eating itself and there's just like all sorts of weird ai creations yeah i would not like i'm saying they rack up views on social media the kangaroo one no one is signing them the kangaroo right like that was a viral yeah that one was more in the realm of you weren't quite sure if it was real or not right the other ones are like clearly they're fake because there's no way they could be real but they're just like bizarro like tap into that kind of asmr market of like weird clip that people watch but it's not it warner to your point warner brothers is not signing them yeah so only in the music yeah and the music world feels much more experimental like they're more risk-taking than the media entertainment world that we're in i mean yeah maybe it's like oh we can ride cap some lightning in a bottle and ride this for a few months that's until my thought is just like well spotify is working on their own ai music generator stuff where it's like what do you need a person in the loop for making this when you could just have something just make music on demand especially if it is more of the background music kind of stuff like the lo-fi genre or the sleep genre or the relaxation genre where it's like you just make You can turn that out.

36:59Google has some experimental tools where you can adjust little knobs for like, what do you want it to sound like? And it just keeps generating lo-fi beat music forever. I could imagine like an elevator company. Otis is an elevator company. They would build in a GPU into every elevator. So you do local inference of a Suna model. So you just have elevator music just generating on the elevator. It's not even connected to the cloud. I think that's too... What, you don't think that's going to happen? I think that's too expensive and too high-tech for such a specific need. Like an elevator company. When was the last time you've heard elevator music?

37:39All the time. Where? I've never... Hotels. You go to Vegas hotels? They would have that. Besides a Vegas hotel, I can't think of any office building or residential. I've not heard elevator music. Lobbies have a lot of music. uh yeah yeah like uh hospital lobbies doctors lobbies no i mean lobbies do yeah but i mean elevators i mean it's la we don't have many lobby spaces yeah no i have a friend who actually programs they program the playlist for because like a lot of these like large like restaurants or lobbies yeah they need fresh music they need playlists like also lobbies are looking for not just like generic background music but actual like like the real songs song of the moment yeah that programs it in yeah but like they'll build out they have a whole system where it's like a playlist for the morning, playlist for the evening and stuff that transitions.

38:29And so it's like the whole day and environment and like locations are programmed and built out with playlists. Okay, fine. Maybe I went a little overboard there. But can I come back down to reality? All right. Here's my take on Spotify building their AI infinite generation thing. Dude, nobody will listen to that crap. I don't know about that. Come on, man. Well, I mean, if you're in the group where you're just like, I just need some background stuff. like i mean i'll load up spotify's uh you know the dj lo-fi beats hey joey what's up i got no i got tired of that um i just use playlists but i'll like load up playlists of like background beat music and uh you know like lo-fi or something and i'm not looking at who unless it's like a really good song i'm like i kind of like that i'll save it but like 90 of the songs like i don't i'm not looking at the name i don't know who it is it's just there for like work but that's a curation algorithm right it is curated of other music but i don't think it's a big stretch for spotify to just generate generate stuff that sounds like that that's like your next track is not this artist but it's just generated it's just generating the sounds but then you would listen to that maybe i mean some of the stuff on ceno is not that bad yeah for like background for like some videos and stuff i don't know i just feel like life is too short to listen to synthetic stuff and look at synthetic films.

39:48Like we're here to consume other humans' arts. And that's a big moment for us when we do that, right? I think it depends on the need and the use case or like what use case that thing is going for right now at that moment that you're trying to do. That's true. Like, I mean, the lo-fi girl, do they even say who the music is? Like, I only know where it's lo-fi girl, but it's just always playing. It's probably an entire team of people. but i don't think they even like i'm trying to think do they i don't think they like display you know like box tv like the song title and and creator i think it's just music on loop forever but like so anyone lo-fi girl is super popular except did she like graduate or something did they like kill the channel i think they said lo-fi girl you know graduated do you know what i'm talking about yeah okay but anyway it's just playing the music forever but you don't really know what the song is they're playing sure so like in that same lo-fi girl genre you could just spot like you just generate background music and um where lo-fi girl like the video or the track is being played in so many places you wouldn't otherwise expect right like in in an uber or something that kind of music yeah yeah like uh waymos uh yeah they've got like just this chill spa music playing right uh or you can pick other music but it's like start default to spa and it's just like as you're driving it's a robot's driving you around town and you're freaking out that it's like they're not gonna like turn into a car you're in an active police car chase that's playing chill music obviously sleep music's another huge genre too and it's like you're literally falling asleep so you're not gonna look at who the artist is yeah and then when it comes to like kids and babies to put them to sleep you need some type of lullaby music and yeah i'm sure there's a million that's what i said like i think i think there's room for both okay you know human and look i mean obviously spotify was trying to figure this out because it's easier to build the algorithm to play the music yeah and instead of paying people yeah it's passive income for them they're like why not we could just generate a whole cheaper than the royalties right for better or worse okay last one uh hicksfield our favorite company they also have uh their first ai idol it is an ai k-pop idol and the same thing they built a whole like you know using i assume hicksfield's tools keon music generator yeah music videos fake character the whole thing this is like the little nikaela type model for for k-pop yeah thing but then they're also like hey we want to make more models like you know be our next like ai model yeah it wouldn't be funny if somebody steals her i know we should yeah i feel like anything that hickfield does is on the table to uh copy replicate and run with it so yeah i mean this is an emerging genre of like music's gonna be you know i think first to be impacted by it like it's just gonna be a new genre on music i mean after the little michaela experiment with you know unreal engine based avatar we've had a few mild hits i don't see this as a thing like there will be attempts there will be many more keons i think but you might be too old we might be too old you're right like you're right for you know the target demo and to like where this would resonate or where they would not care like your kids might not care at all but like well the thing that with the younger generation i'm finding is they're yearning for and i'm super over generalizing here um in general the reason why 90s and 80s aesthetics are back they yearn for a time without connectivity with analog stuff that's why they're going back to wired headphones they're looking at kodak kodak gotta wait to see the photo so along that same sense i think they will desire a real connection with the real artist versus just the stuff that meta did initially you remember like the whole ai generated family that's posting photos yeah and now the weird like um chatbots like as much as we despise it i think the younger generation will despise it more because they will be much more inundated by it than we will So I think there's a correction period that's already happening.

43:57And with more AI slop, you'll have a harder correction. Yeah. And it's like, how do you do an in-person event for your AI K-pop star? Like, how do you make things that you can, you know, go to and connect with other people? Yeah, because concerts make money, right? Concerts make money. Yeah. I mean. So is it just a giant TV screen? You have no talent. It's an LED wall. Right. But I mean, if you're, you know, your AI K-pop star, you do not have to pay them a bunch of money because they're not real. so like the margins are better it with a you know if you just are streaming and building out an online uh portfolio of an ai k-pop star but you don't you know there's no the connection you could have with an ai character is limited like we talked about the little stuff the the flip side of that is there is a small percentage of population who will absolutely connect with kion like a synthetic avatar and they've you know there are people that connect to characters that don't exist at all like a luke skywalker right yeah for sure yeah or yeah i mean the whole world of anime and stuff and anime characters i mean but then a lot of times those people go to conventions and connect with other people who also like the same thing yes so there's still that there will be a community communal element uh and stuff and yeah last thing this just goes back to like what i think we've been saying before where it's like if you are a creator in the world where like AI automation is like, or AI generation is creeping in.

45:19Like, I think that's where having a personal brand or like having like something about yourself that you are a person that people can connect to is gonna be the differentiator. For sure. Besides just the actual work itself, because like it's getting so easy for like the output to be generated or copied or spit out. But if it's like something that people can connect to, like a person, I think that's gonna be the buffer to like you know survive when like everything can just be generated in two seconds in a world where we're going to be drowning in a sea of noise essentially finding something authentic and connecting to it is going to be the thing that we yearn for hopefully it's as beautiful as that if you know i i hope we're not going into a world where you know it's just the commonplace thing to do is to just have an ai friend or go to an ai concert or look at an ai movie maybe that's not the world that i want to live in i don't i think i think it'll be fine i mean look at you know the record numbers of people turned out for the minecraft movie and the the minecraft experience and uh the k-pop uh demon hunters yeah you know like yeah because oh so i just found out they went to go party and hang out netflix's biggest movie to date yeah just passed the most viewed yeah yeah biggest box office for the weekend last weekend yeah i think they uh they uh average it by number of hours viewed and or number of viewers i think it's at 237 million at the moment yeah much higher than anything else yeah yeah i hope that it's a musical and has songs because the stuff with songs yeah has that repeatability oh yeah i think they're already working on a sequel yeah i saw yeah but yeah look at the popularity of that people went out to the theater to like go hang out with their friends and like you know go sing along at a musical so i think i think the human element of like going to stuff is hopefully will always be there.

47:05Great. Great note to end on. Good point to end on. All right. Let us know what you think. Thanks for everything we talked about at denoisedpodcast.com. If you want to go back to our previous episodes on YouTube, we have tons of them, I think over 60 of them. So give some of our older episodes a watch and comment on it. Thanks everyone. We'll catch you in the next episode.