How to Create a Viral Music Video with Sondo AI: The Hwasa’s Maria Formula
Using “Maria” by Hwasa as a case study, this article breaks down the core formula behind a viral music video—from raw, emotionally striking expression to an introspective “self-dialogue” core, as well as strong visual symbolism and emotion-driven storytelling. It shows that what truly connects with audiences isn’t complex narratives, but amplified emotion. From a creation standpoint, AI music video generators are reshaping music video production—turning abstract emotions into visual scenes, automatically syncing visuals with music, and enabling rapid generation of multiple styles, significantly lowering the barrier to entry.
Why does this Music Video keep going viral?
“Maria” — Hwasa
Years after its release, it’s still gaining views, even surpassing 300M+.
But what really made it break out isn’t just the music:
emotion + visuals + self-expression
1. Emotion: Raw and piercing
At its core, the song responds to external judgment:
criticism, denial, attack.
“Maria” isn’t driven by a complex storyline. Instead, it delivers an extremely direct emotional expression. The entire MV revolves around a specific emotional state: the struggle and recovery after being judged, questioned, and rejected.
It feels like a conversation with oneself—“Maria” is both a name and a self-call.
2. Core idea: A dialogue with the self
“Maria” is actually her baptismal name—a way she addresses herself.
So the MV isn’t about confronting the outside world, but about facing one’s inner self. Vulnerability and strength, breakdown and rebuilding, coexist and repeat within the same person.
This internal conflict makes it easy for viewers to project themselves into the story, creating a deep emotional resonance.
3. Visuals: Strong symbols + powerful metaphors
The MV is filled with visual metaphors:
Surrounded by pencils → verbal attacks
Blood and dining table → being “consumed” by the public
Hospital / breakdown scenes → mental pressure
Almost every visual serves metaphor. Abstract psychological states are turned into visible scenes: being surrounded, watched, consumed.
The visuals constantly shift between light and dark, control and chaos, creating a persistent sense of unease. This unstable rhythm keeps viewers emotionally engaged—not through plot, but through feeling.
4. Theme: Self-identity
When all these layers come together, the theme becomes clear:
It’s not about external judgment, but about how you face it—and how you rebuild your sense of self.
In other words, the core isn’t conflict, but self-identity.
That’s why it has lasting appeal. It doesn’t belong to one person—it belongs to anyone who has experienced doubt and rejection.
“Maria” represents a shift in Music Video storytelling:
from narrative-driven → emotion-driven.
And this is exactly where AI excels.
Sondo AI Are Changing Everything
In the past, creating a music video like this required:
actors, locations, lighting, a full team, and lots of time.
Now, with Sondo AI, everything is being redefined.
Tools like Sondo transform creation from a production process into an expression process. You no longer need to physically build scenes. Just describe an emotion—pressure, conflict, release—and Sondo AI generates the visuals. Dreamlike spaces, psychological states, abstract environments—what once required filming can now be created instantly. More importantly, AI can sync visuals to music automatically, aligning rhythm and emotion without complex editing.
1. Emotion → Instant visuals
You don’t need detailed descriptions. Just say:
pressure
loneliness
resistance
breakdown
rebirth
AI turns them into visuals.
2. Metaphors → One-click generation
What used to require shooting:
hospital scenes
cold lighting
intense symbolic imagery
Visual contrasts:
bright vs dark
glamorous vs collapsing
Now:
generated instantly and directly.
3. Rhythm → Auto-sync
music rhythm → visual rhythm
emotional shifts → camera changes
No editing skills needed.
The success of “Maria” isn’t just about content—it’s a signal of a new creative direction. What truly moves people isn’t complex production, but amplified emotion and authentic expression.
And now, with tools like Sondo, this kind of expression is no longer limited to a few.
Start Your First Music Video with Sondo AI
Use Sondo AI to turn your emotions into a music video people can actually see.