WEBVTT 00:00:00.000 --> 00:00:03.140 I want you to picture the year, say, 2015. Okay. 00:00:03.240 --> 00:00:07.280 If you wanted a high -end cinematic motion graphic, 00:00:07.559 --> 00:00:09.099 you know, something that looked like a Nike commercial, 00:00:09.359 --> 00:00:14.140 or a sleek tech explainer, you had exactly two 00:00:14.140 --> 00:00:16.420 options. Right. You either paid a specialized 00:00:16.420 --> 00:00:19.320 freelancer, maybe upwards of $100 per video, 00:00:19.500 --> 00:00:22.600 or you spent three days locked in a room trying 00:00:22.600 --> 00:00:24.839 to figure out keyframes and after effects. Oh, 00:00:24.859 --> 00:00:27.489 the pain. It was a completely gate -kept art 00:00:27.489 --> 00:00:29.989 form. You needed that wizardry just to get in 00:00:29.989 --> 00:00:32.130 the door. It was expensive, and frankly, it was 00:00:32.130 --> 00:00:34.609 painful. But here we are. It's 2026. And things 00:00:34.609 --> 00:00:37.469 have changed. The cost has dropped from $100 00:00:37.469 --> 00:00:42.119 to near zero. And the time, three days to maybe 00:00:42.119 --> 00:00:45.100 15 minutes. And the skill requirement is. It's 00:00:45.100 --> 00:00:47.100 just not there anymore. So today we're exploring 00:00:47.100 --> 00:00:50.880 this democratization of high -end motion design. 00:00:51.000 --> 00:00:52.880 And we aren't just talking about making things 00:00:52.880 --> 00:00:55.859 look pretty. We're doing a deep dive into a really 00:00:55.859 --> 00:00:59.200 comprehensive breakdown by Max Ann from AI Fire. 00:00:59.380 --> 00:01:03.500 He lays out exactly how to master the 2026 AI 00:01:03.500 --> 00:01:06.739 stack. to recreate some of the most viral styles 00:01:06.739 --> 00:01:09.459 on the internet right now. Specifically, we're 00:01:09.459 --> 00:01:11.180 going to look at that Dan Coe minimalist style 00:01:11.180 --> 00:01:14.659 and the Legacy Academy avatar style. I'm interested 00:01:14.659 --> 00:01:16.920 in this because it sits right at that intersection 00:01:16.920 --> 00:01:21.180 of creativity and what I'd call industrialized 00:01:21.180 --> 00:01:24.099 art. We have a lot to cover. We're going to look 00:01:24.099 --> 00:01:27.040 at the data, why these faceless videos are seemingly 00:01:27.040 --> 00:01:29.840 outperforming personality -driven content. Then 00:01:29.840 --> 00:01:31.700 the specific tools. And then we'll walk through 00:01:31.700 --> 00:01:34.099 three specific workflows you can use right now. 00:01:34.359 --> 00:01:36.459 Yeah, the workflows are the real meat here. We're 00:01:36.459 --> 00:01:39.439 going to get into the weeds of VO 3 .1, custom 00:01:39.439 --> 00:01:42.040 prompting, and a model called Nanner Banana Pro. 00:01:42.560 --> 00:01:44.840 Mano Banana Pro. Okay. I have some questions 00:01:44.840 --> 00:01:46.739 about that name, but we'll get there. First, 00:01:46.900 --> 00:01:49.079 let's look at the why. Yeah. Because for a long 00:01:49.079 --> 00:01:51.040 time, the common wisdom was people follow people. 00:01:51.180 --> 00:01:53.819 You need a face. You need a personality. Authenticity. 00:01:53.879 --> 00:01:56.480 Right. That was the buzzword. Exactly. But the 00:01:56.480 --> 00:01:59.099 data in this deep dive suggests something else 00:01:59.099 --> 00:02:01.159 is happening. It really flips it on its head. 00:02:01.760 --> 00:02:05.019 Max Anne points to two massive examples. First, 00:02:05.200 --> 00:02:07.700 you have Legacy Academy. Right. It's a faceless 00:02:07.700 --> 00:02:10.740 business page. They average over 50 ,000 views 00:02:10.740 --> 00:02:13.110 per post. with some spikes hitting a million. 00:02:13.629 --> 00:02:17.210 And they never, ever show a human face. Just 00:02:17.210 --> 00:02:19.770 motion graphics and avatars? And then on the 00:02:19.770 --> 00:02:22.150 other side, the personal brand side, you have 00:02:22.150 --> 00:02:25.650 Dan Coe. The king of minimalism. He hit 580 ,000 00:02:25.650 --> 00:02:27.969 likes on a single post. And it wasn't a selfie. 00:02:28.110 --> 00:02:29.990 It wasn't a dance trend. It was a black and white 00:02:29.990 --> 00:02:33.169 animated graphic. That is a staggering number 00:02:33.169 --> 00:02:36.069 for just text on a screen. But I have to play 00:02:36.069 --> 00:02:37.990 devil's advocate for a second. Go for it. Does 00:02:37.990 --> 00:02:39.990 this actually build a brand or does it just build 00:02:39.990 --> 00:02:42.330 view counts? Are people connecting with Dan Coe, 00:02:42.370 --> 00:02:45.469 the person, or just the aesthetic? That's the 00:02:45.469 --> 00:02:47.430 key question, right? The philosophy here, the 00:02:47.430 --> 00:02:50.150 core insight Max Anne drives home, is that clarity 00:02:50.150 --> 00:02:53.969 beats novelty. In 2026, we're just drowning in 00:02:53.969 --> 00:02:57.469 noise. So complex ideas made simple, that's the 00:02:57.469 --> 00:03:00.240 new viral currency. So you strip away the influencer, 00:03:00.460 --> 00:03:03.500 the ego, the vlog look. And the viewer focuses 00:03:03.500 --> 00:03:07.080 entirely on the idea, not the messenger. So probing 00:03:07.080 --> 00:03:09.900 a bit deeper then. Why do you think removing 00:03:09.900 --> 00:03:13.439 the human face actually increases retention for 00:03:13.439 --> 00:03:16.699 these specific niches like finance or tech or 00:03:16.699 --> 00:03:19.620 stoicism? Because the signal to noise ratio is 00:03:19.620 --> 00:03:22.340 just higher. You're not analyzing a facial expression. 00:03:22.500 --> 00:03:25.000 You're processing a concept. It's pure efficiency. 00:03:25.419 --> 00:03:27.819 Okay, let's get practical. If we want to build 00:03:27.819 --> 00:03:30.360 these, we can't just, you know, slap text on 00:03:30.360 --> 00:03:32.259 a background and hope for the best. No, we are 00:03:32.259 --> 00:03:34.479 terrible at that kind of consistency. That's 00:03:34.479 --> 00:03:36.460 why there's a framework. The source breaks it 00:03:36.460 --> 00:03:38.599 down into a five -step anatomy. And if you violate 00:03:38.599 --> 00:03:41.439 these... The algorithm punishes you. Number one 00:03:41.439 --> 00:03:43.939 is timing. Visuals have to change every two to 00:03:43.939 --> 00:03:46.340 three seconds. That feels incredibly fast. It 00:03:46.340 --> 00:03:48.400 is, but attention spans are what they are. You 00:03:48.400 --> 00:03:50.659 have to lock them in. Number two is simplicity. 00:03:51.340 --> 00:03:54.159 The rule is, if the message isn't clear in three 00:03:54.159 --> 00:03:57.210 seconds, it fails. Brutal. Number three is text. 00:03:57.710 --> 00:04:00.710 Readable typography beats design flair every 00:04:00.710 --> 00:04:04.629 time. Okay. Number four, audio sync. This is 00:04:04.629 --> 00:04:07.110 crucial. The visuals have to hit on the beat 00:04:07.110 --> 00:04:09.169 or the voiceover emphasis. They call it Mickey 00:04:09.169 --> 00:04:11.189 Mousing in the industry. Yeah, like in the old 00:04:11.189 --> 00:04:14.210 cartoons, every footstep has a sound. Every text 00:04:14.210 --> 00:04:17.350 pop has a click. It ties the visual to the audio 00:04:17.350 --> 00:04:19.589 so tightly that your brain just can't look away. 00:04:19.870 --> 00:04:22.410 And the fifth element? Pacing. It needs to be 00:04:22.410 --> 00:04:26.300 calm and purposeful, not frantic. That's a delicate 00:04:26.300 --> 00:04:28.860 balance, isn't it? Calm pacing, but changing 00:04:28.860 --> 00:04:31.600 every three seconds. It's about flow, not chaos. 00:04:32.360 --> 00:04:34.879 So we know the rules. Now we need the tools. 00:04:35.019 --> 00:04:38.199 This is where that 2026 toolkit comes in. Walk 00:04:38.199 --> 00:04:40.560 us through the specific stack this guide recommends. 00:04:40.899 --> 00:04:43.769 It's basically a four -part harmony. First, for 00:04:43.769 --> 00:04:45.870 motion generation, actually making things move, 00:04:45.910 --> 00:04:48.870 we're using VO 3 .1. Okay, VO. That's the heavy 00:04:48.870 --> 00:04:50.490 lifter. Then for the image generation, we're 00:04:50.490 --> 00:04:52.870 using Google Flow, and it's running the Nano 00:04:52.870 --> 00:04:55.050 Banana Pro model. I'm sorry, did you say Nano 00:04:55.050 --> 00:04:57.790 Banana? We're trusting our brand strategy to 00:04:57.790 --> 00:04:59.329 something that sounds like a smoothie ingredient. 00:04:59.610 --> 00:05:02.490 I know, I know. It sounds ridiculous. But technically, 00:05:02.649 --> 00:05:05.569 it's a specific fine -tuned model. It's optimized 00:05:05.569 --> 00:05:09.329 for consistency and specific artistic styles. 00:05:09.449 --> 00:05:11.490 The community names these things in, well... 00:05:11.660 --> 00:05:14.339 Nano banana stuck. But it is a powerhouse. Okay, 00:05:14.399 --> 00:05:16.620 I'll trust the banana. What's next? Then you 00:05:16.620 --> 00:05:19.639 have ChatGPT and Gemini 3 Flash. You're using 00:05:19.639 --> 00:05:22.600 these for prompting, and this part is cool for 00:05:22.600 --> 00:05:25.500 video analysis. Interesting. And finally, CapCut 00:05:25.500 --> 00:05:27.699 for assembly. And before you even open those 00:05:27.699 --> 00:05:30.300 tools, the guide mentions a secret weapon. Pinterest. 00:05:30.459 --> 00:05:33.360 Yes. It's not just for recipes anymore. You search 00:05:33.360 --> 00:05:37.470 kinetic typography. or logo animation the goal 00:05:37.470 --> 00:05:39.829 is to find a visual direction before you start 00:05:39.829 --> 00:05:42.829 prompting you're curating not guessing it seems 00:05:42.829 --> 00:05:45.149 like the human element has really shifted from 00:05:45.149 --> 00:05:50.269 creation to uh curation is the skill now just 00:05:50.269 --> 00:05:54.050 taste in a way yeah you're the director now not 00:05:54.050 --> 00:05:56.769 the animator you decide the shot and the ai handles 00:05:56.769 --> 00:05:59.750 the pixels okay director let's yell action I 00:05:59.750 --> 00:06:01.529 want to walk through that first workflow, the 00:06:01.529 --> 00:06:04.029 elegant cinematic style. The guide says this 00:06:04.029 --> 00:06:05.589 looks like a high -end commercial. How do we 00:06:05.589 --> 00:06:07.709 build it? This one is all about trust and high 00:06:07.709 --> 00:06:10.230 aesthetic. So step one is getting the prompt 00:06:10.230 --> 00:06:12.790 right. And we don't just guess. We use ChatGPT 00:06:12.790 --> 00:06:16.069 to act as a nano -banana prompt optimizer. What 00:06:16.069 --> 00:06:18.370 does that mean, practically speaking? You tell 00:06:18.370 --> 00:06:21.129 ChatGPT, I'm going to give you a scenario. You 00:06:21.129 --> 00:06:23.120 write the prompt for the image generator. But 00:06:23.120 --> 00:06:27.019 here's the trick. You ask for the output in standard 00:06:27.019 --> 00:06:30.620 paragraph form that strictly follows JSON logic. 00:06:30.800 --> 00:06:33.300 JSON logic. I know what JSON is in code, but 00:06:33.300 --> 00:06:35.560 why apply that here? This is a really important 00:06:35.560 --> 00:06:38.339 nuance. If you just write a long paragraph to 00:06:38.339 --> 00:06:40.680 an image generator, the model tends to focus 00:06:40.680 --> 00:06:42.779 heavily on the first few words and ignore the 00:06:42.779 --> 00:06:45.360 end. Okay, it gets lost. Yeah, it sort of bleeds 00:06:45.360 --> 00:06:47.459 the concepts together. But if you structure it 00:06:47.459 --> 00:06:49.839 with JSON logic, you know, brackets for lighting, 00:06:50.000 --> 00:06:53.199 subject. camera angle, you're forcing the AI 00:06:53.199 --> 00:06:55.680 to treat each element as a distinct constraint. 00:06:55.959 --> 00:06:57.759 So the lighting doesn't bleed into the texture. 00:06:58.079 --> 00:07:00.480 Exactly. It cuts down on hallucinations significantly. 00:07:00.860 --> 00:07:03.060 That is a fascinating workaround. So we have 00:07:03.060 --> 00:07:05.180 our optimized prompt. What's next? Then we go 00:07:05.180 --> 00:07:07.139 to Google Flow with that Nano Banana Pro model. 00:07:07.220 --> 00:07:10.040 We set the aspect ratio to 9 .16 for mobile. 00:07:10.180 --> 00:07:12.759 And here's the crucial detail. We generate two 00:07:12.759 --> 00:07:16.160 keyframes, a start frame and an end frame. Why 00:07:16.160 --> 00:07:18.759 two? Why not just one and let the AI improvise? 00:07:18.920 --> 00:07:21.620 Because we want control. In the old days, you'd 00:07:21.620 --> 00:07:23.459 give it one image and say zoom out and the person 00:07:23.459 --> 00:07:25.680 might morph into a car. Or grow a third arm. 00:07:25.720 --> 00:07:28.360 Yeah, the classic AI horror show. Exactly. Yeah. 00:07:28.439 --> 00:07:31.579 But with Vio 3 .1, you upload the start and the 00:07:31.579 --> 00:07:34.959 end. You define the destination. Then you prompt 00:07:34.959 --> 00:07:37.540 the motion between them. For example, slow zoom 00:07:37.540 --> 00:07:40.879 out, silhouette pushing stone. So Vio isn't just 00:07:40.879 --> 00:07:43.220 hallucinating, it's connecting the dots. It's 00:07:43.220 --> 00:07:45.529 connecting the dots. And it's not just morphing 00:07:45.529 --> 00:07:49.029 pixels. VO 3 .1 has a deep understanding of object 00:07:49.029 --> 00:07:51.709 permanence and mass. It actually predicts how 00:07:51.709 --> 00:07:53.730 that stone should move. And I read in the notes 00:07:53.730 --> 00:07:56.089 that it adds sound, too. It does. It generates 00:07:56.089 --> 00:07:58.069 the whooshes and crunches automatically. Whoa, 00:07:58.370 --> 00:08:00.370 okay, that's amazing. I have to be skeptical 00:08:00.370 --> 00:08:03.589 there, though. Usually AI sound is kind of tinny 00:08:03.589 --> 00:08:06.430 and generic. Is it actually usable? For a quick 00:08:06.430 --> 00:08:09.060 social post, it's surprisingly good. But if you're 00:08:09.060 --> 00:08:12.120 Legacy Academy, you're probably layering a high 00:08:12.120 --> 00:08:15.079 -quality Foley track on top and cap cut. It gets 00:08:15.079 --> 00:08:17.279 you, say, 80 % of the way there. Fair enough. 00:08:17.339 --> 00:08:19.019 I want to circle back to that two -frame technique. 00:08:19.759 --> 00:08:22.939 Why is the end frame so critical in this workflow 00:08:22.939 --> 00:08:25.819 compared to just prompting a video from one image? 00:08:26.139 --> 00:08:28.920 It acts as a guardrail. It prevents the AI from 00:08:28.920 --> 00:08:32.440 just drifting off script. Like giving a GPS a 00:08:32.440 --> 00:08:34.340 destination instead of just a compass heading. 00:08:34.620 --> 00:08:37.620 Okay, let's shift to style number two. the avatar 00:08:37.620 --> 00:08:40.659 based business the legacy academy style right 00:08:40.659 --> 00:08:43.159 this is for people who want a consistent brand 00:08:43.159 --> 00:08:46.539 identity without being on camera the workflow 00:08:46.539 --> 00:08:48.919 is similar to the cinematic one but the entire 00:08:48.919 --> 00:08:51.919 focus is on that reference image slot in google 00:08:51.919 --> 00:08:53.899 flow this is the part that usually falls apart 00:08:53.899 --> 00:08:55.600 right the character looks different in every 00:08:55.600 --> 00:08:59.120 video for sure but now banana solves that You 00:08:59.120 --> 00:09:01.379 create a master sheet. You define your avatar 00:09:01.379 --> 00:09:04.000 in a T -pose, then a side profile, a close -up. 00:09:04.080 --> 00:09:06.500 You upload that whole cluster into the reference 00:09:06.500 --> 00:09:08.639 image slot. So you're basically training it on 00:09:08.639 --> 00:09:11.240 the geometry of the face. Essentially. You define 00:09:11.240 --> 00:09:14.080 the hoodie, the posture, the brand colors once. 00:09:14.620 --> 00:09:17.500 Then every time you prompt a new scene. Avatar 00:09:17.500 --> 00:09:20.559 at a desk, avatar looking at a city, the model 00:09:20.559 --> 00:09:23.460 checks against that reference. It forces the 00:09:23.460 --> 00:09:25.799 pixels to align with that master identity. That 00:09:25.799 --> 00:09:27.960 solves the consistency problem. But does this 00:09:27.960 --> 00:09:30.759 replace the need for a human influencer entirely? 00:09:31.279 --> 00:09:35.000 I mean, can a cartoon really sell a high -ticket 00:09:35.000 --> 00:09:38.080 product? Well, the data says yes. For these information 00:09:38.080 --> 00:09:40.399 -heavy niches, the avatar becomes the anchor. 00:09:40.840 --> 00:09:43.299 It's less about I trust this person and more 00:09:43.299 --> 00:09:46.200 I recognize this symbol of knowledge. The mascot 00:09:46.200 --> 00:09:48.620 for the modern age. I guess Geico has been doing 00:09:48.620 --> 00:09:51.580 it with a gecko for decades. Precisely. We just 00:09:51.580 --> 00:09:53.299 have better tools now. Okay, let's get to the 00:09:53.299 --> 00:09:54.879 third style. This is the one I see everywhere. 00:09:55.019 --> 00:09:57.399 The Dan Coe minimalist style. Black and white, 00:09:57.519 --> 00:10:00.279 super high contrast. The king of minimalist motion. 00:10:00.860 --> 00:10:03.100 This workflow is fascinating because it's all 00:10:03.100 --> 00:10:05.279 about reverse engineering. How so? The guide 00:10:05.279 --> 00:10:07.659 suggests you literally download a viral video 00:10:07.659 --> 00:10:10.200 that you like. Then you upload the video file 00:10:10.200 --> 00:10:12.659 itself to Gemini 3 Flash. You upload the whole 00:10:12.659 --> 00:10:15.440 video file? The whole file. Gemini has a massive 00:10:15.440 --> 00:10:18.220 context window now. You ask it to analyze the 00:10:18.220 --> 00:10:20.600 structure, break down the transitions, the segments, 00:10:20.759 --> 00:10:23.799 and here's the magic part. Generate image prompts 00:10:23.799 --> 00:10:25.799 for the first frame of every single segment. 00:10:26.059 --> 00:10:29.740 Wow. So you're using AI to deconstruct the viral 00:10:29.740 --> 00:10:32.139 hit into its component prompts? It gives you 00:10:32.139 --> 00:10:34.320 the recipe. Then you take those prompts to Google 00:10:34.320 --> 00:10:37.029 Flow. But there's a key difference here. For 00:10:37.029 --> 00:10:39.049 this minimalist style, you only use the start 00:10:39.049 --> 00:10:42.210 frame in video 3 .1. Oh, so you drop the end 00:10:42.210 --> 00:10:44.370 frame. Why? Because the motion in these videos 00:10:44.370 --> 00:10:47.450 is incredibly subtle. It's just a slow drift 00:10:47.450 --> 00:10:50.090 or a bit of grain moving. You don't need a complex 00:10:50.090 --> 00:10:52.649 trajectory. You just need it to feel alive. That 00:10:52.649 --> 00:10:55.070 makes it faster to produce, too. Much faster. 00:10:55.570 --> 00:10:57.870 But the real magic, the part most people miss, 00:10:58.090 --> 00:11:00.610 happens in CapCut. It's an editing technique 00:11:00.610 --> 00:11:03.309 called the pattern interrupt. Tell me about that. 00:11:03.549 --> 00:11:05.909 It's how they handle the text. They take the 00:11:05.909 --> 00:11:08.789 captions. and physically split them. Half the 00:11:08.789 --> 00:11:10.850 sentence appears at the top of the screen, the 00:11:10.850 --> 00:11:12.990 other half appears at the bottom. I've noticed 00:11:12.990 --> 00:11:14.850 that. It's actually kind of annoying to read, 00:11:14.870 --> 00:11:17.409 but I can't look away. That's the point. It forces 00:11:17.409 --> 00:11:19.669 your eye to scan the whole screen vertically. 00:11:19.889 --> 00:11:22.509 It keeps the brain active and engaged. It makes 00:11:22.509 --> 00:11:25.789 reading a physical activity. Very clever. I have 00:11:25.789 --> 00:11:28.110 to admit, I still wrestle with prompt drift myself. 00:11:28.799 --> 00:11:30.960 Oh, yeah. Yeah, you know where the style changes 00:11:30.960 --> 00:11:33.500 slightly between scenes. One looks like a sketch, 00:11:33.659 --> 00:11:36.480 the next looks like vector art. This Gemini analysis 00:11:36.480 --> 00:11:39.039 method seems like it would solve that. It does, 00:11:39.139 --> 00:11:41.659 because Gemini generates the prompts for all 00:11:41.659 --> 00:11:44.120 the segments at once, based on that one consistent 00:11:44.120 --> 00:11:46.559 video. The style descriptors stay locked in. 00:11:46.840 --> 00:11:49.480 So back to the text splitting top and bottom. 00:11:50.110 --> 00:11:52.710 Why does that specific edit work so well? It 00:11:52.710 --> 00:11:55.470 just prevents the zombie scroll. It demands active 00:11:55.470 --> 00:11:57.789 participation from the viewer's eyes. Okay, we've 00:11:57.789 --> 00:11:59.509 got the styles, but I know people are going to 00:11:59.509 --> 00:12:02.029 try this and mess it up. What are the traps? 00:12:02.210 --> 00:12:05.429 What kills performance? Max Anne lists four main 00:12:05.429 --> 00:12:07.929 killers. The first one is complexity. Just trying 00:12:07.929 --> 00:12:09.509 to be too clever with too many elements. Keep 00:12:09.509 --> 00:12:11.830 it simple. The second is bad sync. We talked 00:12:11.830 --> 00:12:15.269 about Mickey mousing. If the visual hit misses 00:12:15.269 --> 00:12:19.059 the audio beat by even a few frames. It just 00:12:19.059 --> 00:12:22.019 feels amateur. The flow breaks. Like a drummer 00:12:22.019 --> 00:12:25.559 playing out of time. Exactly. Third is low resolution. 00:12:26.179 --> 00:12:29.539 If you don't upscale to 4K with a tool like Topaz, 00:12:29.720 --> 00:12:33.600 people just scroll past. It signals low value. 00:12:33.860 --> 00:12:37.159 And the fourth? Silence. Silence. But we just 00:12:37.159 --> 00:12:39.980 talked about visual clarity. Sound is 50 % of 00:12:39.980 --> 00:12:42.100 the video, even if there's no music. You need 00:12:42.100 --> 00:12:44.690 the raw voiceover. And you need those specific 00:12:44.690 --> 00:12:47.250 sound effects, the whooshes, the pops, the subtle 00:12:47.250 --> 00:12:50.350 beats to punctuate the motion. Silence kills 00:12:50.350 --> 00:12:53.129 engagement. So if you had to pick one, which 00:12:53.129 --> 00:12:56.330 of these is the most common rookie mistake? Overcomplicating. 00:12:56.470 --> 00:12:58.990 Trying to show too much instead of one clear 00:12:58.990 --> 00:13:01.730 idea. It all comes back to clarity beats novelty. 00:13:02.649 --> 00:13:04.529 Okay, let's take a quick break. We'll be right 00:13:04.529 --> 00:13:07.679 back. So let's recap the big picture here. Motion 00:13:07.679 --> 00:13:09.899 graphics are winning because they simplify complex 00:13:09.899 --> 00:13:13.120 ideas in a very noisy world. And the barrier 00:13:13.120 --> 00:13:15.259 to entry has completely collapsed. You don't 00:13:15.259 --> 00:13:17.000 need to be a motion graphics artist anymore. 00:13:17.200 --> 00:13:19.960 You need to be a stack operator. A stack operator. 00:13:20.019 --> 00:13:21.980 Yeah, you need to know how to weave VO, Nano 00:13:21.980 --> 00:13:24.379 Banana, and CapCut together. And the workflows 00:13:24.379 --> 00:13:27.059 themselves are replicable. Whether you want that 00:13:27.059 --> 00:13:30.120 cinematic look, the avatar brand, or the minimalist 00:13:30.120 --> 00:13:33.580 aesthetic, the path is pretty much paved. Max 00:13:33.580 --> 00:13:35.220 And actually ends his guide with a challenge, 00:13:35.299 --> 00:13:36.779 and I think we should pass it on. Let's hear 00:13:36.779 --> 00:13:39.929 it. Create one motion graphic this week using 00:13:39.929 --> 00:13:43.909 one of these workflows. Just one. Post it and 00:13:43.909 --> 00:13:46.210 see what happens. I love that. It's about getting 00:13:46.210 --> 00:13:48.450 your hands dirty. You know, it really makes you 00:13:48.450 --> 00:13:50.730 reflect on how the definition of creativity itself 00:13:50.730 --> 00:13:53.850 is changing. How so? It's moving from manual 00:13:53.850 --> 00:13:57.649 labor, literally moving pixels around to intellectual 00:13:57.649 --> 00:14:00.210 selection. It's about having the pace to know 00:14:00.210 --> 00:14:02.509 what to make, not just how to make it. The tools 00:14:02.509 --> 00:14:04.690 are infinite. The constraint is your imagination. 00:14:05.389 --> 00:14:07.269 A provocative thought to leave you with then. 00:14:07.669 --> 00:14:10.990 If everyone can produce high -end, perfect motion 00:14:10.990 --> 00:14:14.490 graphics in minutes, what becomes the next signal 00:14:14.490 --> 00:14:17.230 of quality? When perfect is cheap, maybe the 00:14:17.230 --> 00:14:20.090 flaws, the shaky camera, the bad lighting, the 00:14:20.090 --> 00:14:22.929 human error will become the new premium. Something 00:14:22.929 --> 00:14:24.690 to think about. Thanks for listening to this 00:14:24.690 --> 00:14:26.149 deep dive. See you in the next one.