0:00 / 0:00

How to create consistent AI outputs with @freepik spaces🔥 Comment “AI” for a link #FreepikSpaces #FreepikAI #NodeBasedWorkflow #AISuite #AIImageGenerator #AIVideoGenerator #GenerativeAI #CreativeAI #AIForCreators #SmartWorkflow #DigitalCreators #NextGenDesign #AIContentCreation #CreativeTools #InnovativeAI #AICollaboration #VisualStorytelling #CreatorEconomy #AIEditingTools #AIDesignAgent

Rourke Sefton-Minns

@rourke · creator

INSTAGRAM · 2025-11-14Source

3.0Klikes

1.1Kcomments

Remix This

Recreate with Kling 3

Make your own AI viral video

Prompt

GLOBAL LOCK:
Subject is a Caucasian male, mid-30s, with a well-groomed dark beard and mustache. In the cinematic sequence, he is wearing a full suit of polished silver medieval knight armor with intricate engravings. He wears a dark green baseball cap backwards under his helmet or as a stylistic choice. The environment is a dramatic, smoky battlefield with an overcast, moody sky and orange flames/explosions in the background. The color grade is cinematic, desaturated with high contrast and warm highlight roll-off from the fires. Camera movement is dynamic, following the subject.

[00:00–00:05]
Split-screen view. Bottom: Creator talking to camera in a white/black striped hoodie and "VANS" cap. Top: A dark digital interface showing a node-based workflow with lines connecting "Creation," "Text," and "Image Generator" boxes. The creator points down toward the microphone.

[00:05–00:10]
Top screen: A full-body photo of the male subject in a white t-shirt and striped pants against a white wall. The background of the photo then turns into a bright, solid green screen.

[00:10–00:15]
Top screen: Individual 3D-rendered silver armor pieces (gauntlet, chest plate, greaves) float around the subject on the green screen, then snap onto his body, replacing his clothes.

[00:15–00:25]
Top screen: The subject, now in full knight armor, is seated on a majestic white horse. The background is still a green screen. A white horse asset appears and he is composited onto it.

[00:25–00:45]
Top screen: A cinematic wide shot of the knight on the white horse galloping through a war-torn field. Thick grey smoke billows behind him. He holds a large red and green flag with a "GenHQ" logo that waves violently in the wind. Explosions of orange fire erupt in the background. The camera tracks the horse's movement with a slight handheld shake.

[00:45–00:51]
The cinematic knight sequence continues. Large white text "Comment 'AI'" is centered on the screen. The creator in the bottom frame continues to speak and gesture enthusiastically. The horse slows to a trot as the flag continues to wave.

NEGATIVE PROMPT:
Visual: robotic movement, distorted face, inconsistent armor textures, blurry horse legs, floating objects, cartoonish colors, low resolution, flickering lighting, extra limbs, text/logos other than specified.
Speech: robotic tone, muffled audio, background noise, lip-sync mismatch, stuttering, flat delivery.

SPEECH PACK:
[00:00–00:05]
"This new method of creating AI generated content gives us so much control over the output."
TAKE_A: (Enthusiastic, fast-paced) "This new method of creating AI generated content gives us so much control over the output!"
TAKE_B: (Authoritative, measured) "This new method... of creating AI generated content... gives us so much control over the output."
TAKE_C: (Casual, friendly) "Check this out—this new AI method gives you total control over what you're making."

[00:45–00:51]
"So if you want to try this out for yourself, type AI in the comments and I'll send you the link."
TAKE_A: (Direct, urgent) "So if you want to try this out for yourself, type AI in the comments and I'll send you the link!"
TAKE_B: (Warm, inviting) "Want the link? Just type AI in the comments and I'll send it right over."
TAKE_C: (Punchy, instructional) "Type AI below and I'll DM you the link to try this yourself."

How rourke Made This Freepik Spaces Consistent Character AI Video — and How to Recreate It

This case study analyzes a high-performing tutorial by creator @rourke, demonstrating how to achieve consistent AI character outputs using Freepik Spaces. The video utilizes a highly effective split-screen layout: the bottom half features a high-energy "talking head" commentary, while the top half showcases a dynamic, node-based software interface and the resulting cinematic AI generation. The core hook revolves around a dramatic transformation—taking a simple photo of the creator in a white t-shirt and evolving it into a cinematic shot of a knight in silver armor riding a white horse through a smoky battlefield. This "UGC-meets-Cinematic" aesthetic bridges the gap between relatable creator content and high-end AI capabilities, making complex technology feel accessible to indie creators.

What You’re Seeing

The video is structured as a fast-paced technical walkthrough. The creator is positioned in the bottom third of the frame, wearing a branded "VANS" cap and a striped hoodie, speaking directly into a professional microphone. This establishes immediate authority and trust. The top two-thirds of the frame are dedicated to the "canvas," showing the Freepik Spaces interface where nodes (media, text, image generators) are connected by flowing lines. The color palette shifts from the clean, white-walled aesthetic of the initial photo to the vibrant green of a virtual "green screen," and finally to the desaturated, moody tones of a cinematic war zone.

Shot-by-Shot Breakdown

Time Range	Visual Content	Shot Language	Lighting & Tone	Viewer Intent
00:00–00:05	Split screen: UI nodes at top, creator at bottom.	Medium Close-up (MCU) for creator; Screen recording for UI.	Neutral indoor lighting; High-tech UI feel.	Hook: Promise of "control" over AI output.
00:05–00:15	Creator's photo transforms to green screen, then armor pieces appear.	Static portrait photo vs. dynamic UI overlays.	Bright, saturated green screen contrast.	Process: Show the "magic" of asset compositing.
00:15–00:45	Full cinematic sequence: Knight on horse, smoke, fire, waving flag.	Dynamic tracking shot; Horse galloping; Flag waving.	Moody, overcast, warm fire highlights, cinematic grain.	Payoff: Demonstrate the high-quality final result.
00:45–00:51	Final result with "Comment AI" text overlay.	Slow motion; Text centered.	Cinematic desaturation.	CTA: Drive engagement through comments.

Why It Went Viral

The Power of "Control" in AI

The primary reason this video resonated is that it addresses the #1 pain point for AI creators: consistency and control. Most AI tools feel like a "slot machine" where you prompt and pray. By showcasing a node-based workflow, @rourke appeals to the psychological need for agency. Creators don't just want a cool image; they want to know how to build it step-by-step. The transition from a casual t-shirt photo to a medieval knight provides a "wow factor" that serves as the perfect visual proof of the tool's power.

Platform Signals & Engagement Triggers

From a platform perspective, this video is a masterclass in retention and conversion. The split-screen format keeps the eye moving, preventing "scroll fatigue." The fast-paced editing (cuts every 2-3 seconds) ensures high watch time. Most importantly, the "Comment AI" CTA is a strategic move to trigger Instagram's algorithm. High comment volume signals to the platform that the content is valuable, pushing it to a wider audience. This is likely paired with an automation tool (like ManyChat) to deliver the link, creating a seamless funnel.

5 Testable Viral Hypotheses

The "Control" Hook: If you start a video by promising "total control" over a chaotic process (like AI), retention will increase by 20% in the first 5 seconds.
The Split-Screen Authority: Placing the creator's face at the bottom while showing the "work" at the top builds more trust than a voiceover alone.
Asset-to-Outcome: Showing individual assets (armor, horse, flag) before the final composite creates a "Lego effect" that makes the result feel more achievable.
Keyword Triggering: Using a simple, 2-letter keyword ("AI") for the CTA reduces the friction for users to engage, leading to 3x more comments.
Cinematic Contrast: Moving from a "boring" real-life photo to a "epic" AI scene creates a dopamine hit that encourages shares.

How to Recreate: From 0 to 1

Identify the Transformation: Choose a simple starting point (e.g., a selfie) and a high-concept ending point (e.g., a cyberpunk pilot or a fantasy wizard).
Record the Talking Head: Film yourself in a well-lit room with a clean background. Use a striped or textured shirt to add visual interest. Ensure your audio is crisp.
Capture the UI: Use a screen recorder (like Loom or OBS) to capture the node-based workflow in Freepik Spaces. Focus on the "connecting" of nodes to emphasize the logic.
Generate Consistent Assets: Use the "Image Generator" nodes to create specific pieces (armor, background, props) while maintaining the same seed or character reference.
The "Green Screen" Step: Explicitly show the step where you remove the background of your original photo to place it into the AI scene. This is a crucial "how-to" moment.
Edit the Split Screen: In your editing software (CapCut or Premiere), stack the screen recording on top and your talking head on the bottom. Use a 70/30 or 60/40 split.
Add Dynamic Overlays: Include text captions that mirror what you are saying, and use red circles or arrows to point out key UI elements.
Craft the CTA: End the video with a clear, high-contrast text overlay telling users exactly what to comment to get the tool link.

Growth Playbook

3 Opening Hook Lines

"Stop gambling with your AI prompts—here’s how to get total control."
"This new node-based workflow is changing how we create AI content."
"I turned this simple selfie into a cinematic masterpiece in 60 seconds."

4 Caption Templates

Option 1: The Problem/Solution
Tired of AI giving you random results? 😤
Freepik Spaces lets you build consistent characters using a node-based workflow. It’s like Lego for AI.
Want to try it yourself?
👇 Comment "AI" and I’ll send you the link!

Hashtag Strategy

Broad (Reach): #AI #GenerativeAI #CreativeTech #DigitalArt
Mid-Tier (Targeted): #AIForCreators #ContentCreationTips #Freepik #AITutorial
Niche (Long-tail): #NodeBasedWorkflow #ConsistentAI #FreepikSpaces #AIWorkflow

Frequently Asked Questions

What tools make it look the most similar?

Freepik Spaces for the workflow and CapCut for the split-screen editing.

How do I keep the face consistent?

Upload a clear reference photo of yourself into the "Media" node as a base.

Is this easier on Instagram or TikTok?

Instagram is currently favoring "educational/tool" reels with high comment-to-link automation.

How do I avoid the "AI look"?

Use specific lighting prompts like "overcast cinematic lighting" and add "film grain" in post-production.

Do I need to disclose AI use?

Yes, use the platform's built-in "AI-generated" label to maintain transparency and trust.