Generative AI models

Unleashing the power of AI to transform your digital assets

Derivative assets

A derivative asset refers to a modified or transformed version of the original digital asset. These derivatives are created to meet specific needs, such as different file formats, resolutions or variations in content. The goal is to make the asset more suitable for various platforms or use cases, without altering the integrity of the original.

For instance, a high-resolution image can have derivatives in different resolutions for web, print or mobile applications. Those assets play a crucial role as they enable efficient distribution and utilization across diverse channels and media.

Derivative generation

Derivative generation involves the automated or manual process of creating these derivative assets from the original master asset. They can usually be generated on-the-fly or through predefined workflows. Automation reduces the manual effort required to produce derivatives and ensures consistent output quality.

Additionally, derivative generation allows users to access and use the right version of an asset that suits their specific requirements. This functionality streamlines asset management, reduces duplication, and ensures that the right content is efficiently delivered to the right audience.

Generative AI

Derivative generation can be enhanced and accelerated using different machine learning models. ML models, particularly those in the field of computer vision and image processing, can play a significant role in automating the creation of derivative assets.

A Generative AI model is a type of artificial intelligence algorithm designed to generate new content that resembles or is similar to the data it was trained on. Unlike traditional AI models that are used for classification or prediction tasks, generative models focus on creating new data rather than making decisions based on existing data.

They can be trained to recognize and understand different elements of an image, such as objects, faces, backgrounds, and other features. This understanding allows for intelligent resizing, cropping, background removal and other manipulation that produce derivatives without compromising the overall quality and aesthetics. By incorporating such capabilities, the process of derivative generation becomes more accurate and scalable.

Generative AI models have a wide range of applications, including image synthesis, text generation, music composition, video generation, and more. They are particularly valuable in creative fields and content generation tasks where producing new and original content is essential. However, they can also be used in other domains, such as data augmentation for training other machine learning models or in data generation for simulations and testing.

The following sub pages describe some of the derivative generation models offered.