0:00 / 0:00

Flux 2 just released and it’s almost pixel perfect for text 👍 Comment “AI” to get access to Flux 2 on Leonardo AI #Flux2 #AIImageModel #AIImageGenerator #GenerativeAI #CreativeAI

Rourke Sefton-Minns

@rourke · creator

INSTAGRAM · 2025-11-26Source

6.2Klikes

1.0Kcomments

Remix This

Recreate with Wan2.6

Make your own AI viral video

Prompt

GLOBAL LOCK: Subject is a male in his mid-30s with light brown wavy hair, a well-groomed beard, wearing a tan "Vans" custom classic trucker hat and a plain white t-shirt. The environment transitions between macro paper textures, cinematic outdoor settings, and clean studio backgrounds. Lighting is consistently high-quality, ranging from warm golden hour to professional high-key studio. Color grade is vibrant with high contrast and sharp details. Speech is energetic, direct-to-camera, with a warm and professional tone.

[00:00–00:04]
Macro extreme close-up of a sharpened graphite pencil writing "FLUX 2" in bold, sketchy capital letters on heavily textured white watercolor paper. Small graphite particles are visible around the strokes. The camera is static. Lighting is bright, natural side-lighting emphasizing the paper grain.
SPEECH: "Flux 2 just released and honestly..."

[00:04–00:08]
A series of rapid cuts: 1) A cinematic portrait of the subject (male, Vans hat, beard) in golden hour sunlight with soft bokeh. 2) A full-body shot of the same subject wearing a multi-colored, patchwork editorial suit against a magenta background. 3) An extreme macro close-up of a blue human eye with hyper-realistic skin texture and reflection in the pupil.
SPEECH: "...the details on this AI image model are insane. You can create photo-realistic images of yourself from any angle and it's spotless."

[00:08–00:14]
Product photography shots: 1) A white tube of "Green People" sun cream with clear, legible orange and black text, centered on a clean white/blue background. 2) A matte grey "Stanley" tumbler with a black lid, standing on a vibrant orange surface with a soft shadow. The text on the tumbler is perfectly rendered.
SPEECH: "And don't even get me started on text. You can now create packaging flawlessly with any products now using this image model."

[00:14–00:17]
Medium close-up of the subject (male, beard, long hair) wearing a bright yellow blazer over a green shirt. He looks directly into the camera with a confident expression. Large white text overlay reads "Here's How".
SPEECH: "So here's how you can access it too."

[00:17–00:23]
Screen recording of the Leonardo.ai user interface in dark mode. A cursor clicks on "Image Generation," then selects the "FLUX.1 PRO" model from a dropdown menu. The UI is clean and responsive.
SPEECH: "To get started, go to Leonardo AI, where you can go to image, then you can go to the Flux 2 Pro model."

[00:23–00:28]
A sequence showing the prompt "suncream on a product shelf in a pharmacy" being typed, followed by a grid of generated images showing realistic pharmacy shelves filled with sun cream bottles, all with legible labels and realistic store lighting.
SPEECH: "You can write in a prompt with a reference photo and it will create the most stunning, realistic AI images you've ever seen."

[00:28–00:32]
Macro shot of a hand using a pencil to draw a detailed portrait of the subject's face on paper, followed by the pencil writing "Comment AI" in elegant cursive. The camera zooms in slightly on the text.
SPEECH: "So if you want to try it out for yourself, type AI in the comments and I'll send you a link."

NEGATIVE PROMPT: Robotic speech, monotone delivery, blurry text, mangled fingers, inconsistent facial features, low-resolution textures, flickering lighting, unnatural eye movements, watermarks, distorted UI elements, muddy colors.

SPEECH PACK:
[00:00-00:04]
TAKE_A: "Flux 2 just released and honestly, the details on this AI image model are insane."
TAKE_B: "Flux 2 is finally here, and the level of detail in this model is absolutely mind-blowing."
TAKE_C: "Check this out: Flux 2 just dropped, and the image quality is on a whole different level."

[00:04-00:14]
TAKE_A: "You can create photo-realistic images of yourself from any angle and it's spotless. And don't even get me started on text. You can now create packaging flawlessly."
TAKE_B: "From perfect portraits to flawless product shots, this model handles everything. Look at how it renders text on this packaging—it's perfect."

[00:14-00:32]
TAKE_A: "So here's how you can access it too. Go to Leonardo AI, select the Flux 2 Pro model, and type your prompt. Comment AI for the link!"
TAKE_B: "Want to try it? Head over to Leonardo AI, find Flux 2 Pro, and start creating. If you want the direct link, just comment AI below."

Why rourke's Flux 2 AI Video Went Viral and the Formula Behind It

This case study analyzes a high-performing AI tool review by creator @rourke, focusing on the launch of the Flux 2 image model. The video utilizes a "talking head overlay" format, where the creator provides commentary over a rapid-fire sequence of high-fidelity AI-generated visuals. Key aesthetic elements include macro pencil-on-paper textures, cinematic editorial portraits, and clean product photography. By demonstrating Flux 2's superior text-rendering capabilities—a long-standing pain point in AI art—the video achieves high "save" and "share" value. The strategy centers on visual proof-of-work, using the creator's own likeness to build trust while leveraging a "Comment AI" automation trigger to drive massive engagement and lead generation.

What You’re Seeing: A Visual Analysis

The video is a masterclass in dynamic pacing. It opens with a macro shot of a pencil physically "writing" the words "FLUX 2" on textured paper, immediately establishing a tactile, non-digital feel that contrasts with the AI subject matter. The creator, @rourke, appears in a circular or rounded-square overlay at the bottom, wearing a consistent "Vans" brand cap and white t-shirt, which grounds the high-tech content in a relatable, "indie creator" persona.

The visual sequence moves from text-heavy macro shots to photorealistic portraits of the creator himself (demonstrating identity consistency), then to commercial product renders (sun cream and tumblers). The lighting transitions from warm, golden-hour outdoor light in the portraits to clean, high-key studio lighting for the products. The editing rhythm follows the beat of an upbeat, rhythmic track, with cuts occurring every 1.5 to 2 seconds to maintain viewer attention. The color palette is vibrant but professional, emphasizing the "pixel-perfect" nature of the new model.

Shot-by-Shot Breakdown

Time Range	Visual Content	Shot Language	Lighting & Tone	Viewer Intent
00:00–00:04	Pencil writing "FLUX 2" and underlining text on paper.	Macro / Extreme Close-up	Natural, bright, high texture.	Hook: Visual proof of text rendering.
00:04–00:08	AI portraits of the creator (close-up and full body).	Medium Shot / Eye Close-up	Golden hour / Cinematic rim light.	Reinforce persona & identity consistency.
00:08–00:14	Product shots: Sun cream bottle and Stanley tumbler.	Product Close-up	Studio High-key / Vibrant orange.	Tutorial value: Commercial application.
00:14–00:17	Creator in a yellow jacket, looking at camera.	Medium Close-up	Warm, professional studio.	Transition to "How-to" section.
00:17–00:23	Screen recording of Leonardo.ai interface.	UI Capture	Dark mode / Tech-focused.	Educational: Showing the tool in use.
00:23–00:28	AI images of sun cream on pharmacy shelves.	Wide Shot / Multi-image grid	Fluorescent pharmacy lighting.	Demonstrate realism in complex scenes.
00:28–00:32	Pencil drawing of creator's face and "Comment AI".	Macro / Time-lapse feel	High contrast, graphite texture.	CTA: Drive comments for automation.

Why It Went Viral: The Breakdown

The primary driver of this video's success is Utility-Based Hype. By focusing on "Flux 2," a trending topic in the AI community, the creator taps into an existing search and interest surge. However, instead of just talking about it, he provides undeniable visual evidence. The "text-on-paper" shots solve a specific "pain point" (AI's historical struggle with text), which triggers a "wow" response and high shareability among other creators.

From a psychological perspective, the video uses Identity Mirroring. By showing AI-generated versions of himself that look nearly identical to his real-life talking head overlay, @rourke proves the model's capability for "character consistency"—the holy grail for AI filmmakers and brand builders. This creates a "if he can do it, I can do it" motivation for the viewer.

Platform Perspective: Instagram's algorithm prioritizes "Save" and "Comment" actions. The "Comment AI" call to action is a classic Engagement Loop. By promising a direct link or access via DM (likely using ManyChat), the creator forces the algorithm to see a high volume of interactions, which signals the content is valuable and pushes it to a broader "Explore" audience. The fast-paced cuts and high-quality "eye candy" ensure high retention (watch time), which is the secondary signal for viral distribution.

5 Testable Viral Hypotheses

The "Text Proof" Hook: If you show an AI model perfectly rendering complex text in the first 3 seconds, retention will increase by 40% because it solves a known industry flaw.
The "Double-Self" Effect: Placing a real talking head next to an AI version of the same person creates a "spot the difference" psychological game, increasing watch time.
The "Tactile Contrast" Strategy: Using macro shots of physical pencils and paper to introduce digital AI tools creates a sensory contrast that stops the scroll better than pure digital UI.
The "Niche Commercial" Use Case: Showing a specific product (like sun cream) rather than generic art makes the tool feel "profitable" to business owners, leading to higher saves.

The "Comment-to-DM" Frictionless CTA:

How to Recreate: From 0 to 1

Step 1: Topic Selection & Positioning

Identify a "Breaking News" or "Major Update" in your niche (e.g., a new AI model, a software feature, or a viral trend). Position yourself as the "tester" who provides the proof.

Step 2: Establish Your "Real" Persona

Record your talking head footage first. Wear a consistent accessory (like the Vans cap) to make your "AI clones" more recognizable later. Use a clean, well-lit background.

Step 3: Generate "Proof" Assets

Use Flux 2 (or your chosen tool) to generate 5-10 high-quality images. Focus on:

Text rendering (e.g., a sign, a label).
Your own likeness (use LoRA or Image-to-Image).
A commercial product relevant to your audience.

Step 4: Create the "Tactile" Hook

Film a 3-second macro shot of a pencil writing the name of the tool on paper. This "analog" opening is key to stopping the scroll in a digital-heavy feed.

Step 5: Screen Recording the "How-To"

Record a 5-10 second clip of the actual interface (e.g., Leonardo.ai). Show the mouse clicking the specific model name to provide "tutorial value."

Step 6: Dynamic Editing

In CapCut or Premiere, layer your talking head (remove background or use a mask) over the generated assets. Sync the cuts to a rhythmic beat. Add "punch-ins" (zooming in slightly) every few seconds.

Step 7: The "Comment Trigger" CTA

End the video with a visual of the pencil writing "Comment [KEYWORD]". Set up an automation tool like ManyChat to automatically DM anyone who uses that keyword.

Step 8: Publishing Strategy

Post as a Reel/TikTok. Use a cover image that shows a "Before/After" or a very clear "Text-in-AI" result. Keep the caption short and focused on the CTA.

Growth Playbook: Distribution & Scaling

3 Ready-to-Use Opening Hooks

"Stop scrolling—AI just solved its biggest problem with text."
"I put my own face into the new [Model Name] and the results are scary."
"This is exactly how you create professional product shots for $0."

4 Caption Templates

The "Value First" Template:
[Hook: Flux 2 is finally here and it’s a game changer.]
[Value: No more mangled fingers or gibberish text. I tested it on product design and portraits.]
[Question: What’s the first thing you’re going to generate?]
[CTA: Comment “AI” and I’ll send you the direct link to try it.]

Hashtag Strategy

Broad (Reach): #AI #GenerativeAI #TechTrends #ArtificialIntelligence
Mid-Tier (Niche): #Flux2 #LeonardoAI #AIArtCommunity #ContentCreatorTools
Long-Tail (Specific): #AIProductPhotography #AITextRendering #IndieCreatorTips

Frequently Asked Questions

What tools make it look the most similar?

Use Leonardo.ai for the Flux 2 model and CapCut for the talking-head overlay effect.

What are the 3 most important words in the prompt?

"Hyper-realistic," "Text-rendering," and "Cinematic-lighting."

Why does the generated face look inconsistent?

You likely need to train a LoRA on your specific face or use a stronger "Image Guidance" reference.

How can I avoid making it look like AI?

Mix in real-world macro footage (like the pencil shots) to ground the digital visuals.

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

Instagram Reels currently favor high-aesthetic "tutorial" content with comment-based automation.