4 Sept 2025
This feels like a Simpsons episode: the beginning has nothing to do with the ending. It all started as an exercise in a creative AI course. The dynamic was to play with the famous srefs in Midjourney (numbers that define the style of the images). With the sref random command you get random styles, and if you like one, you save it. Easy in theory, but then you get carried away generating images… and I ended up making 111 girls blowing bubblegum. Yes, one hundred and eleven. Because none of them convinced me. At that moment I thought I had wasted hours, that I was too picky and obsessive, that I needed to be more practical and just finish things otherwise I’ll never get anywhere… in short, I had a pile of images that were useless. But later (plot twist), that “useless material” turned out to be exactly the piece I needed.
What seemed useless ended up being the key
Meanwhile, on LinkedIn…
Aaah LinkedIn. I rarely log in, and when I do, I try to focus only on people sharing useful and practical stuff. But it’s hard… Between pseudo-AI gurus, empty quotes, corporate whining, and personal branding galore, there’s a lot of noise. And hey, I don’t mind, everyone can use their social networks however they want. But of course, if you fill it only with recycled motivational phrases, “visionary” reflections and categorical statements… well, here goes my categorical statement, but in blog highlight format:
The day you actually have something valuable to say, nobody listens. Because you’ve already bored even the algorithm
From there (and a bit of hate towards social media, why lie), came the connection: everyone saying the same thing on LinkedIn, inflating the bubble (myself included), until it pops. And when it pops, nothing is the same. And then I remembered my 111 bubblegum girls. What seemed like a waste of time ended up being the main visual piece behind POP.
I had it, but I was still missing THE scene: the bubble popping. And here comes the part people don’t usually tell about AI. They only show the pretty results and it looks like magic. Well, either I’m really clumsy (and I even used a custom GPT, the AI Video Prompt Generator for Veo2, Kling, Runway, to refine the prompts) or it’s not magic: it’s trial and error, spending credits, and crossing fingers that the model understands something from your prompts. I thought: “pfft, a bubblegum bubble popping, that must be easy for AI.” Nope. What I got in many tests was straight-up disturbing (seriously, don’t watch them before bed).
AI is not magic: it’s trial and error (and lots of outtakes)
Finally, with VEO2 and quite a bit of patience, I pulled it off. Though not on the first try (I’ve got bloopers to prove it). And I learned there’s no single model that works for everything: the best one is simply the one that adapts to what you need in that moment.
Next time, I promise to do better research on which model does what before I waste attempts like a maniac
Once I nailed the bubble, I moved on to the script and audio. I worked the script with ChatGPT to shape the narration. With version 4—not the standard one, the more creative brainstorming-friendly one (don’t ask me which exactly, because it no longer exists). For audio I used ElevenLabs with the voice Ivanna – Girl Next Door, which sounds very natural, not like an ad or a podcast host. Though again, it took some tests, because you don’t get the voice you want on the first try.
I added a café background murmur (free download) and random AI phrases with other ElevenLabs voices. Result: a messy soundscape and a casual, realistic tone.
No matter the AI hype, you still need the classics
Then came the classics: After Effects. Because in the end, the old tools are still the ones that give you full control over the result and the final polish. I used timewarp for the accelerated sequence of girls, a circular mask, and a wiggle to simulate the imperfect motion you get when blowing a bubble. I also blurred the center of the bubble, since some mouths looked way too sharp to be believable.
And Premiere for the final edit, subtitles (yellow on black, always, for readability), and audio mix with Essential Sound to give everything unity and polish.
And that’s how POP was born, a 25-second micro-story that looks simple but hides a ton of tests, errors, tweaks and learnings.
Read Next
