Creative agency VML South Africa has built a new AI image generator tool to produce “authentic images of South African people”.
Asili AI – which stems from the Swahili word ‘Asili’ – means ‘origin’ or ‘essence’. The agency believes it captures the core mission of the AI-powered image generator: to create authentic, culturally significant African imagery that is deeply rooted in the continent’s heritage.
“As South Africans we have always struggled to get decent stock photography featuring real South African people as opposed to stereotypical or Westernised/Americanised people,” says Matthew Arnold, chief innovation officer at VML South Africa.
“This hasn’t really changed with the explosion of AI. While you can get really great quality image generation now, the lack of authentic South African training material continues to be a problem.”
The team at VML decided to address the problem by creating their own stock image solution. Asili was developed by Sphiwe Dube and Arnold, with input from Jarred Cinman and various different creative and production teams within the VML team.
“We needed to create our own stock photography that we could use in our commercial work that allows for a much more authentic African feel,” says Arnold. “With AI moving so rapidly it made sense to use AI as part of the solution to this problem.”
The tech behind the tech
Asili is based on Stable Diffusion’s Flux model. A major benefit of Asili is that it was created and trained by the same people who will be using it. An internal team spent around six months meticulously training the tool to get its outputs to the standard required for agency work.
“We sourced a large number of open-source commercially ready images, curated them to ensure they reflected real South African people and then categorised and labelled them extensively to ensure our model understands every nuance – from hair length to eye colour. It’s a very intensive training process that is continually being improved and refined on a weekly basis,” says Arnold
The biggest challenges came from scale. “Ensuring we had a big enough dataset to train the model on was paramount, to ensure we generated unique and accurate images,” says Arnold. “Additionally, scaling these images to be able to work for a wide range of commercial outputs, from digital ads to billboards, took a lot of trial and error to find the exact upscaling technique that works with our model to ensure crisp details at large sizes.”
In the rapidly advancing world of AI, VML believes it’s this kind of resourceful use of the tech to solve their own specific problems that will give agencies an edge. “Asili is a proprietary tool available to VML’s clients only,” says Arnold. “It’s accessible by VML team members at this stage and forms a significant competitive advantage for our teams.”
Asili will continue to evolve, making more types of imagery possible. “We are always refining our model,” says Arnold. “Our main focus now is increasing the number of specific South African locations (backgrounds) for images and starting to cater for other African countries as well to provide a bigger footprint of authentic African imagery.”
