In this post, we describe a process for creating design concepts for a new product line of soft pillows called "Sheepdreams," which are inspired by sheep. The goal of this project was to generate a set of visually compelling designs that evoke the aesthetic of a sheep while also appearing soft and appealing to users, including children. To achieve this, we employed text-to-image generation models, which is a type of generative AI model that can generate images from text descriptions.
The prompts we used resulted in several novel design concepts demonstrating the feasibility of using text-to-image models early in the idea generation process. The collage below shows some of the Sheepdreams concept pillows we obtained using this process.
These designs can be used as part of a Generative AI Business (GAIB) where a company would display a large number of product concept designs on its website, allowing customers to vote for their favorite designs. The top design would then be quickly manufactured and sold as a limited edition product. This approach could be an effective way to generate a high volume of unique and interesting designs while also utilizing the collective tastes and preferences of a large group of people.
This post is part of a series of articles on the use of generative AI for bioinspired product ideation. The use of AI for product concept generation allows for the quick creation of many potentially novel designs, which could then be evaluated and refined to select the most promising concepts to move to the next stage of the product development process.
Comments
Post a Comment