UGC | AirBrush AI Action Figure A creator-led social video developed for AirBrush, built around one of the app’s AI transformation features. The concept turns the creator into an action figure and uses the result itself as the hook, combining entertainment, product discovery and a simple demonstration of how the feature works inside a short social format.

0

15

PAID SOCIAL | Lucky Fours Watch Ad A performance-focused video ad created for Lucky Fours, combining product footage, bold typography, music-driven pacing and detailed sound design to give the brand a more energetic and premium social presence. The project was built around a supplied script, voiceover direction and existing product footage, with a strong focus on making each visual beat support the message rather than simply showcasing the watches.

0

23

BRANDED | Six Months to Speech — Founder-Led Social Content Six Months to Speech is a founder-led parenting brand created by Chelsea Juels, whose work is shaped by her own experience as a mother of twins and her professional background in school psychology and nutrition. For this project, I developed three short-form edits designed to serve different points in the brand’s social content journey. Rather than treating each video as an isolated Reel, the goal was to create a consistent visual and editorial language that could support different types of communication while still feeling like part of the same brand. The videos were built around Chelsea’s existing footage, with an emphasis on clear hooks, natural pacing, accessible captions, restrained motion and a warm founder-led presence. The visual system was intentionally simple and recognizable, allowing the message and Chelsea’s voice to remain central.

0

30

A little look at my workflow inside Magnific for AI teaser production. I really like building my own process instead of relying on a one-click workflow. Usually, I start with the characters first. Then I shape a loose storyboard inspired by the book/story, selecting the scenes that would actually make sense in a teaser. From there, I generate base images and use those as the foundation for multiple variations — mostly to explore different framings, compositions, and emotional tones. If you look closely, you can also see a lot of wrong generations in this board — and that’s exactly why having access to tools with generous or unlimited generation options matters so much. For this phase, tools like Nano Banana 2.0 and Kling 2.5 inside Magnific are incredibly useful, because they let me generate a large volume of images, compare, curate, discard, and refine without being overly precious too early in the process. My workflow usually looks like this: — build the characters — generate base stills — create variations for framing and continuity — select the strongest images — make light fixes / upscale where needed — test prompts and reactions in motion Once I find something that really works, I usually replicate or polish it in Kling 3.0, or sometimes re-run it in Kling 2.5 at 1080p. I mostly save Seedance for moments where I specifically want to work with audio, but honestly… it gets expensive fast 😅 If I were using Seedance more heavily, I’d probably consider a separate Dreamina plan just for that part of the workflow. What I like about working this way is that it feels much closer to an actual creative process: not just generating random beautiful shots, but developing visual consistency, testing scene logic, and building a teaser with intention. AI helps a lot — but curation, taste, and structure are still doing most of the heavy lifting.

1

78

Jessica Leonel

Video Editor | Short-Form, UGC Ads & Branded Content