Our Creative Director Gary McCartney wanted to see what all this fuss was about AI generated design.
So he logged into ChatGPT and had a chat with them.
What did we learn? Well, we did have a play with generating some images by inputting a description of a project from our web site. After some trial and mostly error we were surprised, shocked even, to find some plausible looking interpretations of the brief. None of which, we hasten to add, we would ever put in front of a client. Not that they were bad for 30 seconds’ work, but given the Frankenstein style imagery welded together from internet sources, the result is really no better than design-by-Pinterest. It's hard to see how you would generate something truly original by doing this. Overall, the process lacks the research, the observations, the interactions, the insights, that make up good design. It’s fun for a while but as a designer, if you want to actually have an idea you’re better off going for a walk.
In conversation, our artificial friend was a little cagey about the copyright aspects of the process, inferring there will be ”legal debate“. They also went to great lengths to reassure us that they weren’t going to take our jobs.
The takeout? We’re not losing sleep just yet. But it’s early days. It will get better and more sophisticated at what it does. And, yes, it has the potential to speed up all those hours of research, analysis and data sifting - it’s already doing it. For designers, it will eventually be able to generate presentable mood boards and images really quickly. It will be able to create options in form, look and feel. It will make the whole process faster. But it’s hard to imagine that it will ever replicate that one intangible aspect of being human - creativity.
So here's an abridged version of the conversation – ChatGPT, or Chatty as we like to call them, tends towards repetition and has the interpersonal skills of, well, a chat bot. Actually, a bit less engaging. So if you don’t make it to the end we won’t blame you. But hear them out - this is the future!
GM: So, ChatGPT, do you think you can design a retail experience?
ChatGPT: As an AI language model, I can certainly generate ideas and provide information. However, I do not have the ability to physically design a fully-realised retail experience.
My role is to provide information and insights that can help retailers and designers create more engaging, efficient, and effective retail spaces.
And where do you get the information to do this?
ChatGPT: As an AI language model, I have access to vast amounts of data and information from a variety of sources, including books, articles, research papers, and other online resources.
GM: Your friends Dall.E and Stable Diffusion will have a go at creating an environment though.
ChatGPT: Dall-E is a state-of-the-art AI model developed by OpenAI that is capable of generating images from textual descriptions. It can generate images of different types of environments based on textual descriptions. It is not designed to create fully-realised retail experiences.
Stable Diffusion is a powerful AI design tool that has the potential to generate designs that are tailored to specific retail spaces and target audiences. However, it should be seen as a tool to augment and enhance the work of human designers, rather than a replacement for them.
GM: So where does Dall-E find the material it uses to create these images?
ChatGPT: Dall-E does not "find" the material it uses to create these images in the traditional sense, but rather generates new images based on the input it receives.
While the images generated by Dall-E can be incredibly detailed and realistic, they are not based on existing images or physical materials.
GM: But are there copyright issues here?
ChatGPT: While Dall-E generates new images based on textual descriptions, those images may still contain elements that are protected by copyright. For example, a Dall-E-generated image may include branded products, logos, or designs that are protected by copyright or trademark. As with any new technology, the legal implications of using Dall-E-generated images will likely be subject to ongoing debate and legal interpretation.
GM: Interesting. Will there still be room in the future for the human element in the design process?
ChatGPT: While AI models like Dall-E have the potential to significantly impact the design process, there will likely still be a role for human designers in creating and refining retail spaces.
For example, human designers can consider the specific needs and preferences of the target audience for a retail space, as well as the local culture and context. AI-generated images can provide designers with new ideas and visuals of different design options, which can be used as a starting point for further refinement. The combination of human creativity and expertise with AI-generated insights and possibilities may lead to more innovative and effective retail designs in the future.
GM: But will it not be possible in the future for AI to take over those human creative roles?
ChatGPT: As AI technology continues to evolve, it may be able to analyse and interpret vast amounts of data to gain insights into consumer behaviour, cultural trends, and other relevant factors.
However, it's important to note that understanding the needs and preferences of consumers is a complex and multi-faceted task that goes beyond simply analysing data. It often involves a deep understanding of psychology, sociology, and other human-centred disciplines, as well as the ability to think creatively and adaptively in response to changing trends and contexts.
Therefore, it's likely that in the future, the role of AI in the retail design process will be one of collaboration and augmentation rather than replacement of human designers.
GM: Thank you ChatGPT - a very interesting conversation.
You're welcome Gary! It was a pleasure chatting with you and discussing the potential impact of AI on retail design. If you have any further questions, feel free to ask!
Did we do it better? A Matcha-Ya cafe - designed by McCartney Design.
Comments