Using AI for Concept Generation in Industrial Design
Artificial Intelligence (AI) has been making significant strides in the field of art, and it’s not surprising that it’s also transforming industrial design. As a product designer, I have been experimenting with various AI tools to explore how they can enhance my design process. In this article, I will share my experience with two AI tools — Midjourney and Stable Diffusion — and how they can be used for concept generation in industrial design.
Midjourney
Midjourney is a text-to-image AI tool that generates high-quality images based on textual prompts. I was amazed by the quality of its outputs, and I immediately saw its potential for concept generation. I started by asking for a SteamPunk 6-Cylinder engine, and Midjourney generated some fantastic results. It allows you to choose one of the four variations it generates to either create variations of the same or increase the quality of it.
What I found even more useful was its ability to create new images inspired by the images I input, along with a prompt for context. I pulled an old sketch from my archive, popped it into Midjourney, and gave it a small prompt. The results were not too similar to the original sketch, but they were definitely high-top sneakers. If you’re just looking for variations that are closer to a reference sketch, Midjourney might not be for you. However, it’s an almost scarily powerful tool for concept generation.
Stable Diffusion
Stable Diffusion is another AI tool that generates images based on textual prompts and image references. I used Dreamstudio, which works similarly to Midjourney but with more control over the quality and quantity of the output. What’s cool is that you can dial in exactly how much you want the reference image to influence the output. Lower image strengths will make the sketch more loosely based on your image, and higher percentages make it closer to the image.
I imported an image reference and typed in a prompt for what I was looking for to give more context. At 50% image strength, the results were not terrible, but I could see some sketches with some resemblance. At 60%, the variations were more interesting and closer to my original sketch. At 70%, I was impressed by the quality of the outputs, and I could use them as a starting point for further development.
Conclusion
AI tools like Midjourney and Stable Diffusion are incredibly powerful for concept generation in industrial design. However, it’s important to note that they are not a replacement for human creativity and critical thinking. Rather, they are tools that can help designers explore new ideas and possibilities quickly. As AI technology continues to advance, it’s crucial for designers to be acquainted and equipped with it. By incorporating AI tools into your design process, you can stay ahead of the curve and produce innovative and exciting designs.
Overall, I have found using AI tools in my design process to be an enriching experience, and I look forward to exploring more tools and techniques in the future. If you’re a product designer, I encourage you to try out Midjourney and Stable Diffusion for yourself and see how they can enhance your design process.
Feel free to reach out to me on LinkedIn if you need any more information on this topic or have any other questions related to UX design or product development.
