AI Video Production for a Global Brand Campaign

The Brief

A global brand needed campaign videos showcasing new products, each scene based on a supplied storyboard. The challenge: AI-generated product visuals at this level need to be accurate enough for real campaign use — correct packaging, legible text, consistent product details across shots.

My Approach

The client supplied high-quality product photography and packaging assets. My job was to turn a storyboard into finished video — with all the accuracy and cinematographic quality that implies.

I used Gemini-based image generation to create start frames from the reference assets, then generated video with VEO and Kling. The pipeline required constant iteration: getting AI models to render small product details — label text, texture, packaging print — consistently and accurately is genuinely hard. Each model has its own failure modes, and developing a feel for how to prompt around them takes time and experience.

What Was Built

A series of AI-generated campaign videos, plus a ~30-second edited piece for the brand's internal presentation. The entire pipeline — from storyboard reference to final edited output — was handled end to end.

What Made It Difficult

Product and text consistency. Generative models have a strong tendency to hallucinate or smooth over fine details — exactly the details that matter most in branded content. Getting this right required a large number of controlled iterations, careful prompt engineering, and a precise understanding of how each model interprets reference imagery.

Outcome

Delivered on brief, on time, to campaign quality.