0:00 / 0:00

Comment “AI” for all the prompts! The Artlist AI Toolkit lets video creators generate images, videos, and creative assets inside a single platform, making it easier than ever to experiment, iterate, and push your content to the next level. It’s built for creators who want higher-quality AI visuals, faster workflows, and more creative freedom without juggling multiple tools. #ArtlistAI #AIToolkit #AIVideoCreation #CreativeAI #GenerativeAI

Rourke Sefton-Minns

@rourke · creator

INSTAGRAM · 2026-01-23Source

15.5Klikes

6.4Kcomments

Remix This

Recreate with Kling 3

Make your own AI viral video

Prompt

GOAL
Maximize visual + motion + speech (audio) similarity to the reference video, prioritizing:
1) Subject consistency (identity / wardrobe / props) for the creator in the bottom half.
2) Environment consistency (location, set dressing) for the creator's room.
3) Split-screen layout consistency (Top half: UI/AI Video, Bottom half: Creator).
4) Visual fidelity of the AI-generated casino sequence (lighting, morphing transitions, specific objects).
5) UI accuracy for the screen recording segments.
6) Speech signature (script/semantics, cadence, energetic tone).

WORKFLOW
A) MISE EN PLACE
- Invariants: Split-screen vertical format. Bottom half: Caucasian male, 30s, beard, beige t-shirt, blue baseball cap with yellow logo, sitting in a bright room with a window behind him. Top half: Alternates between high-end cinematic casino AI video and dark-mode web UI screen recordings.
- Variables: The specific content shown in the top half (casino sequence vs. UI), the creator's hand gestures (pointing up, gesturing to explain).

B) SHOTLIST & D) PROMPT SYNTHESIS

MASTER PROMPT:
GLOBAL LOCK: Vertical 9:16 video format featuring a continuous split-screen layout. The bottom half consistently shows a Caucasian man in his 30s with a beard, wearing a beige t-shirt and a blue baseball cap with a yellow logo. He is sitting indoors in a brightly lit room with a window visible in the background. He speaks directly to the camera with an energetic, educational tone, frequently using his hands to gesture upwards towards the top half of the screen. The top half of the screen displays varying content, alternating between a highly polished, cinematic AI-generated video sequence and screen recordings of a dark-mode web interface. The lighting on the man is natural and soft, while the AI sequence features warm, golden, high-contrast cinematic lighting.

[00:00–00:05] Top half: A cinematic, warm-lit shot of a man in a white tuxedo at a casino poker table, pushing chips forward. The camera pushes in rapidly, and the scene seamlessly morphs into an extreme close-up of a hand holding a yellow and black casino chip. Text overlays "Start Frame" and "End Frame" appear briefly, along with a graphic of a video editing timeline. Bottom half: The man points both index fingers upwards at the top screen, looking impressed. Text overlay: "This is AI? 🤯".
[00:05–00:15] Top half: The continuous morphing sequence continues. The yellow casino chip flips into the air, spinning, and seamlessly transforms into a spinning wooden roulette wheel. A white ball drops onto the wheel, bounces, and falls down a dark, golden-lit chute. As it falls, it morphs into two golden dice that land on a green craps table. The dice have the words "Artlist" and "AI Toolkit" engraved on them. In the background, out-of-focus people in formal wear are cheering. Bottom half: The man watches the sequence, resting his hand on his chin, then points downwards, then makes an "okay" hand gesture, reacting to the visuals above.
[00:15–00:35] Top half: The view switches to a screen recording of a dark-mode web interface for "Artlist AI Toolkit". The cursor clicks on "Generate image". The screen scrolls through various AI image models, specifically highlighting "Artlist Original 1.0" and "Nano Banana Pro". Thumbnails of the generated casino images (tuxedo man, chip, roulette) are shown. Bottom half: The man speaks directly to the camera, explaining the process, using his hands to emphasize points.
[00:35–00:44] Top half: The screen recording switches to a video generation interface, highlighting a model called "Kling 2.5 Turbo Pro". The UI demonstrates a workflow using a "Start Frame" and an "End Frame" input, showing the previously generated casino images being placed into these slots to create the transition. Bottom half: The man continues his explanation, gesturing with his hands to indicate the connection between the two frames.
[00:44–00:51] Top half: A static graphic appears showing a dark-themed PDF document titled "GenHQ Workflow Overview" containing thumbnails of the casino images and blocks of text (prompts). A large, bold text overlay appears: "Comment 'AI'". Bottom half: The man points emphatically at the "Comment 'AI'" text, urging the viewer to take action.

NEGATIVE PROMPT:
Visuals: Loss of split-screen format, creator's appearance changing (different hat, different shirt, losing beard), inconsistent lighting on the creator, jarring cuts in the top-half AI sequence, loss of momentum during the morphing transitions, misspelled text on the golden dice (must say "Artlist" and "AI Toolkit"), blurry or illegible UI elements in the screen recording, unnatural hand anatomy during gestures.
Audio: Robotic voice, low energy, muffled audio, lack of sync between creator's lips and speech.

SPEECH PACK:
[00:00-00:15] (No speech, upbeat electronic background music playing)
[00:15-00:35] SPEAKER A (Creator): "Here's how you can make this using Artlist's new AI Toolkit. On Artlist, go to the top of the page and select 'Generate image'. From here, you can go and select all of the best image models, including Artlist's new image model called 1.0. Then, when you pair that with Google Nano Banana Pro, you can insert yourself into the scenes."
[00:35-00:44] SPEAKER A (Creator): "And we'll give you this PDF document at the end of the video with all of our prompts and images. Then you can use the video section of the toolkit, where you can use the best video models, and use Kling 2.5 first and last frame to create these epic transition shots."
[00:44-00:51] SPEAKER A (Creator): "If you want access to all of our prompts and images, type 'AI' in the comments and I'll send you the links. Artlist has a lot of new features coming soon."

How to Create Viral AI Video Transitions with Artlist AI Toolkit & Kling 2.5

1. Case Snapshot

This Instagram Reel by @rourke is a masterclass in educational "how-to" content for AI creators, utilizing a dynamic split-screen format to showcase a mind-bending, cinematic AI-generated casino morphing sequence (tuxedo man to chip to roulette to golden dice) on the top half, while the creator provides an energetic, step-by-step UI walkthrough of the Artlist AI Toolkit and Kling 2.5 Turbo Pro on the bottom half. The video perfectly balances visual spectacle with actionable utility, culminating in a highly effective engagement loop by offering a PDF of the exact prompts used in exchange for a simple comment ("AI").

2. What You're Seeing

The video employs a consistent vertical split-screen layout. The bottom half features the creator—a Caucasian male with a beard, wearing a beige t-shirt and a blue baseball cap with a yellow logo—sitting in a well-lit room with a window behind him. He speaks directly to the camera, using frequent upward hand gestures to direct the viewer's attention to the top half of the screen. The top half serves as the visual evidence and tutorial space. It begins with a fast-paced, highly polished AI video sequence set in a luxurious casino with warm, golden lighting. We see a man in a white tuxedo, which seamlessly transitions into a close-up of a hand holding a casino chip, which then flips and morphs into a spinning roulette wheel, followed by a bouncing ball that transforms into golden dice bearing the text "Artlist" and "AI Toolkit". After this 15-second hook, the top half switches to screen recordings of the Artlist AI Toolkit interface, demonstrating the selection of image models (Artlist Original 1.0, Nano Banana Pro) and the video generation process using Kling 2.5 Turbo Pro with "Start Frame" and "End Frame" inputs. The video concludes with a graphic of a PDF document and a large text overlay prompting the viewer to "Comment 'AI'".

Shot-by-Shot Breakdown

Time Range	Visual Content	Shot Language	Lighting & Color Tone	Viewer Intent
00:00 - 00:05	Top: Man in tuxedo at poker table, transitions to hand holding a chip. Bottom: Creator points up, looking impressed. Text: "This is AI? 🤯" and a Premiere timeline graphic.	Top: Medium shot pushing in, morphing to extreme close-up. Bottom: Medium close-up, static.	Top: Warm, golden, cinematic casino lighting. High contrast. Bottom: Natural daylight, soft.	Hook the viewer immediately with a visually stunning, seemingly impossible continuous shot. Establish the "magic trick."
00:05 - 00:15	Top: Chip flips, morphs into spinning roulette wheel, ball drops, morphs into golden dice with text. Bottom: Creator watches, gestures, points up.	Top: Dynamic, continuous motion. Close-ups and macro shots. Fast pacing. Bottom: Medium close-up, reactive.	Top: Consistent warm gold and deep blacks. High saturation. Bottom: Natural daylight.	Sustain attention by escalating the complexity of the AI generation. Prove the capability of the tools being showcased.
00:15 - 00:35	Top: Screen recording of Artlist AI Toolkit UI. Selecting "Generate image", showing model options (Artlist Original 1.0, Nano Banana Pro). Bottom: Creator explains the process.	Top: Screen capture, clear and legible. Bottom: Medium close-up, direct address.	Top: Dark mode UI, varied colors from generated thumbnails. Bottom: Natural daylight.	Transition from spectacle to education. Show the "behind the curtain" process, making the complex result seem achievable.
00:35 - 00:44	Top: UI showing Kling 2.5 Turbo Pro. Demonstrating the "Start Frame" and "End Frame" workflow with the casino images. Bottom: Creator explains the video generation step.	Top: Screen capture, focusing on specific UI elements. Bottom: Medium close-up, instructional gestures.	Top: Dark mode UI. Bottom: Natural daylight.	Deliver the core technical value: explaining how the seamless transitions were actually made (frame interpolation).
00:44 - 00:51	Top: Graphic of a detailed PDF document. Large text overlay: "Comment 'AI'". Bottom: Creator points directly at the text, urging action.	Top: Static graphic. Bottom: Medium close-up, strong call to action.	Top: Dark background, high contrast text. Bottom: Natural daylight.	Drive engagement and lead generation. Offer a tangible reward (the prompt PDF) for a low-friction action (commenting).

3. Why It Went Viral (Breakdown of the Viral Mechanism)

The "Magic Trick" Hook (0-3s)

The video opens with a visual spectacle that defies immediate explanation. The seamless morphing from a man in a tuxedo to a casino chip, and then to a roulette wheel, acts as a digital magic trick. This taps into the viewer's sense of curiosity and wonder. In the first three seconds, the brain is trying to process *how* this continuous, physics-defying shot was created. The text overlay "This is AI? 🤯" validates the viewer's disbelief and sets the premise: this is cutting-edge technology, and I'm going to show you how it works. This immediate delivery of high-quality visual evidence is crucial for stopping the scroll.

The "Behind the Curtain" Value Proposition

After hooking the viewer with the result, the video immediately pivots to the process. It doesn't just show off; it educates. By breaking down the complex sequence into manageable steps—generating a start frame, generating an end frame, and using a specific tool (Kling 2.5) to bridge them—the creator demystifies the process. This appeals to the aspirational desires of other creators and tech enthusiasts who want to replicate these high-end results. The value is clear: watch this video, and you'll learn a new, powerful workflow.

The Engagement Bait Automation (ManyChat)

The most significant driver of the video's virality (evident from the 6,355 comments) is the strategic use of an automated DM funnel. The creator doesn't just explain the process; he offers the exact "recipe" (the prompts) in a PDF format. However, to get it, the viewer must comment a specific keyword ("AI"). This creates a massive spike in engagement signals for the platform's algorithm. Every comment tells the algorithm, "People are highly interested in this," pushing the video to a broader audience. It's a frictionless transaction for the user (typing two letters) in exchange for high perceived value.

Platform Signals: Watch Time via Density

From a platform perspective, this video is engineered for high retention. The split-screen format is inherently information-dense. The viewer's eye is constantly darting between the creator's gestures on the bottom and the fast-paced visuals or UI walkthroughs on the top. There is no dead space. The pacing is rapid, with visual changes happening every few seconds. This density prevents boredom and encourages viewers to watch the entire 51 seconds, and often re-watch it to catch details they missed in the UI sections, sending strong positive signals to the algorithm.

Platform Signals: Shares via Utility

While the hook drives watch time and the CTA drives comments, the educational nature of the content drives shares and saves. Creators will save this video as a reference for the "Start Frame/End Frame" workflow. They will share it with colleagues or friends interested in AI video generation. The video acts as a mini-tutorial, making it a highly utilitarian piece of content that users want to keep in their personal libraries or distribute within their networks.

5 Testable Viral Hypotheses

The "Result-First" Hypothesis: Showing the final, complex AI sequence in the first 5 seconds before explaining the tutorial increases retention compared to starting with the UI walkthrough. (Evidence: The video opens with the stunning casino morph sequence.)
The "Split-Screen Density" Hypothesis: Using a split-screen to show the creator's face alongside the screen recording increases watch time by providing a human connection while maintaining visual interest, compared to a full-screen UI recording with just voiceover. (Evidence: The consistent top/bottom split throughout the video.)
The "Specific Tool Callout" Hypothesis: Explicitly naming the tools used (Artlist AI Toolkit, Kling 2.5 Turbo Pro) increases saves and shares because it provides actionable, specific utility rather than vague advice. (Evidence: The creator clearly shows and names the models in the UI.)
The "Keyword Automation" Hypothesis: Asking for a specific, short keyword comment ("AI") to receive a lead magnet generates exponentially more comments than asking a generic question, triggering algorithmic distribution. (Evidence: The massive comment count and the clear CTA at the end.)
The "Visual Proof of Concept" Hypothesis: Showing the "Start Frame" and "End Frame" side-by-side before showing the generated transition makes the AI's capability easier to understand, increasing the perceived value of the tutorial. (Evidence: The UI demonstration clearly shows the two input images before the final result.)

4. How to Recreate (Replication Tutorial: From 0 to 1)

This workflow is ideal for tech educators, AI artists, or software reviewers who want to showcase complex AI capabilities in an accessible, engaging format.

Step 1: Conceptualize the Morphing Sequence

Plan a sequence where objects share similar shapes or thematic elements to make the AI interpolation smoother. In the video, a round casino chip morphs into a round roulette wheel. Create a storyboard of your "Start" and "End" keyframes.

Step 2: Generate Keyframes (Start/End)

Use an image generator (like the Artlist AI Toolkit shown, or Midjourney/DALL-E) to create your keyframes. Crucial detail from the video: Ensure consistent lighting (warm, golden) and style across all images so the video model doesn't have to invent drastic lighting changes during the transition.

Step 3: Video Generation via Interpolation

Use a video model that supports start and end frame inputs (the video explicitly highlights Kling 2.5 Turbo Pro). Upload your first image as the start frame and the second image as the end frame. Generate the video. Repeat this for each transition in your sequence.

Step 4: Screen Recording the UI

Record your screen as you navigate the tools you used. Don't just show the final result; show the process of selecting the models and uploading the images. Keep these recordings concise and focused on the key actions.

Step 5: Recording the A-Roll

Film yourself explaining the process. Crucial detail from the video: Frame yourself in the lower half of the shot and use upward hand gestures to point to where the B-roll will be placed. Speak energetically and directly to the camera.

Step 6: Editing and Split-Screen Assembly

In your editing software (Premiere, CapCut), set up a 9:16 vertical sequence. Place your A-roll on the bottom track and crop/position it to fill the lower half. Place your AI sequences and screen recordings on the top track, filling the upper half. Ensure the timing of your gestures matches the visual changes above.

Step 7: Create the Lead Magnet

Compile the exact prompts you used into a clean, easy-to-read PDF document. This is the value you will exchange for engagement. Create a simple graphic representing this PDF for the end of your video.

Step 8: Setting up the Auto-DM Funnel

Use a tool like ManyChat to set up an automation on Instagram. Configure it so that when a user comments a specific keyword (e.g., "AI", "PROMPT"), they automatically receive a direct message containing the link to download your PDF. Add a strong CTA to the end of your video and in the caption directing users to do this.

5. Growth Playbook (Distribution & Scaling Strategy)

3 Ready-to-Use Opening Hook Lines

"Stop scrolling. This 15-second AI sequence took me 5 minutes to make, and I'm going to show you exactly how."
"Everyone is using AI video wrong. Here is the 'Start and End frame' secret that changes everything."
"I tested the new Kling 2.5 update so you don't have to. The results are actually insane."

4 Caption Templates

The Direct Tutorial: [Hook] Want to create seamless AI transitions like the one above? [Value] The secret is using start and end keyframes in Kling 2.5. It forces the AI to interpolate exactly what you want. [Question] What two objects would you morph together? [CTA] Comment "TUTORIAL" and I'll DM you the exact step-by-step guide and prompts I used!
The Tool Spotlight: [Hook] The Artlist AI Toolkit just quietly dropped a massive update. [Value] You can now generate cinema-grade images and animate them all in one place. The workflow is incredibly smooth. [Question] Have you tried generating video from images yet? [CTA] Comment "ACCESS" and I'll send you a link to try it out plus my cheat sheet of prompts.
The "Behind the Scenes": [Hook] This looks like a million-dollar VFX shot. It's actually just two AI images. [Value] By controlling the start and end points, you remove the randomness from AI video generation. [Question] What's your biggest struggle with AI video right now? [CTA] Comment "PROMPTS" and I'll send you the exact text I used to generate these casino assets.
The Value Bomb: [Hook] Stop guessing with your AI prompts. [Value] I spent hours refining the lighting and texture prompts to get this golden casino look, and I've documented the entire process. [Question] Are you team Midjourney or team Artlist for images? [CTA] Comment "GUIDE" and I'll automatically send you my 5-page PDF breaking down this entire workflow.

Hashtag Strategy

Broad (The Algorithm Net): #AIVideo #ContentCreator #VideoEditing #Filmmaking #TechTutorial. Why: These cast a wide net to signal the general category of the content to the platform.
Mid-Tier (The Target Audience): #AIArtCommunity #KlingAI #ArtlistIO #VideoTransitions #CreativeWorkflow. Why: These target users specifically interested in AI generation tools and editing techniques.
Niche Long-Tail (The Search Intent): #HowToMakeAIVideo #Kling25Tutorial #AIImageToVideo #SeamlessTransitions #AIPromptGuide. Why: These capture users actively searching for specific tutorials or solutions to problems they are facing in their own workflows.

6. FAQ

What tools make it look the most similar?

The creator explicitly uses the Artlist AI Toolkit for image generation (specifically Artlist Original 1.0 and Nano Banana Pro) and Kling 2.5 Turbo Pro for the video transitions.

How does the creator achieve the seamless morphing effect?

By generating a 'Start Frame' and an 'End Frame' in an image generator, and then using a video model like Kling 2.5 Turbo Pro to interpolate the transition between them.

Why does the video use a split-screen format?

The split-screen allows the creator to maintain a personal connection (A-roll on the bottom) while simultaneously demonstrating complex visual evidence and UI workflows (B-roll on top) without cutting away.

How does the creator drive engagement and leads?

By offering a high-value PDF document containing all the prompts used in the video, accessible only by commenting a specific keyword ('AI'), which triggers an automated DM.

What is the most important part of the prompt for the casino sequence?

Maintaining consistent lighting (warm, golden, cinematic) and subject matter (casino elements like chips, roulette, dice) across the start and end frames to ensure a smooth transition.

How can I avoid making the transition look like a messy AI morph?

Choose objects that share similar geometric shapes (e.g., a round chip to a round roulette wheel) and ensure the camera angle and lighting direction are identical in both the start and end frames.