Big Idea

The argument in one line.

The premium 'cinematic scroll journey' website — a genre normally built by expensive motion designers — can be produced almost entirely by one AI coding agent chaining together an ideation model, a video generation model, a frame-interpolation model, and a code generator, for the cost of the API credits alone.

Who This Is For

Read if. Skip if.

READ IF YOU ARE…

You build landing pages or portfolio sites and want a way to make a scroll-driven hero video without hiring a motion designer.
You already use an AI coding agent (Claude Code, Kimi Code, etc.) and want a concrete example of chaining multiple AI tools together via MCP.
You're curious what a fully agent-driven web build workflow looks like end to end, from concept to a deployed public URL.
You want copy-paste-able prompts for generating a cinematic 'macro journey' video concept and turning it into a working site.

SKIP IF…

You need a fully custom, brand-specific design system — this produces a single striking hero effect, not a complete design language.
You're not willing to sign up for and pay small credit amounts across two paid tools (Higgsfield video credits and a Kimi Code plan).

TL;DR

The full version, fast.

The video walks through building a scroll-driven 'cinematic journey' website end to end using AI. First, Kimi K3 (a coding-agent chatbot) generates ten concept ideas for an 8-second macro camera journey, then turns the chosen concept into a detailed video-generation prompt. That prompt goes into Higgsfield's Cinematic Studio 3.0 to generate an 8-second video, which gets interpolated from 30fps to 60fps with ByteDance's AIGC model so it doesn't look choppy when tied to scroll. Rather than doing each step by hand, the creator connects Higgsfield to Kimi Code via MCP so the agent can generate, interpolate, and fetch videos directly from the terminal, then feeds it a master prompt that builds the full React/Tailwind/GSAP site around the video and deploys it to Netlify with an API token. The conclusion: a single 'go nuts' prompt can run this entire pipeline unattended, producing a finished, deployed cinematic website for the cost of a couple dollars in AI credits.

Free for members

Chat with this breakdown — free.

Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.

Create a free account →

Chapters

Where the time goes.

00:00 – 00:43

01 · The claim

Cold open scrolling through a finished cinematic site; states the video will hand over both the process and the exact prompts.

00:43 – 01:43

02 · How the scroll trick works

Explains that scroll sites are just a video bound to scroll position, frame by frame, plus a tour/autoplay mode.

01:43 – 03:47

03 · Signing into Kimi Code

Signs up for a Kimi subscription, installs Kimi Code via a terminal curl command, and logs in via OAuth.

03:47 – 05:35

04 · Generating ten site concepts

Feeds Kimi a 'creative director' prompt asking for ten radically different scroll-driven landing page concepts, each built around an 8-second macro camera journey.

05:35 – 06:56

05 · Picking concepts and saving them

Reviews the whiskey, capsule/skincare, and other concepts Kimi generated, picks three favorites, and saves them into a Google Doc.

06:56 – 08:13

06 · Turning a concept into a video prompt

Uses a second Kimi prompt, seeded with an example of the desired detail level, to convert a chosen concept into a precise cinematic video-generation prompt.

08:13 – 08:27

07 · The three-step pipeline, whiteboard version

States the three-step creative pipeline on a plain slide: generate the macro journey video with Cinematic Studio 3.0, interpolate to 60fps with ByteDance AIGC, tie it frame-by-frame to scroll.

08:27 – 11:32

08 · Generating video in Higgsfield

Pastes the Kimi-written prompt into Higgsfield's Cinema Studio 3.0, sets resolution and duration, and generates three concept videos simultaneously to increase the odds of a usable result.

11:32 – 14:05

09 · Connecting Higgsfield to Kimi via MCP

Adds Higgsfield as an MCP server inside Kimi Code so the agent can generate and interpolate videos directly from the terminal instead of the browser.

14:05 – 16:21

10 · Interpolating and running two agents at once

Has Kimi interpolate the three downloaded videos to 60fps using ByteDance AIGC via MCP, and opens a second Kimi session in YOLO mode to work on the website while interpolation runs.

16:21 – 17:48

11 · The site-building master prompt

Pastes a long, pre-written 'site prompt' into Kimi along with the video file path and the original concept text, so the agent builds the full interactive site around the footage.

17:48 – 18:21

12 · Result: the finished, working site

Shows the finished capsule/skincare site live in the browser — smooth scroll journey, click-to-jump sections, and a 'hold to reverse' interaction.

18:21 – 19:16

13 · Deploying to Netlify

Generates a Netlify personal access token and hands it to Kimi, which deploys the site live to a netlify.app subdomain without any manual dashboard steps.

19:16 – 21:17

14 · The one-prompt version

Reveals a single master prompt that runs the entire pipeline end to end — Kimi asks what subject/industry to build around, then generates, interpolates, builds, and deploys unattended; shows a gallery of resulting sites (hot air balloon, dark cave, foundry).

21:17 – 21:39

15 · Close and pitch

Points to the free prompt library (Maker Zero) and the paid client-acquisition program (Maker School) before signing off.

Atomic Insights

Lines worth screenshotting.

A scroll-driven cinematic website is structurally just a video bound to scroll position — every frame becomes a scene, and scrolling up or down moves forward or backward through it.
AI is far better at generating a wide space of creative concepts than at picking the best one; the efficient workflow is to have AI ideate broadly and let a human apply taste to select.
Video generated at 30fps looks visibly choppy once tied to scroll, because a user can pause on any single frame; interpolating to 60fps with a model like ByteDance's AIGC removes most of the jank.
Batching three video generations simultaneously trades AI credits for time, which is worth it because AI video outputs are typically only satisfying 30-50% of the time on a single attempt.
Connecting a video generation platform to a coding agent via MCP collapses a five-tool manual workflow (chat for ideas, copy prompt, paste into video tool, download, feed to coding agent) into a single terminal session.
A well-structured master prompt can encode an entire multi-stage pipeline (concept generation, video generation, interpolation, site scaffolding, deployment) so the agent runs the whole process from one instruction.
Publishing a fully working site requires nothing more than a static host's API token handed to the coding agent — no manual dashboard clicking once that credential exists.
The creative asset — the background video — is the actual heavy lifter of the visual impression; the surrounding interactive scaffolding is comparatively easy for a coding agent to produce.

Takeaway

AI tool-chaining beats manual copy-paste for creative pipelines

WHAT TO LEARN

Connecting AI tools together with MCP so one agent can drive several platforms turns a five-step manual workflow into a single prompt, and letting AI generate broadly while a human curates gets better creative results than trying to prompt for the 'perfect' idea directly.

02How the scroll trick works

A scroll-driven site is structurally just a video bound to scroll position — every frame becomes a scene, and scroll direction determines forward or backward motion through it.

03Signing into Kimi Code

Installing and logging into a coding-agent CLI is typically a single terminal command plus an OAuth login — the barrier to trying these tools is lower than it looks.

04Generating ten site concepts

AI is far better at generating a wide space of creative concepts than at judging which one is best; the efficient split is AI for volume, human taste for the final pick.

06Turning a concept into a video prompt

Feeding a model an example of the output detail level you want (a 'like this' sample) produces far more usable results than describing the desired detail in the abstract.

07The three-step pipeline, whiteboard version

The three-step creative pipeline — generate a macro video, interpolate its frame rate, bind it to scroll — is the entire technical trick behind an entire genre of premium-feeling sites.

08Generating video in Higgsfield

Generating multiple concepts in parallel rather than one at a time costs more in credits but saves real time, since only a fraction of AI outputs end up being worth keeping.
Video meant to be scrubbed by user input needs a higher frame rate than video meant to just play back; 30fps that looks fine playing normally looks choppy once a viewer can pause on any frame via scroll.

09Connecting Higgsfield to Kimi via MCP

Connecting a video platform to a coding agent via MCP replaces a manual loop (generate, copy prompt, download, re-upload) with the agent calling the tool directly.

10Interpolating and running two agents at once

Running a second agent session in an unattended ('YOLO') mode lets you parallelize slow steps like video interpolation against faster steps like scaffolding a site, instead of waiting on one task at a time.

11The site-building master prompt

A single long, detailed prompt can encode an entire multi-stage build (site structure, styling, animation library, deployment) so the agent executes the whole spec in one pass rather than being re-prompted at each stage.

13Deploying to Netlify

Once a finished asset exists, publishing it live often requires nothing more than generating a scoped access token and handing it to the agent — no manual dashboard navigation.

14The one-prompt version

The most leveraged version of any repeatable AI workflow is a single master prompt that runs the full pipeline end to end and only asks the human for the one decision that actually requires taste.

Glossary

Terms worth knowing.

Cinematic Studio 3.0: A video-generation model inside Higgsfield used to produce the short macro-camera-journey clips that become each site's background video.
MCP (Model Context Protocol): A connector standard that lets an AI coding agent call another platform's tools directly — here, letting Kimi Code query and control Higgsfield's video generation without leaving the terminal.
Frame interpolation: A video processing technique that generates new in-between frames between two existing frames, used here to double footage from 30fps to 60fps for smoother scroll-scrubbing.
Scroll-driven journey: A website pattern where scrolling up or down moves forward or backward through a bound video, creating the illusion of physically traveling through a scene.
YOLO mode: A Kimi Code setting that lets the agent execute every step of a task without stopping to ask for confirmation.

Resources

Things they pointed at.

02:17toolKimi K3 / Kimi Code ↗

08:13toolHiggsfield Cinematic Studio 3.0 ↗

09:26toolByteDance AIGC (frame interpolation model)

18:29toolNetlify

21:21communityMaker Zero (free prompt/resource community) ↗

21:23productMaker School (paid client-acquisition program) ↗

Quotables

Lines you could clip.

00:00

“Kimmy k three can design absolutely gorgeous, beautiful websites just like these for literally just a dollar or 2.”

the whole video's thesis in one line→ TikTok hook↗ Tweet quote

14:08

“For AI, which views ideas as sort of these plots on a big graph of possible concepts, ideation's actually really easy. The cool thing that humans are great at right now is employing our taste to pick things.”

clean, quotable framing of human-vs-AI division of labor→ newsletter pull-quote↗ Tweet quote

18:16

“This is like a live and working example now.”

payoff moment right after the reveal→ IG reel cold open↗ Tweet quote

The Script

Word for word.

Read-along

Don't just watch it. Burn it in.

See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.

metaphor

00:00So Kimmy k three can design absolutely gorgeous, beautiful websites just like these for literally just a dollar or 2. And in this video, I'm gonna show you everything that you need to do in order to create these sorts of cinematic journey experiences, and then host them on a website.

00:17In addition to showing you guys what to do, I'm also going to give you all of the prompts therein so you guys have everything that you need to do to just copy and paste this, whether it is to Kimmy k three, ChatGPT, Claude, or another Frontier model. Let's get into it.

00:30So logically, what exactly is going on in websites like this? Well, one thing that you can't really tell is right now I'm scrolling up and down. And so essentially, there is some form of progress or forward motion through a video.

00:43Well, at its core, what we're doing is we are taking every frame in a video, we're turning them into different scenes essentially, and then we're binding them to some sort of scroll animation such that when I scroll up, I go forward, and when I scroll down, I go back. We're also providing down here a sort of tour based experience so that people can also progress through the website and sort of autoplay as they will.

01:07There are a couple of different things that you need to know in order to make work for you. Uh, I'm just gonna give them to you, and then you guys can just copy and paste them in. But obviously, we need to both generate the creative asset, which is sort of that background video.

01:20We also need to perform some processing on the background video to make it really high quality, you know, macro sort of this zoom in journey effect. And we also need to interpolate frames and do a couple of other things so that it's not janky and it's smooth unlike what a lot of other people do. And then finally, we need Kimmy k three to wrap this in a nice bow and then present it to us.

01:37The first thing we need is we need some sort of concept. And so in this case, what are we doing? We're scrolling through some sort of deep sea underwater, I don't know, like plant or site or something like that.

01:47And so this concept is one that you can come up with yourself. But in our AI era, I much prefer to just have AI do the concept generation for me. And so let's start really easily.

01:56First thing we're gonna do is sign up to Kimi k three. In case you guys didn't know, this is the new frontier model intelligence dropped by Moonshot, Kimi's creators. And essentially, k three is really solid.

02:07It is on par with, you know, Fable, g b d 5.6 Soul, and other great models. So I'm just gonna say, hey, let's wave over and see what k three says back to us. This obviously isn't sufficient for us to make a website with.

02:19This is just a chatbot. So we're gonna have to head over not to Kimi chat, but Kimi code, which is sort of the code version of what we just saw earlier. Now Kimi subscriptions are pretty heavily throttled and bottlenecked right now because it's such a cheap way of producing high quality experiences like this.

02:34So you guys may not be able to sign up right this second. But when you are, they have a variety of different plans like Moderado, Allegrado, Allegro, and Vivace. And it's just sort of a one click sign up situation.

02:44You just click subscribe, and, uh, it will essentially take you to a Stripe page where you can, you know, do the sign up. Once you're there, you actually need to get Kimi code, and the way that you do this in terminal is pretty easy.

02:53You just copy this command, and then you open up a terminal. So that's what I'm gonna do over here. Then I'm going to drag this terminal into view, just make it really big, and then zoom in.

03:02And then, you know, terminal may look kind of intimidating if you're new to this sort of stuff, but all you really have to do is just paste in whatever that command was, and Kimmy will sort of do the rest for you. So curl dash f s s l, whatever the heck is going on. What we're doing right here is we're basically just, like, updating the the version right now because I already have it on my computer.

03:18This may take, you know, same amount of time, a little bit faster, a little bit longer, just depending on your Internet connection. And once it's downloaded, all you have to do in order to make this work is just type Kimi. It'll then open up Kimi code.

03:29Now in case you're not already logged in, you do have to type backslash login right over here, and then connect to Kimi code via OAuth. In my case, I am already logged in, but on yours, it may open up like the the Kimi page. Once we're done with that, all you have do is type slash clear.

03:44That'll clear everything else up up top, and now we can actually get to having Kimi do stuff for us. Now you don't have to do this in order to get what I'm about to show you, but I do publish all of my prompts entirely free on Maker Zero, which is my free community, um, that I link at the bottom of every single one of my YouTube videos.

04:00So I'm just gonna go down there and copy this prompt here, which says you're the sole creative director and senior front end author for a premium interactive portfolio. Give me creative ideas, videos for 10 radically different scroll driven commercial landing pages. This is the really important part.

04:16They need to be scroll driven. The video must involve a single continuous eight second extreme macro journey.

04:22Let me just make this more visible for you. This journey is what we use as the main captivating feature of our websites, so make this as interesting as possible. And what we want is we want Kimi to come up with just these concepts for us.

04:35You know, we don't necessarily need them to be the best concepts in the whole wide world, but we just want some ideas to sort of take advantage of. The cool part about AI is for humans, coming up with ideas is very computationally difficult. For AI, which views ideas as sort of these plots on a big graph of possible concepts and stuff like that, ideation's actually really easy.

04:55The cool thing that humans are great at right now is employing our taste to pick things that we think might actually sound good or make sense to our audience. And so that's what I like doing. I like having AI ideate over a very large space of possible solutions for me, and then all I really do is I pick my favorite.

05:10And so, as you can see here, we have a bunch of different ideas. This one up top is the pour luxury whiskey. We start buried inside a single bubble in the whiskey.

05:18The sphere's skin glows amber around the lens. Then the camera pushes through the membrane into liquid gold, slides past rising carbonation threads, climbs the meniscus of the glass, breaks the surface tension. See, that seems pretty interesting, but I don't know.

05:31I I kind of want to do something more impressive than just a luxury whiskey website. Here we have the capsule, Skincare and Pharma.

05:39Begin on the surface of a dissolving capsule. The gelatin wall is melting in front of the lens like slow ice. The camera pushes through the membrane into a cloud of white macro powder, drifts through the granules, each one catching light like a snow globe, and condenses onto a single droplet that falls and lands on skin.

05:53The pore it touches blooming smooth. K. I like this.

05:57This sounds really solid, and I think that's probably one of the many ideas that I'm gonna generate. So for now, I'm just gonna copy this. K.

06:03And then I'm gonna head over to just a Google Doc here, and then up here, I'll call this concepts. And just to make it really easy for you, rather than just generate one concept, because it's gonna take the same amount of time to generate, um, as, you know, multiple, I'm just gonna do multiple simultaneously and we'll find whichever one we like the best.

06:17Okay. Once we have the concepts, we're actually already about 50% of the way there to designing a smooth sort of jaw dropping experience like this. Because if you pay close attention, you'll notice that despite the fact that this website in particular seems like there's a lot of motion going on, that the website itself is what's moving and rotating around, It's actually just the video in the background.

06:37And so the creative is really the heavy lifter of this site. You know, the interactive experiences and and stuff like that. That's important as well, but that's something that Kimi can do far easier.

06:47Okay. Great. Once we have these concepts of which I picked three, all you need to do now is copy over a prompt that looks something like this.

06:56What I've done is I've just cleared through all of Kimi, then I say use the below concept to generate a high quality macro video prompt for an advanced video model. For example, then there's a single continuous eight second cinematic engineering shot moving forward from above a stormy cold North Atlantic Ocean.

07:14What I'm doing here is I'm giving it an example of the level of detail that I would like. And then what I'll do is I'll go back over to that Google Doc that stores all the different website concepts, and I'm just gonna save one of them. Actually, just paste that in here.

07:28So what I wanted to do is I wanted to generate a high quality video prompt in the exact same style that I know performs very well. We're doing this. We're just transforming ideas into prompts now.

07:38And, you know, we can use one of these to generate a big list of different high quality ideas. We can do another one to actually generate the video itself. So now you can see we're generating a single continuous ten second cinematic macro shot opening on the hexagonal lattice of a single ice crystal at molecular scale.

07:54It's approximately the same length as this other one, and now we're actually good to design the creative or the video itself. After experimenting with a few dozen different video models and types of approaches, this is probably the one that I found that the best. To make a long story short, we start by generating some sort of macro journey video.

08:12And the model that I'm gonna be using for this today is Cinematic Studio three point o. I want you to know that you can use a variety of other ones like Cdance two point o seems to work pretty well for this sort of thing, but I just wanted the best of the best as of this point in time. And so I thought I'd use Cinematic Studio three point o to to generate them.

08:27Now, once you generate them, okay, this is gonna be coming out at I believe 30 FPS. The issue with 30 FPS on one of these like scroll heavy, you know, cinematic journey sites is you can actually see every individual frame as you scroll through. And so it's really choppy.

08:42It's it's a very bad experience, I would say, for the user. So instead, what we're going to do is we're actually going to take the the core video and then interpolate it. And that just means, you know, if if this is a frame here and this is another frame here and this is another frame here, and there's some sort of element that's sort of like moving across the screen of this.

09:00K. Since this is frame one, two, three. What it does is it takes frame one and frame two, and then it generates an additional frame sort of between the two.

09:09K. And then it'll take take frame two and frame three, and it'll generate sort of an additional frame between the two. That way, instead of it being kind of choppy, you'll actually get like a smooth movement of elements throughout the thing.

09:22And when we scroll through, it'll be a lot prettier. Now again, lots of different models you could do for this sort of interpolation. I'm gonna be using ByteDance AIGC to take us from 30 to 60.

09:31And then once we're at double the FPS, the vast majority of all these scrolling issues tend to disappear. Finally, we're just gonna tie it frame by frame to some sort of smooth browser scroll, just so we can kinda get that out there.

09:42And then we can actually start, you know, moving through a video on a screen, and then we'll add the rest of the website as well. So in order to make this work, I'll be using cinematic studios straight out of Higgs Field. It's fairly straightforward.

09:53This is just like a big video, audio, and prompt library that contains more or less, you know, everything you need to copy and paste into one of these models like Kimmy k three to make it work.

10:04Obviously, using it in Kimmy k three is cool because Kimmy is a pretty cheap and also very intelligent model. So all you need to do in order to do that is just head over to sign up. They're doing some promo right now.

10:14You can sign up and get an additional discount. I already have an account, so I'm just gonna skip past this. Inside of Higgs Field, once you're signed in, you're gonna wanna go to explore up here, video, Cinema Studio 4 K.

10:26K. Once you're done, just head over to Cinema Studio at the top or you can go down to video and click on Cinema Studio 4 K. That'll take you here.

10:32You can see there are a variety of different ones, 3.5, 3.0, 2.5. I'm fine using 3.0. I don't really need all of, the cool scene changes and stuff like that.

10:41And then what I'm gonna do is I'm just gonna paste in that prompt that, you know, Kimmy just generated for us. And then the resolution that we want, if you think about it, you know, at least for us, if you're doing a desktop experience, needs to be 16 by nine.

10:55If you wanted to do a mobile experience, which I'm seeing a lot more people do these days or maybe, you know, generate a sort of creative for Instagram, you can do that by clicking nine by 16. I'm just gonna be doing 16 by nine, uh, for simplicity. And then you can use a variety of different resolutions.

11:08The one that I'm gonna use is ten eighty p just because I don't want this to take too long. I also think that the duration slider, it makes the most sense just to be eight seconds as opposed to ten or sixteen. So I'm just gonna set this to eight for now.

11:19Also, I don't wanna spend too many credits here since obviously every video generation, you know, consumes some amount of credits. In this case, it looks like it's about 80.

11:28You have custom multi shot smart and so on and so forth. That's fine. I'm just gonna click generate, and it'll actually go through the process of doing said generation.

11:35And so when you click on this, it'll sort of take the whole prompt in here. K? And it's kind of ugly right now just because I realized it's on multiple lines.

11:42Hopefully, that doesn't impact the actual gen. And then it'll open up this new little modal where it says new project processing. All you have to do now is basically just sit around and and wait.

11:50There's really nothing else to do. Because I want to be, I guess, mindful of my own time, I'm just gonna generate multiple of these simultaneously. So I'm just gonna go back here and feed in the other two website prompts.

12:02So I'm gonna go here, and I'll go back to Kimi. I'm just gonna do okay.

12:07Do these two as well, and then paste those in. So now we actually have, you know, the capsule. We also have the circuit.

12:12Okay. And so we have all of this now for the capsule. I'm just gonna feed this in, copy, paste.

12:18I'm just gonna keep to the exact same effects because we want it 16 by nine. So click generate. Then the last one I want is the circuit, obviously, and it looks like that one is now done too.

12:28So I'm gonna copy that. After we're done generating, I'm also going to generate this. So now we have three generating simultaneously.

12:37Why am I doing this? I'm just doing this because if you think about it logically, like, it'll take x amount of time to generate one of these. You But can actually just do them simultaneously.

12:45Right? The model can work on multiple things at the same time. So rather than me just, like, waiting for it to finish and then doing another one, why not just batch all three?

12:51That way, I'll have three times the creative to kind of look through. Obviously, I'm trading off my money here in credits for, you know, time and and efficiency, but I typically do this because I'm never really satisfied a 100% of the time with the outputs of AI. I'm satisfied maybe 30 to 50% of the time, which means typically I need more than one sample or more than one output in my batch in order to be happy with.

13:11And here is what looks to be a capsule dissolving and opening. This is really high quality, very clean, like micellar water type stuff there, improves the quality of the skin. So I mean, like, you know, we can scrub through this just using their little editor, but obviously, I wanna tie this to scroll wheel.

13:26Right? Here's another one. This is the city walkthrough, and so we are actually going through this, like, cool three d city.

13:32And that city is actually a circuit as well on some sexy wafer. Alright. Just took a break and saw that three websites were done.

13:39So all we have to do is just click on the little download button here and it'll automatically download it to your computer. I've already done that a couple of times. So now we actually have the the videos themselves, which is quite nice.

13:48That said, doing this stuff manually is starting to get pretty tiring. So what I'm gonna do is I'm gonna take all this from the interface in Higgs and I'm going to add it to Kimi directly. So that instead of me saying, hey, you know, generate me a prompt that I can copy and paste and put in the Higgs field, instead, I just want you to generate the Higgs field videos directly.

14:05Likewise, I'm also gonna be able to say, hey. I want you to upscale these videos as well, and then create a pipeline so that every time I generate a video, it's automatically upscale to begin with. How do you actually do this?

14:14It's pretty straightforward. Just go to MCP and CLI. MCP is essentially what's going to create a little function for us that'll enable us to connect directly to Higgs field's back end.

14:24Then just click this little copy button. Then once you're done, just head back over to Kimmy and actually paste this in and just say to Kimmy, install this MCP.

14:33This is fairly straightforward. It'll actually go through and create like a connector behind the scenes that allows it to query Higgs field and all of the models therein, which will save us the step I talked about earlier. Okay.

14:44And now it's actually written a file called m c p dot JSON on our computer. That's sort of just how, you know, the m c p syntax works. Once we're done with all that, you can just type slash clear.

14:55By doing so, it'll initiate a new server. So that's what just happened up here. If it's not already connected for you because let's say you didn't log in, you know, I've logged in on this computer multiple times.

15:05It clearly has some of my authentication credentials. Just type slash MCPDash config like this.

15:11And it'll actually walk you through a brief little sign up wizard where you can go back to Higgs field and then just sign in. Okay. Now that we're done with this, all we have to do is we have to find the files from earlier, which in my case were going to be three.

15:22We had this one, this one, and also this one. And then just gonna copy, so command c to get all the names. And I'll say, interpolate this with ByteDance AIGC.

15:34The whole idea here is we're just gonna be increasing the number of frames by two. It'll find the right Higgs field model and that's what it's doing right over here. Now that it has, you know, AIGC through byte dense, it'll then actually perform.

15:48Now the unfortunate thing about Kimi is despite it being quite intelligent, it can also be pretty slow at times. And so often, instead of just running one instance, like I'm currently doing on the left hand side where it's sending out those Higgs field requests and so on, I will run multiple. And that way, you know, while this is improving the quality of the media, I can also have other steps that are starting to scaffold the website.

16:07And so up here, I'm just gonna go a Kimi dash dash YOLO. This is just sort of like a funny mode that prevents it from ever having to ask me a question. It's on like the you only live once mode, so just let the agent do everything.

16:19Okay. So then finally, all I'm gonna do is head over here to site prompt, copy all of this in. And you know, it's pretty long, but as mentioned, you guys can get that entirely free if you want to.

16:29And then paste this in fully to Kimmy k three.

16:34Now the one thing that we need to provide, well, I should say two things actually, is we need to provide both the video URL, which is on our computer, and we also need to provide that concept prompt that we use to generate it. And so, you know, the way this prompt works is essentially, it will go through, you know, a very in-depth series of steps in order to produce this nice motion graphic design.

16:57But it'll ask for a video file name or a concept. And you can even say it says e g capsule dot m p four.

17:04So I'll just go back over here, open up Finder, and then I'll go to downloads. And this is the capsule one that I want.

17:11So I'll say video is here, and then concept. And then I'll just go back to Higgs field.

17:18And if I click on this, it'll actually allow me to copy in whatever prompt I used and and fed in there. Then I'll paste that in. Okay.

17:26And you're probably already seeing areas that we can optimize the hell out of this. And the reason for that is because what we've done here is we've manually sort of made all these steps. Right?

17:35Well, we can actually just to kind of weave this entire pipeline together to do all of this for us. And so I'll show you how to do that right after this is done with it. So okay.

17:41And here is the finished website. As you guys can see here, we are smooth scrolling through what looks to be a pretty complicated universe. I mean, we have, obviously, circuit boards and so on and so forth and some cool sexy light at the end there.

17:54What I also like about this is you can hold to reserve and, you know, presumably, this is, I don't know, us doing some sort of prelaunch or something like that for a product. But this is like a a live and working example now. You can also click from one section to the next by using the watch it dissolve feature, and then obviously, you guys can go as fast or as slow as you want to with the manual scroll to.

18:15And that's end to end. If you wanted now to say publish this on the Internet, let's say Netlify or something like that. Like, you know, I did my kimmy k three designs dot netlify dot app service, which contains all of these other websites that you guys could see right here.

18:29It's actually fairly straightforward. All you have to do is just get some sort of static hosting site service. So maybe Netlify, maybe Vercel, and then just go to the service, log in, you know, go to the user settings or user settings, then over here under applications, there'll be OAuth.

18:44You can then click new access token. I'll just say example token expiring. I don't know.

18:50Can we just say tomorrow or today? Let's do click generate token. We can just copy that token into Kimi, and we can actually just give it to it.

18:57And I don't know if you guys could see, but this is currently creating the site on my Netlify. So I've just fed up my key, and you can do this with whatever platform you want.

19:05You can do this with Vercell. You can do this with whatever. And now it is 100% online.

19:09So we've actually published this to netlify.app down in the bottom right hand corner or left hand corner. There's sort of this, like, you know, flow tour button so you can proceed as a whole video if you wanted to.

19:22And, yeah, you can you guys can actually access this website right now. Alright. And I told you this is gonna be the mother lode.

19:26This is a single prompt that contains every one of these steps end to end. And so all you need to do in order to essentially produce whatever sort of style of motion journey cinematic website that you want, So you just feed this entire thing in, and then it'll just ask you, hey.

19:43Do you have any ideas of websites you wanna generate, or do you just want me to go nuts? And obviously, I kinda just want it to go nuts. And so if I just paste in this entire thing into Kimi, k, which is now showing me the whole prompt, and this is just a a slightly different terminal in case you guys are wondering why I look different.

19:57You can see that it is now going to ask me what subjects, products, industries, materials, or ideas are you interested in? And I'm just going to say, you go nuts.

20:05And two, do you have any creative direction references or constraints, should I grab everything? You go nuts too. And the end result is websites like I showed you guys earlier.

20:14I mean, is us going into the sky and eventually the whole horizon. Very sexy experience from the inside, legitimately inside of a hot air balloon. This is us scrolling through some dark, dank cave and then getting to what looks to be like a record player or something where the head is on fire.

20:34That one's a little bit more zany, and this one is like a foundry, which essentially produces what looks to be some form of, I don't know, brass or yeah. It looks like one of those old school printing presses, which is also really neat.

20:47So you can have this generate as many as you want. It really just boils down to how much time you wanna spend and how many credits, but, hopefully, you guys have everything that you need to do the same. As mentioned, if you guys want all of the assets and everything that I use to generate all of these websites, it's entirely free inside of MakerZero.

21:02If you guys want to get to the point where you can sell these sorts of interactive visual experiences to other people and get paid for it, definitely check out Maker School. It's the first link in the description. Maker School is my ninety day accountability program that shows you guys not only how to, you know, build a really cool interactive experiences like this, but also build AI automations.

21:20And then more importantly, sell them to people that are asking for systems like this. I have a ninety day full money back guarantee where if you do not acquire client number one, I will literally just give you your money back, and it's because I'm super confident in the program of what it does.

21:34Okay? Anyway, I'll stop showing my own products. Have a lovely rest of the day, and thanks so much for watching.

The Hook

The bait, then the rug-pull.

He opens by scrolling through a moody underwater-looking hero site and claims the whole cinematic effect cost about a dollar to make — then spends the next twenty minutes proving it, one terminal command at a time.

Frameworks

Named ideas worth stealing.

08:15list

Cinematic "Journey" Creative Generation (3-step pipeline)

Generate a macro journey video with Cinematic Studio 3.0
Interpolate with ByteDance AIGC to get to 60fps
Tie frame-by-frame to smooth browser scroll

The core three-step method behind every site in the video: generate a short cinematic clip, smooth it out with frame interpolation, then bind it to scroll position in the browser.

Steal forany landing page or portfolio hero that wants a premium scroll-video effect without hiring a motion designer

CTA Breakdown

How they asked for the click.

VERBAL ASK

21:23product

“If you guys want to get to the point where you can sell these sorts of interactive visual experiences to other people and get paid for it, definitely check out Maker School... a ninety day full money back guarantee where if you do not acquire client number one, I will literally just give you your money back.”

Soft CTA to the free resource community first (Maker Zero), then a harder pitch for the paid program (Maker School) with a guarantee, delivered directly to camera in the closing seconds.

MENTIONED ON CAMERA

02:17toolKimi K3 / Kimi Code ↗

08:13toolHiggsfield Cinematic Studio 3.0 ↗

21:21communityMaker Zero (free prompt/resource community) ↗

21:23productMaker School (paid client-acquisition program) ↗

FROM THE DESCRIPTION

PRIMARY CTAWhere the creator wants you to go next.

OTHER LINKSAlso linked in the description.