0:00 / 0:00

#AD AI Video Production is about to get a whole lot WILDER 🔥 @samsunguk Type “AI” in the comments for the links to the tech and tools #Ad #AIVideoProduction #LiveActionToAI #SketchToImage #ImageToVideo #VideoToVideo #GenerativeAI #CreativeAI #AIForCreators #AIMagic #SamsungGalaxyTab #AISketchWorkflow #AIContentCreation #NextGenVideo #AIStorytelling #InnovativeAI #SmartAI #DigitalCreators #FutureOfFilmmaking #AIEditingTools #CreatorEconomy

Rourke Sefton-Minns

@rourke · creator

INSTAGRAM · 2025-09-20Source

17.3Klikes

6.7Kcomments

Remix This

Recreate with Sora 2

Make your own AI viral video

Prompt

GLOBAL LOCK:
Subject is a Caucasian male in his mid-30s with a dark, well-groomed beard and mustache. He consistently wears a white baseball cap with a small logo and a white t-shirt. The AI-generated versions must maintain his facial structure and beard while changing costumes. The overall style is high-end cinematic photorealism with 8k textures, dramatic lighting, and professional color grading. The video follows a 3-panel vertical split-screen format: Top (Sketch), Middle (AI Video), Bottom (Live Action).

[00:00–00:03]
SUBJECT: The subject is a medieval knight wearing a brown leather chest plate with a white deer emblem, green undershirt, and leather bracers. He is holding a wooden longbow, drawing the string back to his cheek with a focused expression.
ENVIRONMENT: A grand medieval castle courtyard with stone walls, flags, and a blurred crowd in the background.
ACTION: Drawing the bowstring, aiming, and holding the tension.
CAMERA: Medium shot, 50mm lens, slight side profile.
LIGHTING: Bright, natural sunlight with soft shadows.
SPEECH: "This new method of creating AI videos is absolutely insane." (Warm, energetic tone).

[00:04–00:08]
SUBJECT: The subject is a master potter wearing a tan canvas apron over a white shirt. His hands are covered in wet clay.
ENVIRONMENT: A rustic, sun-drenched pottery studio with wooden shelves and ceramic pots.
ACTION: Shaping a spinning clay vase on a wooden pottery wheel. The clay is smooth and wet.
CAMERA: Close-up on hands and face, shallow depth of field.
LIGHTING: Warm, golden hour light coming from a side window.
SPEECH: "So you can now play yourself as a consistent character moving through any scene."

[00:09–00:12]
SUBJECT: The subject is a gallery visitor in a striped shirt and white cap, holding a black picture frame that contains a vibrant floral oil painting.
ENVIRONMENT: A dark, modern art gallery with grey walls and red security laser beams crisscrossing the room.
ACTION: Holding the frame up, looking at the camera with a surprised, excited expression.
CAMERA: Medium shot, centered composition.
LIGHTING: Moody, low-key lighting with red accent lights from the lasers.
SPEECH: "And the crazy part is that you no longer need Hollywood level budgets for this."

[00:13–00:15]
SUBJECT: The subject is a scuba diver with long flowing hair (no cap), wearing a white t-shirt.
ENVIRONMENT: A vibrant underwater coral reef with colorful fish, bubbles, and caustic light rays filtering through the surface.
ACTION: Swimming forward with a breaststroke motion, looking around in awe.
CAMERA: Wide shot, tracking the movement.
LIGHTING: Cool blue underwater lighting with shimmering highlights.
SPEECH: "You can record all of this from your own home."

[00:16–00:18]
SUBJECT: The subject is a world-class DJ wearing a white cap and professional headphones.
ENVIRONMENT: A massive concert stage overlooking a cheering crowd of thousands. Neon lights and stage fog.
ACTION: One hand on a DJ controller, the other hand raised to the crowd in a "pumping" motion.
CAMERA: Over-the-shoulder shot looking out at the crowd.
LIGHTING: High-contrast, flashing concert lights (purple, blue, white).
SPEECH: "So I'm going to show you exactly how you could achieve the same results for yourself."

[00:19–00:21]
SUBJECT: The subject is a professional chef in a white chef's coat and tall hat.
ENVIRONMENT: A busy, high-end restaurant kitchen with stainless steel surfaces and other chefs in the background.
ACTION: Tossing pasta in a frying pan, creating a large, controlled burst of orange flame.
CAMERA: Medium shot, dynamic movement.
LIGHTING: Bright kitchen lighting with the warm glow of the fire reflecting on the subject's face.
SPEECH: "...with a few subscriptions and a simple sketch."

[00:22–00:59]
SUBJECT: The subject is an 18th-century opera singer in a lavish blue and gold velvet frock coat with white lace cuffs and a powdered wig (beard remains).
ENVIRONMENT: A grand, ornate opera house with red velvet seats, gold-leaf balconies, and a spotlight on the stage.
ACTION: Standing center stage, arms outstretched in a dramatic singing pose, then performing a theatrical twirl.
CAMERA: Starts as a wide shot of the theater, then punches in to a medium shot of the singer.
LIGHTING: Dramatic theatrical spotlighting, high contrast.
SPEECH: Detailed tutorial narration explaining the sketch-to-video process. (Clear, instructional, engaging).

NEGATIVE PROMPT:
Visual: Cartoonish, low resolution, blurry, distorted facial features, inconsistent beard, flickering lights, floating objects, extra limbs, text/watermarks in the AI panel, jittery motion.
Speech: Robotic, flat tone, muffled audio, background noise, lip-sync mismatch, stuttering, unnatural pauses.

SPEECH PACK:
[00:00–00:03] "This new method of creating AI videos is absolutely insane."
TAKE_A: (Excited/High Energy) "This NEW method of creating AI videos is absolutely INSANE!"
TAKE_B: (Awestruck/Lower Pitch) "This... new method of creating AI videos... it's absolutely insane."

[00:04–00:08] "So you can now play yourself as a consistent character moving through any scene."
TAKE_A: (Informative/Smooth) "So you can now play YOURSELF as a consistent character, moving through ANY scene."
TAKE_B: (Fast-paced/Direct) "You can now play yourself as a consistent character in any scene you want."

[00:22–00:30] "To get started, you need to do a basic sketch mapping out the scene."
TAKE_A: (Instructional/Clear) "To get started, you just need a basic sketch... mapping out the whole scene."

PROSODY NOTES:
- Use emphasis on "INSANE," "ANY," and "HOLLYWOOD."
- Maintain a rhythmic pace that matches the visual cuts.
- Ensure lip-sync is high-priority for the tutorial sections where the creator's face is visible in the bottom panel.

Why rourke's Sketch to Cinematic Went Viral - and the Formula Behind It

This case study analyzes a high-performing "AI Video Production" tutorial by creator @rourke. The video utilizes a distinctive three-panel vertical split-screen to demonstrate the evolution of a creative idea: from a simple line-art sketch (top) to a cinematic AI-generated scene (middle), driven by UGC live-action footage (bottom). By showcasing wildly different environments—from medieval archery ranges and underwater coral reefs to grand opera houses—the creator proves that high-budget visual effects are now accessible to anyone with a smartphone and AI tools. The core keywords for this aesthetic are "Sketch-to-Video," "AI Character Consistency," and "Cinematic V2V (Video-to-Video)."

What You’re Seeing: Visual Analysis

The video is a masterclass in visual storytelling through comparison. The subject is a male creator with a prominent beard and a signature white baseball cap. In the live-action "driving" footage, he is in a domestic setting (kitchen, living room, garden), performing exaggerated actions like drawing an invisible bow or swimming on a table. The AI-generated middle panel transforms him into various personas: a medieval archer, a master potter, a scuba diver, a world-class DJ, and a 17th-century opera singer.

The color palette shifts dramatically between the panels. The bottom panel is natural, bright, and slightly overexposed (typical of home lighting), while the middle AI panel features cinematic color grading, deep shadows, and high-contrast lighting (e.g., the warm glow of a pottery kiln or the neon lasers of a concert). The editing is fast-paced, using the rhythm of the background music to trigger scene transitions every 2-3 seconds, maintaining a high "visual dopamine" hit for the viewer.

Shot-by-Shot Breakdown

Time Range	Visual Content	Shot Language	Lighting & Tone	Viewer Intent
00:00–00:03	Archery scene. Sketch vs. Knight vs. Creator in garden.	Medium Shot (MS), profile view.	Bright daylight, cinematic film grade.	Hook: Instant "Magic" transformation.
00:04–00:08	Pottery wheel. Hands shaping clay.	Close-up (CU) on hands and face.	Warm, amber workshop lighting.	Demonstrate detail and texture consistency.
00:09–00:12	Art Gallery. Creator holding a "painting" (tablet).	Medium Shot, centered.	Moody gallery lighting with red lasers.	Showcase prop integration (Tablet to Painting).
00:13–00:15	Underwater swimming. Creator on a table.	Wide Shot (WS), horizontal movement.	Cool blue, caustic water light effects.	Surprise/Humor: The "behind the scenes" reveal.
00:16–00:18	DJ at a festival. Creator at a desk.	Over-the-shoulder to Wide.	High-energy, flashing stage lights.	Scale: Showing "massive" environments.
00:22–00:59	Tutorial: Opera Singer. Step-by-step UI demo.	Screen recording + Talking head.	Informational, clear UI visibility.	Tutorial Value: Retain users for the "How-to."

Why It Went Viral: The Breakdown

The "Low Effort, High Reward" Psychology

This video taps into the biological instinct for efficiency. It shows a creator performing mundane tasks in a messy kitchen and instantly becoming a professional chef or an opera star. This "superpower" fantasy is highly shareable because it suggests that the viewer's own "boring" life could be transformed into a cinematic masterpiece with just a few clicks. The contrast between the low-fidelity sketch and the high-fidelity AI output creates a "satisfying" visual loop that encourages re-watching.

Platform Signals & Engagement Engineering

From a platform perspective, the 0–3 second hook is flawless. By starting with the archery shot—a high-action, recognizable movement—the creator captures attention before the user can swipe. The "Type AI in the comments" call-to-action (CTA) is a classic engagement hack. It triggers the Instagram/TikTok algorithm by flooding the comment section with a specific keyword, which the platform interprets as high interest, subsequently pushing the video to a wider audience. The use of a 3-panel layout also increases watch time, as viewers often need to watch the video twice to see what's happening in each panel.

5 Testable Viral Hypotheses

The Contrast Effect: Showing the "ugly" reality (creator on a table) next to the "beautiful" AI (underwater diver) creates a humor-value hybrid that drives saves.
The "Magic Tool" Curiosity: By not naming the tools immediately and asking for a comment, you create a "curiosity gap" that forces engagement.
Multi-Persona Consistency: Demonstrating that the same person can be in 5 different costumes proves the tech is "ready," which attracts professional creators.
The Sketch-to-Life Trope: Humans are naturally fascinated by drawings coming to life. Using a simple line sketch as the "source" makes the AI feel like a creative partner, not a replacement.
Fast-Paced Pacing: Cutting every 2 seconds prevents "boredom drops" in the retention graph, keeping the viewer in a state of constant discovery.

How to Recreate: Step-by-Step Tutorial

1. Topic Selection & Positioning

This format works best for "Creative Tech," "Digital Art," or "Lifestyle" accounts. Choose 5-6 wildly different "dream" scenarios (e.g., Astronaut, Samurai, Cyberpunk Hacker).

2. The "Driving" Video (Live Action)

Record yourself in a well-lit room. Perform the actions of your chosen personas. Crucial: Use props that mimic the final object (e.g., a broom for a sword, a tablet for a shield). Keep your camera stable on a tripod.

3. The Composition Sketch

Create a very simple black-and-white line drawing of the scene. Focus on the composition (where the person is, where the background elements are). You don't need to be an artist; AI only needs the "bones."

4. Generating the Reference Image

Use an AI image generator (like Leonardo.ai or Midjourney). Upload your sketch as a "Composition Reference" and a photo of your face as a "Character Reference." Use a prompt like: "A cinematic shot of a [Persona] in a [Environment], high detail, 8k."

5. Video-to-Video Generation

Use a tool like Luma Dream Machine or Runway Gen-3. Upload your live-action "driving" video and the reference image you just generated. Set the "Motion" or "Strength" slider to ensure the AI follows your movements but keeps the style of the image.

6. Character Consistency

To keep the face the same, ensure your reference photo is clear and that you use the same "Character Reference" seed or image across all generations.

7. The 3-Panel Edit

In CapCut or Premiere Pro, create a 9:16 sequence. Stack your three clips vertically.

Top: The Sketch (Crop to top 1/3).
Middle: The AI Video (Crop to middle 1/3).
Bottom: The Live Action (Crop to bottom 1/3).

8. Publishing Strategy

Sync the scene changes to a trending "beat-drop" audio. Add text overlays like "AI VIDEO IS GETTING WILD" to the middle panel to frame the narrative.

Growth Playbook: Distribution & Scaling

3 Opening Hook Lines

"Stop paying for film crews. This AI workflow is insane."
"I turned my kitchen into a Hollywood set using a simple sketch."
"The secret to consistent AI characters is finally here."

4 Caption Templates

The "Value" Lead: "AI Video production just got a massive upgrade. 🚀 I used [Tool Name] to turn these sketches into cinematic scenes. Which one is your favorite? Comment 'TECH' for the full breakdown!"
The "Behind the Scenes" Lead: "Expectation vs. Reality. 🎭 Swipe to see how I recorded the 'driving' footage for these AI shots. It’s easier than you think. #AIVideo #CreativeProcess"
The "Question" Lead: "Archery or Opera? 🏹 Which AI transformation hit the hardest? I’m showing you exactly how to maintain character consistency in my latest guide. Link in bio!"
The "Short & Punchy": "Sketch to Cinema. ✍️🎬 The future of storytelling is here. Type 'AI' to get the tool list."

Hashtag Strategy

Broad (Reach): #AI #GenerativeAI #VideoProduction #Filmmaking
Mid-Tier (Niche): #AIVideo #LumaAI #RunwayGen3 #DigitalCreator
Long-Tail (Specific): #SketchToVideo #AICharacterConsistency #IndieFilmmaker #AIWorkflow

Frequently Asked Questions

What tools make it look the most similar?

Use Leonardo.ai for the reference image and Luma Dream Machine or Runway Gen-3 for the video-to-video transformation.

What are the 3 most important words in the prompt?

"Composition reference," "Cinematic lighting," and "Character consistency."

Why does the generated face look inconsistent?

You likely didn't use a strong enough "Character Reference" image or your "driving" video has too much motion blur.

How can I avoid making it look like AI?

Lower the "AI Strength" in your V2V tool to retain more of the natural movement from your live-action footage.

Is it easier to go viral on Instagram or TikTok with this?

Instagram currently favors high-aesthetic "magic" transformations, while TikTok favors the "how-to" breakdown aspect.

How should I properly disclose AI use?

Use the platform's built-in "AI Generated" label and mention the tools used in your caption to build trust with your audience.