Flag

We stand with Ukraine and our team members from Ukraine. Here are ways you can help

Get exclusive access to thought-provoking articles, bonus podcast content, and cutting-edge whitepapers. Become a member of the UX Magazine community today!

Home ›› Artificial Intelligence ›› AI as an ideation tool: Dall-E outdoor baby carriage

AI as an ideation tool: Dall-E outdoor baby carriage

by Asbjørn Mejlvang
2 min read
Share this post on
Tweet
Share
Post
Share
Email
Print

Save

AI as an ideation tool

UX designer Asbjørn Mejlvang shows how to use Dall-E, an AI system that generates realistic visuals from a description given, to reach your design goals.

In this post, I will showcase a quick example of how to use an AI as Dall-E as a tool in the ideation process.

The object we want to design is an outdoor baby carriage for hiking.

A simplified version of an ideation process

Example of Traditional ideation

As a designer, you might create a moodboard to help you communicate a direction for yourself or others. Followed by drawing some quick ideation sketches. Finally, you then highlight your best idea with a more refined sketch.

(Apologies for the quality of my example sketches. Since I have transitioned to UX I haven’t done many product drawings.)

Moodboard

moodboard, design, baby carriage

Idea sketches

sketch, design, baby carriage

Direction sketch

sketch, design, baby carriage

Dall-E examples

Below you will see how I try different variations to point the AI in the direction I would like to explore.

The prompt sentence used is written below the generated images.

design, baby carriage, ai, dall-e
A photograph of a muddy rugged baby carriage designed for outdoor experiences on a trail in the woods on a sunny day
design, baby carriage, ai, dall-e
A product render of a rugged baby carriage with big terrain wheels inspired by outdoor clothing
design, baby carriage, ai, dall-e
A product render of a rugged and waterproof baby carriage with three big terrain wheels inspired by hiking bags with pockets
design, baby carriage, ai, dall-e
A product render of a rugged and waterproof baby carriage with dirt bike wheels
design, baby carriage, ai, dall-e
A product render of a hiking baby carriage designed by the north face
design, baby carriage, ai, dall-e
A product render of a hiking baby carriage designed by Arc’teryx

Exploring a direction with AI

Similar to traditional ideation when working with AI you can refine a direction. With Dall-E you can create variations from a selected output.

design, baby carriage, ai, dall-e

Above is the selected output and below are the variants generated from it.

design, baby carriage, ai, dall-e
design, baby carriage, ai, dall-e

Dall-E with an image prompt

Besides text inputs, Dall-E can also take an image combined with a sentence as input. It looks like this:

design, baby carriage, ai, dall-e
A product render of a rugged baby carriage with big terrain wheels
design, baby carriage, ai, dall-e
A product render of a waterproof and rugged baby carriage with mountain bike wheels

Use outputs as inputs

In my opinion, AI is fascinating and inspiring — but very hard to stir in the right direction. So for now I would not use AI output as final output, but instead, combine them with the traditional way and include the most interesting AI outputs in front of me when beginning to draw.

(I however do believe the AI beat me in this round).

post authorAsbjørn Mejlvang

Asbjørn Mejlvang

Designer interested in how improvements in tech will change how the creative process.

Tweet
Share
Post
Share
Email
Print
Ideas In Brief
  • The author gives a brief example of how to use Dall-E, an AI system that can produce art and realistic visuals from a description given in plain language, as a tool in the brainstorming process.
  • According to the author, the process of AI ideation is as simple as that:
    • Write a sentence.
    • Go through generated visuals.
    • Choose a direction to get the most accurate realization of your idea.
    • Receive generated variations from the selected output.
  • Traditional ideation process versus AI ideation process – the article covers how to combine them to get the best result in the most efficient way.

Related Articles

What if your AI didn’t just agree, but made you think harder? This piece explores why designing for pushback might be the key to smarter, more meaningful AI interactions.

Article by Charlie Gedeon
The Power of Designing for Pushback
  • The article argues that AI systems like ChatGPT are often too agreeable, missing opportunities to encourage deeper thinking.
  • It introduces the idea of “productive resistance,” where AI gently challenges users to reflect, especially in educational and high-stakes contexts.
  • The article urges designers to build AI that balances trust and pushback, helping users think critically rather than just feel validated.
Share:The Power of Designing for Pushback
6 min read

As UX research shifts and reshapes, how can researchers stay ahead? This article explores the changing landscape and how to thrive in it.

Article by James Lang
Hopeful Futures for UX Research
  • The article explores how UX research is evolving, with roles shifting and adjacent skills like creativity and knowledge management becoming more important.
  • It looks at how non-researchers are doing more research work, and how this trend challenges traditional UX research careers.
  • The piece argues that researchers can stay relevant by adapting, staying curious, and finding new ways to share their value.
Share:Hopeful Futures for UX Research
16 min read

Mashed potatoes as a lifestyle brand? When AI starts generating user personas for absurd products — and we start taking them seriously — it’s time to ask if we’ve all lost the plot. This sharp, irreverent critique exposes the real risks of using LLMs as synthetic users in UX research.

Article by Saul Wyner
Have SpudGun, Will Travel: How AI’s Agreeableness Risks Undermining UX Thinking
  • The article explores the growing use of AI-generated personas in UX research and why it’s often a shortcut with serious flaws.
  • It introduces critiques that LLMs are trained to mimic structure, not judgment. When researchers use AI as a stand-in for real users, they risk mistaking coherence for credibility and fantasy for data.
  • The piece argues that AI tools in UX should be assistants, not oracles. Trusting “synthetic users” or AI-conjured feedback risks replacing real insights with confident nonsense.
Share:Have SpudGun, Will Travel: How AI’s Agreeableness Risks Undermining UX Thinking
22 min read

Join the UX Magazine community!

Stay informed with exclusive content on the intersection of UX, AI agents, and agentic automation—essential reading for future-focused professionals.

Hello!

You're officially a member of the UX Magazine Community.
We're excited to have you with us!

Thank you!

To begin viewing member content, please verify your email.

Tell us about you. Enroll in the course.

    This website uses cookies to ensure you get the best experience on our website. Check our privacy policy and