Cinematic Success of 'Stay' by The Kid LAROI & Justin Bieber

The "Stay" music video owes its cinematic success to director Colin Tilley's frozen-time concept, where LAROI and Bieber move through motionless crowds in an abandoned LA hotel. Wire harnesses created seamless levitation sequences that Digital Axis then scrubbed clean in post. The result? Over two billion YouTube views, a TikTok clip that earned 43.9 million likes, and a drone-shot hilltop dance the world couldn't stop recreating. There's plenty more behind every frame worth knowing.

Key Takeaways

• Director Colin Tilley's frozen-time concept, where performers move while surrounding pedestrians remain motionless, gave the video a striking, emotionally resonant visual identity.
• Wire harnesses enabled seamless levitation sequences through cityscapes, with VFX studio Digital Axis removing all rigging traces in post-production.
• The TikTok-friendly drone-shot hilltop dance sparked mass recreation, with one clip earning 43.9 million likes, TikTok's highest ever.
• The official YouTube video surpassed one billion views by April 2025, averaging 1.6 million daily views by mid-2024.
• The MTV VMA live performance version achieved three times the views of its acoustic counterpart, extending the video's cultural reach significantly.

Why the 'Stay' Music Video Became a Cultural Moment Overnight

When TikTok released its 2021 year-end report, one video stood above the rest: @totouchanemu dancing to "Stay" atop a hilltop, captured by drone footage. You can see why it resonated — the drone choreography transformed a simple butt-shake and arm-rotation into something cinematic and oddly personal. That viral intimacy pulled 313 million viewers in, making it TikTok's number one video globally and in the US.

Uploaded on July 28, the clip earned 43.9 million likes, outperforming every other video on the platform. The performer's blue button-up shirt, white over-the-ear headphones, and sunglasses gave it a casual authenticity you couldn't ignore. TikTok credited the video with sparking some of 2021's biggest trends, cementing "Stay" as the year's defining audio track. Much like the landmark April 2019 black hole image, which required over 200 researchers collaborating across continents to produce a single groundbreaking visual moment, viral cultural phenomena often depend on vast, coordinated effort behind the scenes.

The man behind the viral moment is David Allen, an Austin, Texas-based wedding photographer who, despite amassing 8.9 million followers almost overnight, remained candid about not fully understanding why the video exploded the way it did. The explosive spread of content like this is made possible by the open and freely accessible web infrastructure that followed CERN's decision to release its WWW code into public domain in April 1993, removing barriers that once limited who could publish and who could watch.

700 Million YouTube Views: What They Reveal About 'Stay's Visual Power

Numbers rarely lie, and "Stay's" YouTube trajectory tells a story of genuine visual magnetism. You're looking at over 2 billion official views since 2021, averaging 1.6 million daily by mid-2024. That's not passive consumption — that's active rewatching driven by something compelling on screen.

The underwater symbolism throughout the video creates an immersive pull that keeps viewers returning. Combined with deliberate color grading that shifts emotional tones seamlessly, the visuals feel cinematic rather than promotional. You can see this reflected in the high completion rates despite the 2:22 runtime — short enough to replay, rich enough to reward it.

The MTV VMA live version tripled the acoustic counterpart's views, confirming that "Stay's" visual identity isn't accidental. It's a carefully constructed experience that consistently earns attention across every format it appears in. Tracking how content performs across platforms is made easier with tools that provide real-time word tracking and character counts, helping creators fine-tune their writing to meet platform-specific guidelines.

What Colin Tilley's Direction Brought to 'Stay' That Made It Unforgettable

Colin Tilley transformed "Stay" from a chart-ready pop track into a visual experience you can't shake by building his entire concept around frozen time. He placed LAROI and Bieber inside an abandoned downtown LA hotel, letting urban decay amplify the song's emotional weight.

His temporal choreography positioned the two artists moving freely while everyone around them stood motionless, making isolation feel visceral rather than abstract. Tilley's use of ambient lighting deepened that tension, casting the frozen world in a mood that matched the lyrical plea for relationship persistence.

He integrated the track's fast-paced melody directly into the pacing of each shot, so the visuals never lag behind the music. That precision is exactly what pushed the video past one billion YouTube views by April 2025. The music video was released alongside the track on July 9th, 2021.

Levitating Through Cityscapes: The VFX Magic Behind the Video

Behind the levitation sequences in "Stay," Digital Axis handled all VFX work, covering 3D tracking, CG asset creation, animation, and compositing to make LAROI and Bieber float convincingly through frozen cityscapes. Despite the wire harness causing real discomfort during shoots, the team used motion capture data to sync performers seamlessly with dynamic urban environments.

Three standout VFX achievements made this possible:

1. Clean-up work erased all harness rigs from every frame
2. CG animation visualized energy combining between both performers mid-air
3. Night-scene compositing blended live footage with digital cityscapes for dramatic realism

You're watching over one billion views worth of precision — where painful filming conditions transformed into the video's most iconic visual moments. The entire production was brought to life under the creative vision of director Colin Tilley, whose signature visual storytelling shaped the levitation sequences into cinematic standouts.

Why Filming 'Stay' at Night in the City Was the Perfect Creative Call

While Digital Axis worked their VFX magic to erase harnesses and blend performers into frozen cityscapes, the foundation of those iconic visuals started with one smart creative call — shooting at night in the city. You see how the wet asphalt transforms into a canvas of urban reflections, multiplying ambient city lights without adding costly equipment. Night streets carry quiet stakes — empty, atmospheric, and full of mood that daytime shooting simply can't replicate.

Cinematographers often wet surfaces deliberately to amplify this effect, and city lights naturally reduce the need for elaborate lighting setups. RAW footage captured on high-end cameras like RED allows post-production teams to recover dark details precisely, balancing street light overexposure while maintaining those clean, cinematic dim exteriors that made "Stay" so visually compelling.

Beyond the camera work itself, productions frequently modify or gel practical bulbs on set to ensure consistency across the lighting plan, preventing jarring tonal mismatches that could undermine the mood. Modifying practical bulbs is a standard but often overlooked discipline that quietly holds the entire visual aesthetic together.

The Relationship Themes Written Into Every Visual Choice in 'Stay'

Every visual choice in "Stay" carries the weight of its relationship themes, translating lyrical desperation into imagery you can feel before you hear a single word. Attachment motifs surface through isolated performers in vast settings, mirroring a child's terror of abandonment. Pleading choreography reinforces the refrain's emotional urgency, making each gesture feel like a genuine cry for connection.

Three deeper meanings embedded in the visuals:

1. Reaching hands symbolize the dread of emotional isolation within insecure bonding.
2. Nighttime city shots reflect feeling completely lost without a partner's empathy.
3. Alternating solo and duet frames expose dysfunctional persecutor-victim-rescuer cycles driving the relationship.

Together, these choices don't just support the lyrics — they make you experience the song's emotional collapse firsthand. The visual language draws directly from the emotional blueprint shaped by early caregiving experiences, where a caregiver's consistent presence or absence becomes the template for how love, fear, and desperation are later expressed in adult relationships.

Behind the Scenes: LAROI and Bieber's High-Energy Filming Collaboration

The cameras rolled for a relentless twelve hours as Colin Tilley directed LAROI and Bieber through a high-energy single-day shoot on a custom-built, stadium-inspired soundstage.

You'd notice immediately how wardrobe logistics kept pace with rapid costume changes between shots, never breaking the production's momentum.

Both artists arrived prepared, rehearsed jointly, and improvised ad-libs that added authentic spontaneity to each take.

Their vocal endurance matched their physical intensity, with sweat-heavy performances demanding precise footwork and synchronized choreography throughout.

LAROI shared behind-the-scenes footage, revealing genuine laughter breaks that maintained morale without sacrificing focus.

When tech glitches surfaced, the crew resolved them on-site, preserving the live-energy feel Tilley prioritized.

Their mutual encouragement transformed a demanding schedule into a seamlessly executed, high-voltage creative collaboration. LAROI specifically highlighted how much he loved vibing off Bieber's energy on set, noting that Bieber brought an exceptional level of intensity to every moment in front of the camera.

The Visual Decisions in 'Stay' That Gave It Longer Cultural Legs Than Any Chart Run

What made that high-voltage production matter beyond its twelve-hour shoot was how deliberately every visual choice was engineered to travel.

The drone choreography captured @totouchanemu's hilltop dance so cleanly that 313 million views followed. Colin Tilley's color grading gave levitating cityscapes a shareable texture that charts alone couldn't sustain.

Here's why those decisions extended the song's cultural life:

1. Drone choreography made the hilltop dance instantly recreatable, sparking millions of TikTok recreations and 43.9 million likes on a single video.
2. Levitation sequences humanized production pain, generating behind-the-scenes stories that kept audiences engaged post-charts.
3. The montage pre-release on July 12 built visual familiarity before the official drop, priming audiences to recognize and share the aesthetic immediately.

The Specific Visual Choices That Separated 'Stay' From Every Other 2021 Music Video

Few 2021 pop videos dared to freeze time — literally. Colin Tilley's direction placed The Kid LAROI and Justin Bieber inside a world of urban stillness, where every surrounding pedestrian stopped moving while the performers kept going.

That contrast wasn't decorative — it visually embodied the song's emotional core: connection that exists outside normal life's rhythm.

Then came the harness choreography. LAROI actually floated through those cityscapes using wire rigging, blending practical harness work with post-production effects to create seamless levitation.

The discomfort of wearing that equipment made the dreamlike result even more deliberate — nobody adds that complexity without clear creative intention.

Together, these choices gave "Stay" something most pop videos skip entirely: a visual language specific enough to carry the song's meaning long after the charts moved on. The song itself spent seven non-consecutive weeks at number one on the Billboard Hot 100, a commercial dominance that gave the video's imagery an unusually long runway to embed itself in cultural memory.