Welcome to this week’s edition of Architecture Insights.

Planting plans in landscape design can become a laborious task. The process of selecting the perfect tree and shrub species that align with your site's unique requirements can be challenging. Thankfully, we have AI tools to automate lots of the work. *Keep in mind AI in just an assistant, not a designer.*

News & Updates

1. Midjourney is testing a new feature called "consistent characters." This feature allows the generative AI service to use the same character in different images and styles while still maintaining their original design. It can currently recognize faces, hair, and clothes, but it cannot yet identify objects in renderings.

Give Midjourney the URL of a reference image for an AI-generated character. Then ask what you want your character to do, wear, or any other details, and remember to include the tag "--cref" after your request.

To control image reproduction, add the tag "-cw" followed by a number (1-100) to the prompt.

2. The software company Cognition Labs released the first official AI software engineer. A user prompts Devin with a description of the project they want to develop. It then crafts a plan to tackle the project and uses common developer tools. In demos, it built websites and apps in under 10 minutes.

It will be interesting to see the true capabilities of Devon and where it might be able to assist in creating rendering or project management software.

Resources

While we have you covered on all things AI in architecture and landscape architecture there is still lots that goes on outside our industry. Check out The Rundown for a daily general AI newsletter.

Learn how to make AI work for you.

AI won’t take your job, but a person using AI might. That’s why 500,000+ professionals read The Rundown – the free newsletter that keeps you updated on the latest AI news and teaches you how to apply it in just 5 minutes a day.

Subscribe with one click.

Planting Plans with Google Gemini

In landscape design, it is quite common for us to delve into exploring various planting palettes, yet there are instances where we find ourselves unfamiliar with what to select for our projects.

We could be working in an unfamiliar climate or environment.

ChatGPT (or an alternative chatbot, in this case we used Google Gemini to mix things up) can recommend us planting for our specific location that may help with reducing the need for irrigation, improving microclimates and the overall landscape.

Let's run through a simple prompt.

Remember to provide relevant information such as your site location, desired planting types (trees, shrubs, ground covers, perennials etc.) and anything significant to your site.

"Could you design a planting plan for a new football stadium in Seattle, Washington? (CONTEXT)

• Zone 8 Hardiness: Plants built for Seattle's climate. (CRITERIA)

• Trees + Shrubs: Fruit trees and coniferous shrubs. (CRITERIA)

• Part-Shade Champs: Plants will get 3-4 hours of afternoon shade. (CRITERIA)

• A Mix of Natives + Edibles: Native trees plus some fruiting trees/shrubs with a mix of coniferous ground covers. (CRITERIA)

List the amount of species each planting bed will have and the organization of plants.” (CRITERIA)

Why this works: It's not just a wish list. You're giving ChatGPT context for smart suggestions, while still leaving room for creative combos.

This prompt is still fairly broad but the way we format it and the level of information we give it is the important thing to understand.

Gemini returned 3-4 suggestions for both trees and shrubs, additional considerations like spacing and tree maintenance, and tips for getting even more targeted results.

Additional information can be provide for more specific results such as:

Irrigation requirements, soil type, site drainage, drought resistance, etc.

One thing to keep in mind:

AI is a helpful tool, but the human touch is still crucial. Designers use their creativity, experience, and understanding of aesthetics. AI can assist in making design choices, but it shouldn't be the sole decision-maker.

AI Image of the week

Thank you for reading this week’s issue, check past issues here. Share this newsletter with colleagues, friends, or anyone interested in the combined world of architecture and artificial intelligence.

Until next Friday,

A.I.