Stepping Through Art History to CapCut World LA 🎨✨ → 📍Audrey Irmas Pavilion
For the "Unexpected Arrival" theme, I wanted to blur the boundary between classic human artistry and next-gen AI filmmaking. Instead of a standard commute to Los Angeles, the journey pulls me directly through living, breathing masterpieces—from the swirling skies of Van Gogh’s The Starry Night and the crashing barrels of Hokusai’s The Great Wave, all the way to the iconic trapezoidal facade and barrel-vaulted ceiling of the Audrey Irmas Pavilion for CapCut World LA.
How I built it:
AI Generation & Continuity: Built as a connected 9-scene sequence using Seedance 2.5 inside CapCut, maintaining character consistency and fluid motion across completely distinct artistic styles and eras.
Editing & Polish in CapCut: Stitched and paced the transitions so each painting seamlessly morphs into the next dimension, combining keyframe camera momentum, color matching, and immersive sound design to make the final arrival in LA hit with maximum impact.
Why I built it:
Every era of art had its own medium—from oil on canvas and woodblock prints to digital timelines. AI and CapCut are the new canvas. I built this piece to celebrate how creative technology lets us step inside our wildest visual ideas and bring them to life in seconds.
A connected 9-scene sequence where each painting morphs into the next is ambitious, Pedro. That idea that every era had its own medium, from oil on canvas to AI, makes this feel like a real journey rather than just a montage.
Just made an introductory video of myself powered by Artificial Intelligence
A quick introduction to who I am, what I create, and how I bring ideas to life through AI-powered visuals, cinematic storytelling, and professional video editing.:
The big stacked WORK / RESULTS / RATES menu next to the loose purple stickers keeps the portfolio playful while the navigation stays easy to scan. Do the stickers react on hover, or are they tied to scroll?
A 60-second fan short made entirely with AI video, with my own face as the lead. Nine shots, seven characters, built from one selfie and a set of reference images. No cameras were used.
I started from a public prompt guide by kaye_creatives on Higgsfield and treated it like a shooting script: built my own character sheet, cast the missing character, generated each shot separately, then cut, captioned, titled and mixed it myself.
What I'd pass on to anyone trying this:
Give every reference image one job. Face, room, prop or camera angle, never two at once.
Put exact counts in the prompt. Models add people and props unless you tell them how many.
Generate long, cut short. My first assembly was 67 seconds. The final is 60, and the pace is where the quality came from.