0:00 / 0:00

New UNLIMITED GENERATIONS on Kling Speak 🔥 Comment “AI” for a link to try it yourself! #HiggsfieldAI #SoulID #UnlimitedGenerations #CustomAICharacter #ConsistentAICharacter #AIImageGenerator #AIVideoGenerator #KlingAI #KlingAvatar #AILipSync #GenerativeAI #CreativeAI #AIForCreators #AIMagic #AIContentCreation #NextGenVideo #AIStorytelling #InnovativeAI #SmartAI #DigitalCreators #CreatorEconomy

Rourke Sefton-Minns

@rourke · creator

INSTAGRAM · 2025-09-21Source

1.9Klikes

406comments

Remix This

Recreate with Kling 3

Make your own AI viral video

Prompt

GLOBAL LOCK:
Subject is a Caucasian male in his early 30s, dark wavy hair, well-groomed medium-length beard, expressive brown eyes. He maintains a consistent facial structure across all shots. The visual style is a mix of high-end editorial photography and UGC tutorial footage. Lighting is cinematic with soft key lights and motivated rim lighting. Color grade is professional with deep blacks and vibrant but natural skin tones. Speech is clear, energetic, and instructional, delivered with a warm, authoritative tone.

[00:00–00:01]
Subject: MCU of the man wearing a dark suit, white dress shirt, black tie, and a white baseball cap with a green brim.
Action: Talking directly to the camera. A vertical white rectangular mask moves across his face, revealing a slightly different version of the same scene.
Camera: Static MCU, eye-level.
Lighting: Soft studio lighting, neutral background.
Speech: "This is how you can create..."

[00:01–00:04]
Subject: Rapid montage of AI-generated images. 
1. Man in a dark suit and sunglasses driving a green car at night, "AI MAG" text overlay.
2. Man in a checkered blazer and paisley tie in front of a brick wall.
3. Man in a white short-sleeve shirt with multiple pens in his pocket, standing in a white studio.
Action: Static editorial poses.
Camera: Various (MS, MCU).
Lighting: Cinematic, high contrast, nighttime car lighting, studio softbox.
Grade: Magazine editorial style.

[00:05–00:08]
Subject: A 3x4 grid of 12 different AI portraits of the same man in various outfits (boxing gloves, red car, street style, suit).
Action: Static images.
Overlay: Large bold text "UNLIMITED GENERATIONS" in orange and blue.
Camera: Flat grid layout.
Lighting: Varied per image.

[00:09–00:14]
Environment: Screen recording of the Higgsfield.ai website interface. A cursor moves to click "Image" then "Soul ID Character".
Action: UI navigation.
Speech: "On Higgsfield.ai, go to image and select Soul ID Character..."

[00:15–00:20]
Subject: Picture-in-picture of the man talking (wearing a tan cap and beige shirt) over a screen recording of the "Make Your Own Character" page.
Action: Explaining the process while gesturing.
Speech: "...where you can actually create your own custom character of yourself by uploading a bunch of photos."

[00:21–00:24]
Subject: Montage of AI images with text prompts.
1. Man in a suit drinking from a glass (trippy lens effect).
2. Man in a tan suit with a "Micky Mouse Bag" in a city street.
3. Man in a white tank top and jeans in front of a "Tokyo Red Car".
Action: Posing.
Camera: Full body and MS.
Lighting: Bright daylight, stylized urban lighting.

[00:25–00:34]
Environment: Screen recording of the "Lipsync Studio" interface. Subject's PIP continues.
Action: Selecting "Video", then "Lipsync Studio", uploading an image of himself at the beach, and dragging an audio file named "voiceover.wav".
Speech: "Now you can go to video at the top of the page and select the Lipsync Studio where you can upload your photo and audio..."

[00:35–00:38]
Subject: CU of the man at a tropical beach. He is shirtless, wearing black swimming goggles on his head.
Action: He is lip-syncing perfectly to the audio, smiling slightly.
Environment: Bright blue ocean water with small waves in the background.
Camera: CU, static.
Lighting: Bright, direct sunlight with natural shadows.
Speech: "...and it will combine those two together with the best lip-sync models."

NEGATIVE PROMPT:
Visual: robotic movement, distorted facial features, inconsistent beard growth, blurry textures, flickering background, extra fingers, warped UI elements, low resolution, watermarks.
Speech: robotic monotone, lip-sync delay, muffled audio, background hiss, unnatural pauses, slurred consonants, popping sounds.

SPEECH PACK:
[00:00-00:08]
Transcript: "This is how you can create 25 magazine-ready images of yourself using AI and then you can even lip-sync on top of them with this brand new feature."
TAKE_A: (Energetic, fast-paced) "This is how you can create TWENTY-FIVE magazine-ready images of yourself using AI... and then you can even LIP-SYNC on top of them with this brand new feature!"

[00:09-00:20]
Transcript: "On Higgsfield.ai, go to image and select Soul ID Character where you can actually create your own custom character of yourself by uploading a bunch of photos."
TAKE_A: (Instructional, clear) "On Higgsfield dot A-I, go to image and select Soul I-D Character... where you can actually create your own custom character of yourself... by uploading a bunch of photos."

[00:25-00:38]
Transcript: "Now you can go to video at the top of the page and select the Lipsync Studio where you can upload your photo and audio and it will combine those two together with the best lip-sync models."
TAKE_A: (Helpful, concluding) "Now you can go to video at the top of the page and select the Lipsync Studio... where you can upload your photo and audio... and it will combine those two together with the best lip-sync models."

How rourke Made This Higgsfield Soul ID AI Video — and How to Recreate It

This case study analyzes a high-performing tutorial by creator @rourke, focusing on the "Soul ID" and "Kling Speak" features of the Higgsfield AI platform. The video demonstrates how to achieve the "holy grail" of AI content creation: consistent character identity across multiple generated images and videos. By showcasing a "magazine-ready" aesthetic—ranging from cinematic car shots to editorial portraits—the video taps into the desire for high-end personal branding without the cost of a professional photoshoot. The visual style blends "UGC-style" direct-to-camera narration with polished, AI-generated b-roll, creating a bridge between authentic human connection and futuristic technology. Key keywords include consistent AI character, AI lip-sync, Higgsfield AI tutorial, and cinematic AI portraits.

What You’re Seeing: A Visual Deep Dive

The video opens with a high-energy hook featuring the creator, @rourke, in a split-screen mask effect that immediately signals "high-tech editing." He is a Caucasian male with dark wavy hair and a groomed beard, wearing a unique combination of a formal suit and a casual baseball cap. This "business-casual-creative" wardrobe choice establishes a relatable yet professional persona.

The scene transitions rapidly through a series of AI-generated "magazine covers" and editorial shots. We see the subject in a car at night with motion blur, in a checkered blazer against a brick wall, and in a quirky "nerd-chic" outfit with pens in his pocket. The lighting in these AI shots mimics professional studio setups: soft key lights, motivated rim lighting, and high-contrast cinematic grading. The final segment showcases a seamless lip-sync video of the creator at a tropical beach, demonstrating the platform's ability to handle complex textures like water and skin highlights while maintaining perfect facial synchronization.

Shot-by-Shot Breakdown

Time Range	Visual Content	Shot Language	Lighting & Tone	Viewer Intent
00:00–00:01	Creator talking with a vertical mask overlay.	MCU / Static	Neutral Studio	Hook: Visual curiosity.
00:01–00:04	Rapid montage of "AI MAG" covers.	Editorial Portraits	Cinematic / High Contrast	Proof of quality.
00:05–00:08	3x4 grid of diverse AI generations.	Grid Layout	Vibrant / Varied	Showcase "Unlimited" variety.
00:09–00:14	Screen recording of Higgsfield UI.	UI Capture	Dark Mode Tech	Tutorial: Where to click.
00:15–00:20	Creator explaining "Soul ID" character creation.	UGC / Picture-in-Picture	Warm / Relatable	Build trust & authority.
00:21–00:24	Montage of specific AI prompts (e.g., "Tokyo Red Car").	Full Screen AI	Stylized / Thematic	Inspiration for prompts.
00:25–00:34	Workflow of uploading audio for lip-sync.	UI Capture	Technical	Instructional clarity.
00:35–00:38	Final AI beach video with lip-sync.	CU / AI Video	Bright / Tropical	The "Aha!" moment / Result.

Why It Went Viral: The Mechanics of AI Hype

The "Identity Consistency" Pain Point

The primary reason this video resonated is that it solves the biggest frustration in AI art: making the AI generate the same person twice. By leading with "25 magazine-ready images of yourself," @rourke addresses a high-intent audience of creators looking to scale their personal brand.

The "Unlimited" Psychological Trigger

The use of the word "UNLIMITED" in large, bold text overlays (00:05) triggers a scarcity-reversal response. In a world of credit-based AI tools, the promise of unlimited generations is a powerful "stop-the-scroll" mechanism.

The Engagement Loop (Comment "AI")

The creator uses a classic "Comment for Link" strategy. This does two things: it explodes the comment count, signaling to the Instagram algorithm that the post is highly engaging, and it automates lead generation for the tool being promoted.

Platform Perspective: Why the Algorithm Loved It

Instagram's algorithm prioritizes Watch Time and Save Rate. This video excels at both. The fast-paced montage in the first 3 seconds ensures viewers don't swipe away, while the step-by-step UI tutorial makes the video "save-worthy" as a reference for later use. The high-contrast, colorful AI images are perfectly optimized for mobile screens, popping against the standard feed.

5 Testable Viral Hypotheses

The "Self-Cloning" Hook: If you show a human and their AI twin in the first 1 second, watch time increases by 30% because of the "uncanny valley" curiosity.
The UI-Overlay Credibility: Showing the actual software interface (00:09) reduces skepticism compared to just showing the final results.
The "Magazine" Framing: Using a "Magazine Cover" template (00:02) provides a familiar context for "high quality," making the AI results feel more professional.
Audio-Visual Sync: Cutting the image transitions to the beat of the background music (00:01-00:08) creates a "flow state" that keeps viewers watching.
The "Comment AI" CTA: Replacing a link-in-bio with a comment-trigger increases reach by 2-3x due to the immediate boost in engagement signals.

How to Recreate: From 0 to AI Clone

Select Your Tool: Use a platform like Higgsfield AI or a local Stable Diffusion setup with LoRA training.
Capture Reference Photos: Take 10-15 high-quality selfies of yourself in different lighting and angles. This is the "Soul ID" or training data.
Train the Character: Upload these to the "Soul ID" or "Character" section of your chosen AI tool to lock in your facial features.
Generate "Editorial" Shots: Use prompts like "Cinematic editorial portrait, 35mm lens, magazine lighting, [Your Character Name] wearing a tailored suit."
Record Your Voice: Record a 10-second audio clip of yourself speaking naturally.
Apply Lip-Sync: Use a tool like "Kling Speak" or "Lipsync Studio" to map your audio onto one of your generated AI images.
Edit the Hook: Use a masking effect in CapCut or Premiere Pro to show your real self and AI self in the same frame.
Publish with Engagement Bait: Use a "Comment [Keyword]" call to action to drive the algorithm.

Growth Playbook: Hooks & Captions

3 Ready-to-Use Opening Hooks

"Stop paying for professional headshots. Do this instead..."
"I found the secret to making AI look exactly like you."
"Unlimited AI generations are finally here, and they're scary good."

4 Caption Templates

The "Value First" Template:
[Hook: How to clone yourself in 60 seconds] 🤖
[Value: I just tested the new Soul ID feature and the consistency is insane. No more random faces.]
[Question: Which style should I try next? Streetwear or Cyberpunk?]
[CTA: Comment "CLONE" and I'll send you the step-by-step guide.]

Hashtag Strategy

Broad (Reach): #AI #ArtificialIntelligence #TechTrends #ContentCreator
Mid-Tier (Niche): #AIVideo #AIArt #HiggsfieldAI #GenerativeAI
Long-Tail (High Intent): #ConsistentAICharacter #AITutorial #AILipSync #DigitalTwin

Frequently Asked Questions

What tools make it look the most similar?

Higgsfield AI's Soul ID and Kling Speak are the specific tools shown in this video.

How many photos do I need for a consistent character?

Usually, 10 to 20 high-quality photos from different angles work best.

Is this free to use?

Most tools have a free trial, but "unlimited" features usually require a subscription.

How do I avoid the "AI look"?

Use specific camera lens prompts like "35mm" or "85mm" and mention "film grain" or "natural skin texture."

Can I do this on my phone?

Yes, Higgsfield and similar tools are accessible via mobile web browsers.