How to make a video with artificial intelligence

Our first AI video was a mess. There were no tutorials: we had to experiment for weeks, trying and failing, just to make a scene a few seconds long. That's where our method came from — and it hasn't changed much since.

You always start from the script, never from the prompt

The work never starts with generating a clip or an image. It starts much earlier. The first step, for every video we make, is writing a script where we lay out the goal, why we're doing it, who the video is for. Before the what and the how, we think about the why and where we want to end up.

Artificial intelligence hasn't changed that. The starting point is always our own experience, what we see and live every day — then we rework it through AI to give it a new shape.

Why we don't believe in complicated prompts

We've never believed, and still don't, in 14-page Word document prompts. Ours are a few lines long: we just state the movement or the shot we're expecting. In our experience, the more complicated the prompt, the more likely the request gets misread or produces hallucinations.

It's not laziness: a simple instruction leaves the model less room to get confused, and gives us more control over what to keep and what to throw out. For a single product video, we generated more than 27,000 images.

What looks easy is usually the hardest

There's something people rarely talk about: you only ever see the final result, never how many attempts it took to get there. The scenes that look simplest — a person walking, a liquid pouring, a transition between two settings — are almost always the ones that cost the most work.

In one of our early videos we tried to have a drone fly into a stream all the way to a jug pouring water into a moka pot. An idea I really pushed for. It was a total failure in terms of time and cost. We kept it anyway, because we liked the result.

Consistency is the real problem

With generative AI you can't get five or six consistent angles of the same scene at once. A product can change shape and size with every generation. A landscape struggles to stay identical if you just change the light, from sun to rain. It's the most concrete limit we work with every day, not some marginal technical detail.

When AI isn't enough, you go back to the classic tools

The cinematic quality of a generated image can be beautiful while the real product inside it is wrong — it changes shape, loses brand details. In those cases the final step is manual: Photoshop, not another model. Knowing when to stop relying on AI and go back to traditional work is as much part of the craft as knowing how to write a prompt.

You often start over from zero

Nine times out of ten a video gets going, reaches 70% done, and then starts over from zero, because something — a setting, a tone, a character — stops convincing us. That's not a failure of the process: it is the process.

The tools change, the method doesn't

In a single project we've used at least five or six different AI tools — image generation, upscaling, video generation, editing. The tools we prefer change every few months; what we wrote above, though, is the part that never changes, no matter which model comes out next year.

If you're considering a corporate video and want to know what to expect from the process, see how we work on corporate videos. If you want to learn the full method instead, with exercises on your own material, you'll find the complete course at

NNZN Academy.