Goal: Our goal for Flaminco was to shape the cosmetic product not only as a functional FMCG category, but as a part of everyday self-expression. The main approach of the brand was based on creating a flexible and emotional visual world that adapts to the dynamic lifestyle of a young audience. The open “M” shape used in the visual system symbolizes the free, changeable and adaptive character of Flaminco. This approach ensures that the brand is distinguished not only through color and aesthetics, but also through behavior and energy. Target: The main target audience of the brand is the young generation aged 16–25, who are sensitive to visual trends, value self-expression and seek aesthetic value in the products they use daily. Flaminco was formed with a more open and contemporary approach, aimed not only at a female audience, but also at everyone who cares about their appearance and style. The goal was to create a premium brand experience that is more interactive, flexible and able to build an emotional connection in the FMCG and retail market. Result: The result was a unified and flexible visual identity system for Flaminco that stood out in retail environments and could be easily expanded across digital platforms. The resulting visual language more strongly reflected the brand’s energy, flexibility and emotional connection with a young audience. The system was developed to serve as a sustainable and adaptive foundation not only for the current product line, but also for future campaigns, new product categories and communication directions.

excellent work, this is beautiufl!

This project started with a very specific idea for how a static product visual should move.

The base artwork was created with ChatGPT and Nano Banana, but before generating the final animation, I spent time refining the prompt and defining the exact movement, camera behavior and energy we wanted.

I tested the direction with different models, including Kling 2.5, using those iterations to improve the prompt before producing the final sequence with Seedance 2.5.

The result was extremely close to what we had planned, including the animation and even the sound effect that completed the motion.

For me, this is where AI production gets interesting: the real work is not simply generating. It is art direction, prompt design, testing and refinement until the model delivers the intended result.

That line about the real work being art direction and refinement rather than generation is something I don't think most clients grasp yet, they still see 'AI made it' as the whole story. Did you end up walking the client through that process, or did they only care about the final result?